CN114118580A - Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis - Google Patents
Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis Download PDFInfo
- Publication number
- CN114118580A CN114118580A CN202111429817.7A CN202111429817A CN114118580A CN 114118580 A CN114118580 A CN 114118580A CN 202111429817 A CN202111429817 A CN 202111429817A CN 114118580 A CN114118580 A CN 114118580A
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise
- pollution
- enterprises
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 132
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004458 analytical method Methods 0.000 title claims abstract description 24
- 230000004927 fusion Effects 0.000 title claims abstract description 18
- 230000007613 environmental effect Effects 0.000 claims abstract description 59
- 238000005070 sampling Methods 0.000 claims abstract description 7
- 210000002569 neuron Anatomy 0.000 claims description 19
- 238000004519 manufacturing process Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 13
- UHOVQNZJYSORNB-UHFFFAOYSA-N Benzene Chemical compound C1=CC=CC=C1 UHOVQNZJYSORNB-UHFFFAOYSA-N 0.000 claims description 12
- YXFVVABEGXRONW-UHFFFAOYSA-N Toluene Chemical compound CC1=CC=CC=C1 YXFVVABEGXRONW-UHFFFAOYSA-N 0.000 claims description 12
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 12
- 239000010410 layer Substances 0.000 claims description 12
- 229910052760 oxygen Inorganic materials 0.000 claims description 12
- 239000001301 oxygen Substances 0.000 claims description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 230000005611 electricity Effects 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 8
- PPBRXRYQALVLMV-UHFFFAOYSA-N Styrene Chemical compound C=CC1=CC=CC=C1 PPBRXRYQALVLMV-UHFFFAOYSA-N 0.000 claims description 8
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 8
- -1 relative humidity Substances 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 7
- 239000003344 environmental pollutant Substances 0.000 claims description 7
- 231100000719 pollutant Toxicity 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 7
- OKKJLVBELUTLKV-UHFFFAOYSA-N Methanol Chemical compound OC OKKJLVBELUTLKV-UHFFFAOYSA-N 0.000 claims description 6
- CTQNGGLPUBDAKN-UHFFFAOYSA-N O-Xylene Chemical compound CC1=CC=CC=C1C CTQNGGLPUBDAKN-UHFFFAOYSA-N 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 6
- 238000009792 diffusion process Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 230000001537 neural effect Effects 0.000 claims description 6
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 239000010865 sewage Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000003449 preventive effect Effects 0.000 claims description 5
- 238000003911 water pollution Methods 0.000 claims description 5
- CSCPPACGZOOCGX-UHFFFAOYSA-N Acetone Chemical compound CC(C)=O CSCPPACGZOOCGX-UHFFFAOYSA-N 0.000 claims description 4
- HGINCPLSRVDWNT-UHFFFAOYSA-N Acrolein Chemical compound C=CC=O HGINCPLSRVDWNT-UHFFFAOYSA-N 0.000 claims description 4
- YNQLUTRBYVCPMQ-UHFFFAOYSA-N Ethylbenzene Chemical compound CCC1=CC=CC=C1 YNQLUTRBYVCPMQ-UHFFFAOYSA-N 0.000 claims description 4
- KRHYYFGTRYWZRS-UHFFFAOYSA-M Fluoride anion Chemical compound [F-] KRHYYFGTRYWZRS-UHFFFAOYSA-M 0.000 claims description 4
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 4
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 claims description 4
- URLKBWYHVLBVBO-UHFFFAOYSA-N Para-Xylene Chemical group CC1=CC=C(C)C=C1 URLKBWYHVLBVBO-UHFFFAOYSA-N 0.000 claims description 4
- QAOWNCQODCNURD-UHFFFAOYSA-N Sulfuric acid Chemical compound OS(O)(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-N 0.000 claims description 4
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 4
- 239000007789 gas Substances 0.000 claims description 4
- 229930195733 hydrocarbon Natural products 0.000 claims description 4
- 150000002430 hydrocarbons Chemical class 0.000 claims description 4
- LELOWRISYMNNSU-UHFFFAOYSA-N hydrogen cyanide Chemical compound N#C LELOWRISYMNNSU-UHFFFAOYSA-N 0.000 claims description 4
- IVSZLXZYQVIEFR-UHFFFAOYSA-N m-xylene Chemical group CC1=CC=CC(C)=C1 IVSZLXZYQVIEFR-UHFFFAOYSA-N 0.000 claims description 4
- LQNUZADURLCDLV-UHFFFAOYSA-N nitrobenzene Chemical compound [O-][N+](=O)C1=CC=CC=C1 LQNUZADURLCDLV-UHFFFAOYSA-N 0.000 claims description 4
- 229910052757 nitrogen Inorganic materials 0.000 claims description 4
- 239000007787 solid Substances 0.000 claims description 4
- 239000004071 soot Substances 0.000 claims description 4
- CWYNVVGOOAEACU-UHFFFAOYSA-N Fe2+ Chemical compound [Fe+2] CWYNVVGOOAEACU-UHFFFAOYSA-N 0.000 claims description 3
- 229910000831 Steel Inorganic materials 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 239000004568 cement Substances 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 claims description 3
- 239000010842 industrial wastewater Substances 0.000 claims description 3
- 229910052751 metal Inorganic materials 0.000 claims description 3
- 239000002184 metal Substances 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 230000002441 reversible effect Effects 0.000 claims description 3
- 239000002356 single layer Substances 0.000 claims description 3
- 239000010959 steel Substances 0.000 claims description 3
- PMJNEQWWZRSFCE-UHFFFAOYSA-N 3-ethoxy-3-oxo-2-(thiophen-2-ylmethyl)propanoic acid Chemical compound CCOC(=O)C(C(O)=O)CC1=CC=CS1 PMJNEQWWZRSFCE-UHFFFAOYSA-N 0.000 claims description 2
- MGWGWNFMUOTEHG-UHFFFAOYSA-N 4-(3,5-dimethylphenyl)-1,3-thiazol-2-amine Chemical compound CC1=CC(C)=CC(C=2N=C(N)SC=2)=C1 MGWGWNFMUOTEHG-UHFFFAOYSA-N 0.000 claims description 2
- NLHHRLWOUZZQLW-UHFFFAOYSA-N Acrylonitrile Chemical compound C=CC#N NLHHRLWOUZZQLW-UHFFFAOYSA-N 0.000 claims description 2
- 241000894006 Bacteria Species 0.000 claims description 2
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 2
- VEXZGXHMUGYJMC-UHFFFAOYSA-M Chloride anion Chemical compound [Cl-] VEXZGXHMUGYJMC-UHFFFAOYSA-M 0.000 claims description 2
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 claims description 2
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 claims description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 2
- XFXPMWWXUTWYJX-UHFFFAOYSA-N Cyanide Chemical compound N#[C-] XFXPMWWXUTWYJX-UHFFFAOYSA-N 0.000 claims description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 claims description 2
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 claims description 2
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 claims description 2
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 claims description 2
- 241001465754 Metazoa Species 0.000 claims description 2
- ZOKXTWBITQBERF-UHFFFAOYSA-N Molybdenum Chemical compound [Mo] ZOKXTWBITQBERF-UHFFFAOYSA-N 0.000 claims description 2
- JVMRPSJZNHXORP-UHFFFAOYSA-N ON=O.ON=O.ON=O.N Chemical compound ON=O.ON=O.ON=O.N JVMRPSJZNHXORP-UHFFFAOYSA-N 0.000 claims description 2
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 claims description 2
- ISWSIDIOOBJBQZ-UHFFFAOYSA-N Phenol Chemical compound OC1=CC=CC=C1 ISWSIDIOOBJBQZ-UHFFFAOYSA-N 0.000 claims description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 2
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 2
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 claims description 2
- QAOWNCQODCNURD-UHFFFAOYSA-L Sulfate Chemical compound [O-]S([O-])(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-L 0.000 claims description 2
- UCKMPCXJQFINFW-UHFFFAOYSA-N Sulphide Chemical compound [S-2] UCKMPCXJQFINFW-UHFFFAOYSA-N 0.000 claims description 2
- BZHJMEDXRYGGRV-UHFFFAOYSA-N Vinyl chloride Chemical compound ClC=C BZHJMEDXRYGGRV-UHFFFAOYSA-N 0.000 claims description 2
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 claims description 2
- MMDJDBSEMBIJBB-UHFFFAOYSA-N [O-][N+]([O-])=O.[O-][N+]([O-])=O.[O-][N+]([O-])=O.[NH6+3] Chemical compound [O-][N+]([O-])=O.[O-][N+]([O-])=O.[O-][N+]([O-])=O.[NH6+3] MMDJDBSEMBIJBB-UHFFFAOYSA-N 0.000 claims description 2
- IKHGUXGNUITLKF-XPULMUKRSA-N acetaldehyde Chemical compound [14CH]([14CH3])=O IKHGUXGNUITLKF-XPULMUKRSA-N 0.000 claims description 2
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 2
- 125000002490 anilino group Chemical class [H]N(*)C1=C([H])C([H])=C([H])C([H])=C1[H] 0.000 claims description 2
- 239000010775 animal oil Substances 0.000 claims description 2
- 239000003945 anionic surfactant Substances 0.000 claims description 2
- 229910052785 arsenic Inorganic materials 0.000 claims description 2
- RQNWIZPPADIBDY-UHFFFAOYSA-N arsenic atom Chemical compound [As] RQNWIZPPADIBDY-UHFFFAOYSA-N 0.000 claims description 2
- 229910052788 barium Inorganic materials 0.000 claims description 2
- DSAJWYNOEDNPEQ-UHFFFAOYSA-N barium atom Chemical compound [Ba] DSAJWYNOEDNPEQ-UHFFFAOYSA-N 0.000 claims description 2
- 229910052790 beryllium Inorganic materials 0.000 claims description 2
- ATBAMAFKBVZNFJ-UHFFFAOYSA-N beryllium atom Chemical compound [Be] ATBAMAFKBVZNFJ-UHFFFAOYSA-N 0.000 claims description 2
- 229910052793 cadmium Inorganic materials 0.000 claims description 2
- BDOSMKKIYDKNTQ-UHFFFAOYSA-N cadmium atom Chemical compound [Cd] BDOSMKKIYDKNTQ-UHFFFAOYSA-N 0.000 claims description 2
- 239000011575 calcium Substances 0.000 claims description 2
- 229910052791 calcium Inorganic materials 0.000 claims description 2
- 229910052799 carbon Inorganic materials 0.000 claims description 2
- QGJOPFRUJISHPQ-NJFSPNSNSA-N carbon disulfide-14c Chemical compound S=[14C]=S QGJOPFRUJISHPQ-NJFSPNSNSA-N 0.000 claims description 2
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 2
- 239000000460 chlorine Substances 0.000 claims description 2
- 229910052801 chlorine Inorganic materials 0.000 claims description 2
- 229910052804 chromium Inorganic materials 0.000 claims description 2
- 239000011651 chromium Substances 0.000 claims description 2
- JOPOVCBBYLSVDA-UHFFFAOYSA-N chromium(6+) Chemical compound [Cr+6] JOPOVCBBYLSVDA-UHFFFAOYSA-N 0.000 claims description 2
- 229910017052 cobalt Inorganic materials 0.000 claims description 2
- 239000010941 cobalt Substances 0.000 claims description 2
- GUTLYIVDDKVIGB-UHFFFAOYSA-N cobalt atom Chemical compound [Co] GUTLYIVDDKVIGB-UHFFFAOYSA-N 0.000 claims description 2
- 229910052802 copper Inorganic materials 0.000 claims description 2
- 239000010949 copper Substances 0.000 claims description 2
- 238000001704 evaporation Methods 0.000 claims description 2
- 230000008020 evaporation Effects 0.000 claims description 2
- 239000003517 fume Substances 0.000 claims description 2
- IXCSERBJSXMMFS-UHFFFAOYSA-N hydrogen chloride Substances Cl.Cl IXCSERBJSXMMFS-UHFFFAOYSA-N 0.000 claims description 2
- 229910000041 hydrogen chloride Inorganic materials 0.000 claims description 2
- 229910000037 hydrogen sulfide Inorganic materials 0.000 claims description 2
- 229910052742 iron Inorganic materials 0.000 claims description 2
- 239000011133 lead Substances 0.000 claims description 2
- 239000011777 magnesium Substances 0.000 claims description 2
- 229910052749 magnesium Inorganic materials 0.000 claims description 2
- WPBNNNQJVZRUHP-UHFFFAOYSA-L manganese(2+);methyl n-[[2-(methoxycarbonylcarbamothioylamino)phenyl]carbamothioyl]carbamate;n-[2-(sulfidocarbothioylamino)ethyl]carbamodithioate Chemical compound [Mn+2].[S-]C(=S)NCCNC([S-])=S.COC(=O)NC(=S)NC1=CC=CC=C1NC(=S)NC(=O)OC WPBNNNQJVZRUHP-UHFFFAOYSA-L 0.000 claims description 2
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 claims description 2
- 229910052753 mercury Inorganic materials 0.000 claims description 2
- 238000005272 metallurgy Methods 0.000 claims description 2
- 239000003595 mist Substances 0.000 claims description 2
- 229910052750 molybdenum Inorganic materials 0.000 claims description 2
- 239000011733 molybdenum Substances 0.000 claims description 2
- 229910052759 nickel Inorganic materials 0.000 claims description 2
- JCXJVPUVTGWSNB-UHFFFAOYSA-N nitrogen dioxide Inorganic materials O=[N]=O JCXJVPUVTGWSNB-UHFFFAOYSA-N 0.000 claims description 2
- 229940078552 o-xylene Drugs 0.000 claims description 2
- 239000003921 oil Substances 0.000 claims description 2
- 235000019198 oils Nutrition 0.000 claims description 2
- 239000002245 particle Substances 0.000 claims description 2
- 239000013618 particulate matter Substances 0.000 claims description 2
- 239000003208 petroleum Substances 0.000 claims description 2
- 150000002989 phenols Chemical class 0.000 claims description 2
- 229910052698 phosphorus Inorganic materials 0.000 claims description 2
- 239000011574 phosphorus Substances 0.000 claims description 2
- 239000011591 potassium Substances 0.000 claims description 2
- 229910052700 potassium Inorganic materials 0.000 claims description 2
- 238000001556 precipitation Methods 0.000 claims description 2
- 150000003839 salts Chemical class 0.000 claims description 2
- 229910052711 selenium Inorganic materials 0.000 claims description 2
- 239000011669 selenium Substances 0.000 claims description 2
- 229910052708 sodium Inorganic materials 0.000 claims description 2
- 239000011734 sodium Substances 0.000 claims description 2
- 235000015112 vegetable and seed oil Nutrition 0.000 claims description 2
- 239000008158 vegetable oil Substances 0.000 claims description 2
- 239000012855 volatile organic compound Substances 0.000 claims description 2
- 239000008096 xylene Substances 0.000 claims description 2
- 229910052725 zinc Inorganic materials 0.000 claims description 2
- 239000011701 zinc Substances 0.000 claims description 2
- 238000013507 mapping Methods 0.000 abstract description 4
- 230000002265 prevention Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 241001494479 Pecora Species 0.000 description 1
- 238000003723 Smelting Methods 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
- 230000005619 thermoelectricity Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000011514 vinification Methods 0.000 description 1
- 239000002912 waste gas Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis, which is characterized in that data fitting of correlation degree between power consumption data and environmental protection index data is carried out to obtain correlation mapping between the power consumption data and the environmental protection index data of different enterprises; establishing enterprise images of enterprises in a sample set from two dimensions of environmental protection index data and power utilization characteristic data, and realizing enterprise sample pollution discharge monitoring data completion based on the enterprise images and the combination of actual sampling point data of the enterprises and actual power utilization load data of the enterprises; based on the power load prediction values of the enterprises in the short term of the enterprise, the short-term pollution discharge prediction data of the enterprises in the region is obtained by combining the power consumption data of the enterprises and the environmental protection index data correlation mapping and is used as the input of the drainage basin dynamic monitoring and early warning model, so that the short-term environmental indexes in the region are predicted, and the environmental protection early warning and monitoring are realized.
Description
Technical Field
The invention relates to a pollution monitoring and early warning method, in particular to a method for monitoring and early warning a pollution source of a river basin to which a river belongs by fusing electric power and environment-friendly data.
Background
The problems that the real-time pollution discharge monitoring data of the current enterprise is lack and the early warning of regional environmental protection indexes is difficult to realize are solved.
Because the pollution control of enterprises faces the dilemma of multiple points, wide area, long line and the like, and the treatment procedures of industrial wastewater and waste gas are complicated and high in cost, part of heavily polluted enterprises only consider the benefits of the enterprises, and the phenomenon of non-obedient discharge exists.
Existing heavily polluted enterprises are often distributed in middle-east areas with developed economy and numerous industries, such as textile, printing and dyeing, wine making, medicines, building materials and the like, and are often aggregated locally; meanwhile, the monitoring data based on the environmental pollution emission monitoring station is statistical data obtained by mixing various factors, so that the tracing of the pollution source is difficult to effectively realize.
With the promotion of national electric power full coverage and ubiquitous electric power internet of things construction, electric power is essential energy for enterprise production activities, and can timely and accurately reflect the production conditions and equipment use conditions of enterprises, so that current relevant organizations realize enterprise pollution discharge monitoring by monitoring the power consumption of key enterprises, however, only part of the enterprises currently have real-time pollution discharge monitoring data, most of the enterprises (especially medium and small enterprises) only have partial available sampling point monitoring data, sample data is lack of data, and enterprise pollution discharge monitoring is difficult to realize, so that regional environment monitoring and early warning are difficult to realize.
Currently, related mechanisms realize enterprise pollution discharge monitoring by monitoring power consumption of key enterprises, for example, a document [ a monitoring method for illegal production of polluted enterprises based on power utilization law [ J ] electric power big data, 2019,22(08):35-39 ], is to set a power utilization threshold value based on the power utilization law of the polluted enterprises to study and judge illegal production, and the method can realize monitoring alarm of production stopping enterprises and shutdown alarm of environmental protection equipment, but because of production power utilization data interference in practical use, the misjudgment rate is higher; an environmental impact prediction model based on industrial power consumption is constructed by a regression analysis method in a document [ design of a special action scheme for pollution prevention and control of key enterprises based on electric power big data mining [ J ] for power supply and utilization, 2021,38(04):28-36 ], so that monitoring and early warning on atmospheric pollution prevention and control of key enterprises are realized, but follow-up impact of enterprise production on atmospheric pollution cannot be dynamically evaluated.
The method shows that the electricity utilization data can be used as an effective basis for monitoring the pollution discharge of enterprises, but depends on a linear data processing process, on one hand, the equipment, regulation and control constraint conditions of various enterprises and the obtained monitoring data indexes are different, and on the other hand, the linear training model has a cross-enterprise deviation problem in practical application, so that the pollution discharge monitoring and early warning effect is not ideal; on the other hand, the methods do not excavate the potential relevance of various factors in different time and space, short-term pollution discharge data prediction cannot be realized based on currently available data, and the delayed pollution monitoring result often leads to that the environmental management can only be used for sheep death and reinforcement.
Disclosure of Invention
A yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis comprises the following steps:
A. acquiring various types of acquired data, wherein the acquired data comprises: the method comprises the following steps of acquiring electric energy data, equipment operation data, pollution discharge monitoring data, environmental protection index data, meteorological data of an area where the enterprise is located, water area monitoring data, atmosphere monitoring data and holiday data of the enterprise with high energy consumption and high pollution;
summarizing and preprocessing the acquired data to obtain available enterprise sample data;
B. adopting multi-label classification to enterprise sample data to form an enterprise classification training sample set, wherein the labels comprise: industry labels, production scale labels, emission pollutants labels;
C. based on the same type of enterprise sample data, performing relevance analysis on the environmental protection index data and the electric energy acquisition data of the enterprise to obtain the relevance characteristics of the power utilization characteristics of the enterprise and the environmental protection index, and setting a threshold range of the environmental protection index;
D. selecting a plurality of enterprises with real-time pollution discharge monitoring data to set as typical high-pollution enterprises, acquiring environment-friendly index data of the typical high-pollution enterprises, and combining the environment-friendly index data of each typical high-pollution enterprise with respective power load curves to form load cluster data;
according to the load clustering data of each typical high-pollution enterprise, dividing the operation state of each typical high-pollution enterprise into: a full load operating state, an under load operating state and a shutdown state;
for an enterprise with real-time sewage discharge monitoring data, establishing a power utilization-environment protection index association atlas;
E. based on all enterprise classification training sample set data, constructing enterprise figures of all enterprises in a sample set from two dimensions of environment-friendly index data and enterprise electricity utilization characteristics;
F. for enterprises without pollution discharge real-time monitoring data, extracting sample characteristic data from enterprise figures of the same type of enterprises to serve as input data, calculating similarity by adopting a Pearson correlation coefficient, and taking existing enterprises with the largest similarity as similar enterprises of the enterprises without pollution discharge real-time monitoring data;
G. for an enterprise with pollution discharge real-time monitoring data, constructing a short-term power load forecasting model constructed by adopting an LSTM algorithm based on power load characteristic data of a period of history, and outputting a short-term power load forecasting value of the enterprise;
for enterprises without pollution discharge real-time monitoring data, extracting power load characteristic data of a period of history of similar enterprises, constructing a short-term power load prediction model constructed by adopting an LSTM algorithm, and outputting the short-term power load prediction value of the enterprises;
H. judging whether an enterprise has a power utilization-environment protection index correlation atlas, and if the enterprise has the power utilization-environment protection index correlation atlas, matching the power utilization load predicted value of the enterprise in a short period with the power utilization-environment protection index correlation atlas to obtain short-period pollution discharge prediction data; if the enterprise does not have the power utilization-environmental protection index correlation atlas, the power utilization-environmental protection index correlation atlas of a similar enterprise of the enterprise is combined based on the scaling factor, and then short-term pollution discharge prediction data is obtained;
comparing the short-term pollution discharge prediction data with an environmental protection index threshold range;
I. dividing river sections, peripheral atmosphere monitoring stations and high-pollution enterprises to which river watersheds belong according to distribution of an actual Geographic Information System (GIS), and creating a watershed dynamic monitoring area for each river of the watersheds;
J. the method comprises the steps of constructing a basin dynamic monitoring early warning model according to historical sewage discharge data of high-pollution enterprises in a basin dynamic monitoring area, and predicting an environmental protection index in the basin dynamic monitoring area based on acquired short-term sewage discharge prediction data, so that an environmental protection department is assisted to make preventive treatment measures in advance.
Preferably, the electric energy collection data includes: power consumer type, consumer area, consumer industry, power supply address, voltage class, transformer capacity, tariff class, voltage, current, active power, reactive power, power factor, harmonics, solar energy, maximum demand.
Preferably, the emission monitoring data includes: exhaust gas temperature of industrial exhaust gas, relative humidity, air flow rate, fresh air volume, total suspended particle boiler soot, industrial furnace soot, ringelmann's blackness, inhalable particulate matter, ammonium chromate, fluoride, hydrogen chloride, sulfuric acid mist, carbon disulfide, carbon monoxide, nitrogen dioxide, nitrogen oxides, ozone, sulfur dioxide, hydrogen sulfide, hydrogen cyanide, chlorine, phenolic compounds, catering oil fume, anilines, formaldehyde, benzene series, benzene, toluene, xylene, styrene, Total Volatile Organic Compounds (TVOC), contents of methanol, acetone, total hydrocarbons, acrylonitrile, acrolein, non-methane total hydrocarbons, acetaldehyde, vinyl chloride, nitrobenzene, methane;
water temperature, odor, conductivity, transparency, pH, total salt content, color, turbidity, suspended matter, acidity, alkalinity, hexavalent chromium, total mercury, copper, zinc, lead, cadmium, nickel, iron, manganese, beryllium, total chromium, potassium, sodium, calcium, magnesium, total hardness, total arsenic, selenium, barium, molybdenum, cobalt, dissolved oxygen, ammonia nitrogen, nitrite nitrogen, nitrate nitrogen, sulfate, total nitrogen, total phosphorus, chloride, fluoride, total cyanide, sulfide, permanganate index, biochemical oxygen demand, chemical oxygen demand, volatile phenol, petroleum, animal and vegetable oils, anionic surfactants, benzene, toluene, ethylbenzene, p-xylene, o-xylene, m-xylene, styrene content of industrial wastewater.
Preferably, the regional meteorological data includes: the daily value data of the elements of air pressure, air temperature, precipitation, evaporation capacity, relative humidity, wind direction and wind speed, sunshine hours and 0cm ground temperature.
Preferably, the water area monitoring data includes: odor, water temperature, turbidity, pH, conductivity, dissolved solids, suspended solids, total nitrogen, Total Organic Carbon (TOC) Dissolved Oxygen (DO), Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), total bacteria count, coliform content.
Preferably, the summarizing and preprocessing the acquired data includes: the method comprises the steps of data cleaning, data conversion, data normalization standardization and abnormal value deletion, so that available sample data is obtained, and the accuracy of the available sample data is improved.
Preferably, the industry label is: fossil power, steel, cement, petrochemical, chemical industry, non-ferrous metal metallurgy and others, the production scale label is: super-huge, large-sized, medium-sized, small-sized and micro-sized.
More preferably, the enterprises with the same industry label, the same production scale label and the same pollutant emission label belong to the same type of enterprise.
Preferably, the relevance analysis is performed on the environmental protection index data and the electric energy collection data of the enterprise in the following way:
C1. selecting the same type of enterprise sample data as a type of sample data set A; the type data set comprises N power utilization characteristics and M environmental protection index characteristics; sDThe selected power utilization characteristic set is initially an empty set; sHAn environment-friendly index feature set is selected, and an empty set is initially selected; fDThe method comprises the steps that a power characteristic set to be selected initially comprises N characteristics, and the N characteristics of the power characteristic set to be selected are dynamic variables changing along with time; fHThe method comprises the steps that an environment-friendly feature set to be selected initially comprises M features;
C2. calculating a candidate power feature set FDAny one of feature items F ini DAnd candidate environment-friendly feature set FHAny one of the features of
Inter-information between
The calculation formula is as follows:
wherein, the characteristic item Fi DAnd
(i 1,2, …, N, j1, 2, …, M) has a probability density distribution of
And
in order to be a discrete joint probability density,
is Fi DThe value of the characteristic at the time instant t,
is Fi DThe differential value from time t-1 to time t,
is composed of
The value of the characteristic at the time instant t,
is composed of
The difference value from t-1 to t;
because of the feature term Fi DAnd
the correlation degree changes at the same time, so that the difference value of the two at the same time is selected for correlation analysis and mutual information
Representing the degree of association between the two;
C3. setting an environmental index threshold D if
Then the feature item F is selectedi DAnd
repeating the steps C2 and C3 for the associated features until the feature set F is traversedDAnd FHCharacteristic items of interior, consisting ofThe selected power utilization characteristic set S is obtainedDAnd selecting an environmental feature set SHAnd associated feature set
More preferably, when similar enterprises are selected for the enterprises without pollution discharge real-time monitoring data, the formula for calculating the maximum similarity is as follows:
wherein, A is an enterprise without a power-environment protection index correlation diagram, and B is an enterprise with a power-environment protection index correlation diagram set; i isA(FD,FH) The relevance of the associated features included in enterprise a,
correlation characteristic correlation degree mean value, I, included for enterprise AB(FD,FH) The relevance of the associated features included by enterprise B,
is the average of the relevance of the associated features contained in enterprise B,
feature item F for Enterprise Ai DAnd
the value of the degree of association of (c),
feature item F for Enterprise Bi DAnd
cov is covariance and σ is standard deviation.
More preferably, the short-term power load forecasting model and the short-term power load forecasting value of the enterprise are constructed and obtained in the following manner:
G1. the temperature data, the data of holidays and the characteristic data of the electrical loads of enterprises are taken as an input characteristic set x of LSTM model data, an input layer is 100 neurons,
the temperature data, the holiday data and the enterprise power load characteristic data at the time t are input values xtThe predicted output value of the electrical load of the last neural unit is ht+1The two inputs have corresponding weights, and a value of 0-1 is obtained under the action of sigmoid activation, namely three gate values, and the calculation formula is as follows:
it＝σ(Wixt+Uiht-1)
ft＝σ(Wfxt+Ufht-1)
ot＝σ(Woxt+Uoht-1)
at time t, the input gate output value is itThe output value of the forgetting gate is ftThe output value of the output gate is ot，Wi、Ui、Wf、Uf、Wo、UoRespectively corresponding parameters of each door;
input value xtAnd the output h of the previous cellt+1The two values having a corresponding weight WcAnd UcAnd using the tanh activation function, the output value is equivalent to obtaining a new memory value obtained based on the input value at the time t
The calculation formula is as follows:
calculating and acquiring final memory value c of the neural unitt
ftOutput value of forgetting gate at time t, itThe output value of the input gate at time t, ct-1The final memory value of the last neuron at the time t-1;
final output value htIs composed of
The hidden layer adopts a 3-layer structure, the output layer is one-dimensional output, and the output data is the predicted value h of the short-term enterprise power loadt；
G2. Based on historical actual power load data of the enterprise at the time t and the power load predicted value h of the short-term enterprisetPerforming cross entropy operation, performing reverse feedback as a loss function, adjusting each parameter value of the neuron, and fixing each parameter value when the loss function is smaller than a set threshold value to complete the construction of a short-term power load prediction model;
G3. taking temperature data, holiday data and power load characteristic data of an enterprise at the current moment as input, and obtaining a short-term power load predicted value of the enterprise;
more preferably, the scaling factor d is calculated as follows:
wherein,
f for Enterprise Bi DThe value of the characteristic at the time instant t,
for enterprise B
At time tThe value of the characteristic is set to be,
f for Enterprise Ai DThe value of the characteristic at the time instant t,
for enterprise A
The characteristic value at time t, ∑ is
The sum of all actual sampling points of the enterprise A;
and for the enterprises without pollution discharge real-time monitoring data, multiplying the scaling factor d by the short-term pollution discharge prediction data of the similar enterprises to obtain the short-term pollution discharge prediction data of the enterprises.
More preferably, the construction process of the watershed dynamic monitoring and early warning model comprises the following steps:
J1. acquiring historical pollution discharge fitting data of high-pollution enterprises in the dynamic drainage basin monitoring area based on historical power utilization data of the high-pollution enterprises in the dynamic drainage basin monitoring area and historical short-term pollution discharge prediction data of the enterprises;
J2. taking a high-pollution enterprise sample in a river basin dynamic monitoring area as a river basin dynamic monitoring early warning model training sample (x)kH '), K ∈ (1,2, L, K), h' is pollution prediction data, wherein x is an enterprise sample, the total number of enterprises is K, and each sample data comprises historical pollution discharge data/historical pollution discharge prediction data, historical meteorological data and historical holiday data;
J3. the model is defined by adopting an LSTM algorithm structure and various parameters as shown in the step G, single-layer hidden neurons are adopted, and short-term water pollution/atmospheric pollution prediction data of a drainage basin dynamic monitoring area are output;
J4. based on a gradient descent strategy, the parameters are adjusted in the direction of the negative gradient of the target by combining the diffusion weight from the pollution monitoring point to the pollution discharge enterprise,
in the formula,
is a predicted value of pollution, h ', output at time t'tThe actual pollution value at the time t, alpha is the diffusion weight from the pollution monitoring point to the pollution discharge enterprise, and the normalization definition is carried out based on the distance and the number of the enterprises;
J5. iteratively feeding back and optimizing neuron parameters until the neuron parameters are accumulated within a self-defined time period EtIf the epsilon is less than or equal to the expected accumulated error, the training of the basin dynamic monitoring early warning model is finished;
the acquired short-term pollution discharge prediction data is combined with the acquired meteorological data and holiday data to serve as input data of the basin dynamic monitoring early warning model, and environmental protection index prediction in a basin dynamic monitoring area is output, so that an environmental protection department is assisted to make preventive treatment measures in advance
More preferably, in the step J1, if there is a small portion of real sample detection data, the historical short-term pollution discharge prediction data is corrected, and the difference data is used as feedback to update the scaling factor d in the step H, so as to improve the accuracy of the historical pollution discharge fitting data of the highly polluted enterprise.
The technical scheme provided by the invention solves the following technical problems:
1. the problem of data fitting of the correlation degree between the power utilization data and the environmental protection index data is solved. Because the correlation degree exists between the power consumption data and the environmental protection index data, but the correlation degree is changed by various factors such as time, space, environment and the like, the dynamic correlation degree is difficult to describe by a linear relation, and the sample data of the high-pollution enterprise with real-time pollution discharge data monitoring is less, so that the power consumption-environmental protection index correlation atlas of the enterprise is constructed based on the real-time monitoring data of part of available typical high-pollution enterprises, and the correlation mapping between the power consumption data and the environmental protection index data of different enterprises is obtained;
2. the problem of blowdown enterprise real-time supervision sample volume be few, only have partial sampling point data is solved. Establishing enterprise figures of enterprises in a sample set from two dimensions of environmental protection index data and power utilization characteristic data, calculating a Pearson correlation coefficient between the enterprises based on the enterprise figures, acquiring an enterprise power utilization-environmental protection index correlation map set of similar enterprises for the enterprises without real-time monitoring data, combining actual sampling point data of the enterprises with actual power utilization load data of the enterprises, acquiring pollution discharge fitting data of all enterprise samples based on a scaling factor, and realizing the completion of the pollution discharge monitoring data of the enterprise samples;
3. the problem of hysteresis quality of environmental protection early warning is solved. Based on the power load prediction values of the enterprises in the short term, the power consumption data of the enterprises in the area and the environmental protection index data are combined to be mapped in an associated mode, the short-term pollution discharge prediction data of the enterprises in the area are obtained and used as the input of a drainage basin dynamic monitoring and early warning model, so that the short-term environmental indexes in the area are predicted, and the environmental protection early warning and monitoring are realized;
4. the comprehensive monitoring of the pollution discharge data of the high-pollution enterprise is realized. A drainage basin dynamic monitoring area is established based on each river, and environmental protection index prediction in the drainage basin dynamic monitoring area is achieved from a plurality of angles of atmosphere, land infiltration, water sources, upstream and downstream influences and the like through two aspects of atmospheric pollution monitoring and water pollution monitoring and early warning.
The method is based on high real-time electric power data, combines environmental protection monitoring index data, meteorological data and holiday data, monitors and pre-warns the enterprises with the important pollution sources in the yellow river basin, on one hand, potential relation between the pollution discharge and the electricity consumption data of the enterprises is mined, on the basis of multi-label classification, enterprise figures and Pearson correlation coefficient algorithm, migration application of correlation mapping between the electricity consumption and the environmental protection indexes of the enterprises among similar enterprises is realized, LSTM algorithm and electricity consumption-environmental protection index correlation atlas matching is adopted, short-term pollution discharge prediction data of each enterprise is realized, on the other hand, the dynamic pre-warning and traceability analysis of the environmental protection indexes of the yellow river basin are realized by combining enterprise dynamic pollution discharge data with geospatial data based on fine granularity, joint defense joint control of pollution prevention and control of the important enterprises is strengthened, and cooperative control of atmosphere and water source pollution of the yellow river basin is realized.
Drawings
FIG. 1 is a flow chart of the present invention
FIG. 2 is a diagram of a neuron construction process for constructing a short-term electrical load prediction model according to the present invention
FIG. 3 is a flow chart of the construction of the basin dynamic monitoring and early warning model of the present invention
Detailed Description
As shown in fig. 1, the method for monitoring and early warning the pollution source in the yellow river basin based on the fusion analysis of power-environmental protection data, provided by the invention, comprises the following steps:
A. the method comprises the following steps of extracting various electric energy acquisition data of high-energy-consumption and high-pollution enterprises, operating data of the enterprises in operation, pollution discharge monitoring data of the enterprises and corresponding archive data, acquiring meteorological data, water area monitoring data and holiday data of the areas where the enterprises are located, summarizing the data, and finishing acquisition of available enterprise sample data, wherein the specifically acquired data comprises the following contents:
performing data preprocessing on the acquired collected data, including data cleaning, data conversion, data normalization standardization and abnormal value deletion, so as to acquire available sample data;
the data collected for each type are summarized in the following table:
B. based on sample data of each enterprise, performing multi-label classification according to industry, production scale and pollutant emission in sequence to form an enterprise classification training sample set;
wherein, the industry is according to thermoelectricity, steel, cement, petrifaction, chemical industry, non-ferrous metal smelting and the like; the production scale is divided into super-large size, medium size, small size and micro size; labeling and classifying the discharged pollutants according to the discharged pollution monitoring indexes of each enterprise; the same industry and the same scale and the same label of the discharged pollutants are divided into the same category;
C. performing relevance analysis on the environmental protection index data and the enterprise power utilization data based on the same type of enterprise sample data to obtain relevant power utilization characteristics and environmental protection index data and obtain a relevant index threshold range;
C1. based on sample data of a certain same type of enterprise as a sample data set A of the type, the sample data set of the type comprises N power utilization characteristics and M environmental protection index characteristics, SDFor selecting the power consumption feature set, the power consumption feature set is initially an empty set SHFor selecting the environmental characteristic set, an empty set is initially selected, FDInitially containing N characteristics as dynamic variable changing with time, non-static class data, FHThe method comprises the steps that an environment-friendly feature set to be selected initially comprises M features;
C2. respectively calculating a set of candidate power characteristics FDAny one of feature items F ini DAnd candidate environment-friendly feature set FHAny one of the features of
Inter-information between
The calculation formula is as follows:
wherein, the characteristic item Fi DAnd
(i 1,2, …, N, j1, 2, …, M) has a probability density distribution of
And
in order to be a discrete joint probability density,
is Fi DThe value of the characteristic at the time instant t,
is Fi DThe differential value from time t-1 to time t,
is composed of
The value of the characteristic at the time instant t,
is composed of
The difference value from t-1 to t;
because of the feature term Fi DAnd
the correlation degree changes at the same time, so that the difference value of the two at the same time is selected for correlation analysis and mutual information
Representing the degree of association between the two;
C3. set a threshold value D, if
Then the feature item F is selectedi DAnd
repeating the steps C2 and C3 for the associated features until the feature set F is traversedDAnd FHCharacteristic items in the system, thereby obtaining the selected power consumptionFeature set SDAnd selecting an environmental feature set SHAnd associated feature set
D. The method is characterized in that the same enterprise operation state is divided into a full load working state, an under load working state and a shutdown state based on part of typical high-pollution enterprise environmental protection index data with real-time pollution discharge monitoring data and combined with the same enterprise power utilization load curve clustering data, wherein the under load state can be divided into a plurality of types based on the enterprise load clustering condition. According to the associated feature set
Drawing associated features Fi DAnd
the enterprise power utilization-environmental protection index association atlas at the same time;
E. c, training sample set data of all enterprise classifications, and acquiring a power utilization characteristic set S based on the step CDSelecting an environmental feature set SHAnd associated feature set
Establishing enterprise figures of enterprises in a sample set from two associated dimensions of environmental protection index data and electricity utilization characteristic data;
F. in the same multi-label classification sample set, aiming at an enterprise A without pollution discharge real-time monitoring data, taking sample characteristic data of an enterprise image as input, adopting a Pearson correlation coefficient to carry out similarity calculation, and taking an enterprise B of an existing enterprise electricity utilization-environmental protection index association atlas with the maximum similarity as a similar enterprise of the enterprise without pollution discharge real-time monitoring data;
defining an enterprise A and an enterprise B, wherein the enterprise A does not have an enterprise electricity-environment protection index correlation diagram, the enterprise B already has an electricity-environment protection index correlation diagram set, and the maximum similarity calculation formula of the enterprise A and the enterprise B is as follows:
wherein, IA(FD,FH) The relevance of the associated features included in enterprise a,
correlation characteristic correlation degree mean value, I, included for enterprise AB(FD,FH) The relevance of the associated features included by enterprise B,
is the average of the relevance of the associated features contained in enterprise B,
feature item F for Enterprise Ai DAnd
the value of the degree of association of (c),
feature item F for Enterprise Bi DAnd
cov is covariance, σ is standard deviation;
G. based on the obtained historical power load characteristic data of the enterprises, a short-term power load forecasting model is constructed by adopting an LSTM algorithm, and power load forecasting values of the enterprises in the short term are output;
g1 takes temperature data, holiday data and enterprise electricity load characteristic data as LSTM model data input feature set x, the input layer is 100 neurons, and the construction process of each neuron is shown in FIG. 2.
The temperature data, the holiday data and the enterprise power load characteristic data at the time t are input values xtThe predicted output value of the electrical load of the last neural unit is ht+1Both inputs having corresponding weightsAnd obtaining a value of 0-1 under the action of sigmoid activation, namely three gate values, wherein the calculation formula is as follows:
it＝σ(Wixt+Uiht-1)
ft＝σ(Wfxt+Ufht-1)
ot＝σ(Woxt+Uoht-1)
at time t, the input gate output value is itThe output value of the forgetting gate is ftThe output value of the output gate is ot，Wi、Ui、Wf、Uf、Wo、UoRespectively corresponding parameters of each door;
input value xtAnd the output h of the previous cellt+1The two values having a corresponding weight WcAnd UcAnd using the tanh activation function, the output value is equivalent to obtaining a new memory value obtained based on the input value at the time t
The calculation formula is as follows:
calculating and acquiring final memory value c of the neural unitt
ftOutput value of forgetting gate at time t, itThe output value of the input gate at time t, ct-1The final memory value of the last neuron at the time t-1;
final output value htIs composed of
The hidden layer adopts a 3-layer structure, the output layer is one-dimensional output, and the output data is the predicted value h of the short-term enterprise power loadt；
G2 is based on historical actual electric load data of the enterprise at the time t and a short-term enterprise electric load predicted value htPerforming cross entropy operation, performing reverse feedback as a loss function, adjusting each parameter value of the neuron, and fixing each parameter value when the loss function is smaller than a set threshold value to complete the construction of a short-term power load prediction model;
g3, taking temperature data, holiday data and enterprise power load characteristic data of the enterprise at the current moment as input, and obtaining a short-term power load predicted value of the enterprise;
H. if the enterprise has the power utilization-environmental protection index correlation atlas, matching is carried out based on the short-term power utilization load predicted value of the enterprise to obtain short-term pollution discharge predicted data; if the enterprise does not have the power utilization-environmental protection index correlation atlas, the short-term pollution discharge prediction data of the enterprise is obtained by multiplying the scaling factor d by the short-term pollution discharge prediction data of the similar enterprise based on the scaling factor and the power utilization-environmental protection index correlation atlas of the similar enterprise obtained in the step F, and the calculation formula of the scaling factor d is as follows:
wherein,
f for Enterprise Bi DThe value of the characteristic at the time instant t,
for enterprise B
The value of the characteristic at the time instant t,
f for Enterprise Ai DThe value of the characteristic at the time instant t,
for enterprise A
The characteristic value at time t, ∑ is
The sum of all the actual sampling points of enterprise a within.
And comparing the short-term pollution discharge prediction data with the environmental protection index threshold range.
I. Dividing river sections, peripheral atmosphere monitoring stations and high-pollution enterprises to which river basins belong according to actual GIS distribution, and creating a basin dynamic monitoring area for each river of the basin;
J. aiming at historical pollution discharge data of high-pollution enterprises in a dynamic drainage basin monitoring area, a dynamic drainage basin monitoring and early warning model is respectively constructed aiming at two aspects of atmospheric pollution and water pollution, and the model construction process is shown in figure 3 and comprises the following steps:
j1 obtaining historical short-term pollution discharge prediction data of the enterprise according to the step H based on historical power utilization data of the high-pollution enterprise in the dynamic drainage basin monitoring area, correcting the historical short-term pollution discharge prediction data if a small part of sample real detection data exists, and updating the scaling factor d of the step H by using the difference data as feedback, thereby obtaining historical pollution discharge fitting data of the high-pollution enterprise in the dynamic drainage basin monitoring area;
j2 takes high-pollution enterprise samples in the river basin dynamic monitoring area as river basin dynamic monitoring early warning model training samples (x)kH '), K ∈ (1,2, L, K), h' is pollution prediction data, wherein x is an enterprise sample, the total number of enterprises is K, and each sample data comprises historical pollution discharge data/historical pollution discharge prediction data, historical meteorological data and historical holiday data;
j3, as shown in the step G, the model is defined by adopting an LSTM algorithm structure and various parameters, single-layer hidden neurons are adopted, and short-term water pollution/atmospheric pollution prediction data of the drainage basin dynamic monitoring area are output;
j4 based on gradient descent strategy, combined with diffusion weight from pollution monitoring point to pollution discharge enterprise, adjusting parameters in negative gradient direction of target,
in the formula,
is a predicted value of pollution, h ', output at time t'tThe actual pollution value at the time t, alpha is the diffusion weight from the pollution monitoring point to the pollution discharge enterprise, and the normalization definition is carried out based on the distance and the number of the enterprises;
j5 iterative feedback optimization of neuron parameters until E is accumulated within a self-defined time periodtIf the epsilon is less than or equal to the expected accumulated error, the training of the basin dynamic monitoring early warning model is finished;
and (D) outputting environmental protection index prediction in the watershed dynamic monitoring area by taking the short-term pollution discharge prediction data acquired based on the step H and combining the acquired meteorological data and holiday data as input data of the watershed dynamic monitoring early warning model, thereby assisting an environmental protection department to make preventive treatment measures in advance.
Claims (13)
1. A yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis is characterized by comprising the following steps:
A. acquiring various types of acquired data, wherein the acquired data comprises: the method comprises the following steps of acquiring electric energy data, equipment operation data, pollution discharge monitoring data, environmental protection index data, meteorological data of an area where the enterprise is located, water area monitoring data, atmosphere monitoring data and holiday data of the enterprise with high energy consumption and high pollution;
summarizing and preprocessing the acquired data to obtain available enterprise sample data;
B. adopting multi-label classification to enterprise sample data to form an enterprise classification training sample set, wherein the labels comprise: industry labels, production scale labels, emission pollutants labels;
C. based on the same type of enterprise sample data, performing relevance analysis on the environmental protection index data and the electric energy acquisition data of the enterprise to obtain the relevance characteristics of the power utilization characteristics of the enterprise and the environmental protection index, and setting a threshold range of the environmental protection index;
D. selecting a plurality of enterprises with real-time pollution discharge monitoring data to set as typical high-pollution enterprises, acquiring environment-friendly index data of the typical high-pollution enterprises, and combining the environment-friendly index data of each typical high-pollution enterprise with respective power load curves to form load cluster data;
according to the load clustering data of each typical high-pollution enterprise, dividing the operation state of each typical high-pollution enterprise into: a full load operating state, an under load operating state and a shutdown state;
for an enterprise with real-time sewage discharge monitoring data, establishing a power utilization-environment protection index association atlas;
E. based on all enterprise classification training sample set data, constructing enterprise figures of all enterprises in a sample set from two dimensions of environment-friendly index data and enterprise electricity utilization characteristics;
F. for enterprises without pollution discharge real-time monitoring data, extracting sample characteristic data from enterprise figures of the same type of enterprises to serve as input data, calculating similarity by adopting a Pearson correlation coefficient, and taking existing enterprises with the largest similarity as similar enterprises of the enterprises without pollution discharge real-time monitoring data;
G. for an enterprise with pollution discharge real-time monitoring data, constructing a short-term power load forecasting model constructed by adopting an LSTM algorithm based on power load characteristic data of a period of history, and outputting a short-term power load forecasting value of the enterprise;
for enterprises without pollution discharge real-time monitoring data, extracting power load characteristic data of a period of history of similar enterprises, constructing a short-term power load prediction model constructed by adopting an LSTM algorithm, and outputting the short-term power load prediction value of the enterprises;
H. judging whether an enterprise has a power utilization-environment protection index correlation atlas, and if the enterprise has the power utilization-environment protection index correlation atlas, matching the power utilization load predicted value of the enterprise in a short period with the power utilization-environment protection index correlation atlas to obtain short-period pollution discharge prediction data; if the enterprise does not have the power utilization-environmental protection index correlation atlas, the power utilization-environmental protection index correlation atlas of a similar enterprise of the enterprise is combined based on the scaling factor, and then short-term pollution discharge prediction data is obtained;
comparing the short-term pollution discharge prediction data with an environmental protection index threshold range;
I. dividing river sections, peripheral atmosphere monitoring stations and high-pollution enterprises to which river watersheds belong according to distribution of an actual Geographic Information System (GIS), and creating a watershed dynamic monitoring area for each river of the watersheds;
J. the method comprises the steps of constructing a basin dynamic monitoring early warning model according to historical sewage discharge data of high-pollution enterprises in a basin dynamic monitoring area, and predicting an environmental protection index in the basin dynamic monitoring area based on acquired short-term sewage discharge prediction data, so that an environmental protection department is assisted to make preventive treatment measures in advance.
2. The yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis of claim 1, wherein the electric energy collection data comprises: power consumer type, consumer area, consumer industry, power supply address, voltage class, transformer capacity, tariff class, voltage, current, active power, reactive power, power factor, harmonics, solar energy, maximum demand.
3. The yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis according to claim 1, wherein the pollution discharge monitoring data comprises: exhaust gas temperature of industrial exhaust gas, relative humidity, air flow rate, fresh air volume, total suspended particle boiler soot, industrial furnace soot, ringelmann's blackness, inhalable particulate matter, ammonium chromate, fluoride, hydrogen chloride, sulfuric acid mist, carbon disulfide, carbon monoxide, nitrogen dioxide, nitrogen oxides, ozone, sulfur dioxide, hydrogen sulfide, hydrogen cyanide, chlorine, phenolic compounds, catering oil fume, anilines, formaldehyde, benzene series, benzene, toluene, xylene, styrene, Total Volatile Organic Compounds (TVOC), contents of methanol, acetone, total hydrocarbons, acrylonitrile, acrolein, non-methane total hydrocarbons, acetaldehyde, vinyl chloride, nitrobenzene, methane;
water temperature, odor, conductivity, transparency, pH, total salt content, color, turbidity, suspended matter, acidity, alkalinity, hexavalent chromium, total mercury, copper, zinc, lead, cadmium, nickel, iron, manganese, beryllium, total chromium, potassium, sodium, calcium, magnesium, total hardness, total arsenic, selenium, barium, molybdenum, cobalt, dissolved oxygen, ammonia nitrogen, nitrite nitrogen, nitrate nitrogen, sulfate, total nitrogen, total phosphorus, chloride, fluoride, total cyanide, sulfide, permanganate index, biochemical oxygen demand, chemical oxygen demand, volatile phenol, petroleum, animal and vegetable oils, anionic surfactants, benzene, toluene, ethylbenzene, p-xylene, o-xylene, m-xylene, styrene content of industrial wastewater.
4. The yellow river basin pollution source monitoring and early warning method based on power-environmental protection data fusion analysis of claim 1, wherein the regional meteorological data comprises: the daily value data of the elements of air pressure, air temperature, precipitation, evaporation capacity, relative humidity, wind direction and wind speed, sunshine hours and 0cm ground temperature.
5. The method for monitoring and early warning pollution sources in the yellow river basin based on electric power-environmental protection data fusion analysis of claim 1, wherein the water area monitoring data comprises: odor, water temperature, turbidity, pH, conductivity, dissolved solids, suspended solids, total nitrogen, Total Organic Carbon (TOC) Dissolved Oxygen (DO), Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), total bacteria count, coliform content.
6. The yellow river basin pollution source monitoring and early warning method based on power-environmental protection data fusion analysis according to claim 1, wherein the summarizing and preprocessing of the collected data comprises: the method comprises the steps of data cleaning, data conversion, data normalization standardization and abnormal value deletion, so that available sample data is obtained, and the accuracy of the available sample data is improved.
7. The yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis according to claim 1, wherein the industry label is as follows: fossil power, steel, cement, petrochemical, chemical industry, non-ferrous metal metallurgy and others, the production scale label is: super-huge, large-sized, medium-sized, small-sized and micro-sized.
8. The yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis according to claim 7, wherein enterprises with the same industry label, the same production scale label and the same pollutant emission label belong to the same type of enterprise.
9. The yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis according to any one of claims 1 to 8, characterized in that relevance analysis is performed on environmental protection index data and electric energy collection data of enterprises in the following way:
C1. selecting the same type of enterprise sample data as a type of sample data set A; the type data set comprises N power utilization characteristics and M environmental protection index characteristics; sDThe selected power utilization characteristic set is initially an empty set; sHAn environment-friendly index feature set is selected, and an empty set is initially selected; fDThe method comprises the steps that a power characteristic set to be selected initially comprises N characteristics, and the N characteristics of the power characteristic set to be selected are dynamic variables changing along with time; fHThe method comprises the steps that an environment-friendly feature set to be selected initially comprises M features;
C2. calculating a candidate power feature set FDAny one of feature items F ini DAnd candidate environment-friendly feature set FHIn (1)A characteristic item
Inter-information between
The calculation formula is as follows:
wherein, the characteristic item Fi DAnd
has a probability density distribution of
And
in order to be a discrete joint probability density,
is Fi DThe value of the characteristic at the time instant t,
is Fi DThe differential value from time t-1 to time t,
is composed of
The value of the characteristic at the time instant t,
is composed of
The difference value from t-1 to t;
because of the feature term Fi DAnd
the correlation degree changes at the same time, so that the difference value of the two at the same time is selected for correlation analysis and mutual information
Representing the degree of association between the two;
C3. setting an environmental index threshold D if
Then the feature item F is selectedi DAnd
repeating the steps C2 and C3 for the associated features until the feature set F is traversedDAnd FHThe feature items in the system are obtained, and a selected electricity utilization feature set S is obtainedDAnd selecting an environmental feature set SHAnd associated feature set
10. The method for monitoring and warning the pollution sources in the yellow river basin based on the power-environment-friendly data fusion analysis as claimed in claim 9, wherein when similar enterprises are selected for enterprises without pollution discharge real-time monitoring data, the formula for calculating the maximum similarity is as follows:
wherein, A is an enterprise without a power-environment protection index correlation diagram, and B is an enterprise with a power-environment protection index correlation diagram set; i isA(FD,FH) The relevance of the associated features included in enterprise a,
correlation characteristic correlation degree mean value, I, included for enterprise AB(FD,FH) The relevance of the associated features included by enterprise B,
is the average of the relevance of the associated features contained in enterprise B,
feature item F for Enterprise Ai DAnd
the value of the degree of association of (c),
feature item F for Enterprise Bi DAnd
cov is covariance and σ is standard deviation.
11. The yellow river basin pollution source monitoring and early warning method based on power-environmental protection data fusion analysis according to claim 10, wherein the short-term power load forecasting model and the short-term power load forecasting value of an enterprise are constructed and obtained in the following way:
G1. the temperature data, the data of holidays and the characteristic data of the electrical loads of enterprises are taken as an input characteristic set x of LSTM model data, an input layer is 100 neurons,
air temperature data, holiday data, enterprise at time tThe characteristic data of the industrial electrical load is an input value xtThe predicted output value of the electrical load of the last neural unit is ht+1The two inputs have corresponding weights, and a value of 0-1 is obtained under the action of sigmoid activation, namely three gate values, and the calculation formula is as follows:
it＝σ(Wixt+Uiht-1)
ft＝σ(Wfxt+Ufht-1)
ot＝σ(Woxt+Uoht-1)
at time t, the input gate output value is itThe output value of the forgetting gate is ftThe output value of the output gate is ot，Wi、Ui、Wf、Uf、Wo、UoRespectively corresponding parameters of each door;
input value xtAnd the output h of the previous cellt-1The two values having a corresponding weight WcAnd UcAnd using the tanh activation function, the output value is equivalent to obtaining a new memory value obtained based on the input value at the time t
The calculation formula is as follows:
calculating and acquiring final memory value c of the neural unitt
ftOutput value of forgetting gate at time t, itThe output value of the input gate at time t, ct-1The final memory value of the last neuron at the time t-1;
final output value htIs composed of
The hidden layer adopts a 3-layer structure, the output layer is one-dimensional output, and the output data is the predicted value h of the short-term enterprise power loadt；
G2. Based on historical actual power load data of the enterprise at the time t and the power load predicted value h of the short-term enterprisetPerforming cross entropy operation, performing reverse feedback as a loss function, adjusting each parameter value of the neuron, and fixing each parameter value when the loss function is smaller than a set threshold value to complete the construction of a short-term power load prediction model;
G3. taking temperature data, holiday data and power load characteristic data of an enterprise at the current moment as input, and obtaining a short-term power load predicted value of the enterprise;
more preferably, the scaling factor d is calculated as follows:
wherein,
f for Enterprise Bi DThe value of the characteristic at the time instant t,
for enterprise B
The value of the characteristic at the time instant t,
f for Enterprise Ai DThe value of the characteristic at the time instant t,
for enterprise A
The characteristic value at time t, ∑ is
The sum of all actual sampling points of the enterprise A;
and for the enterprises without pollution discharge real-time monitoring data, multiplying the scaling factor d by the short-term pollution discharge prediction data of the similar enterprises to obtain the short-term pollution discharge prediction data of the enterprises.
12. The yellow river basin pollution source monitoring and early warning method of electric power-environmental protection data fusion analysis of claim 11, wherein the basin dynamic monitoring and early warning model building process is as follows:
J1. acquiring historical pollution discharge fitting data of high-pollution enterprises in the dynamic drainage basin monitoring area based on historical power utilization data of the high-pollution enterprises in the dynamic drainage basin monitoring area and historical short-term pollution discharge prediction data of the enterprises;
J2. taking a high-pollution enterprise sample in a river basin dynamic monitoring area as a river basin dynamic monitoring early warning model training sample (x)kH '), K ∈ (1,2, L, K), h' is pollution prediction data, wherein x is an enterprise sample, the total number of enterprises is K, and each sample data comprises historical pollution discharge data/historical pollution discharge prediction data, historical meteorological data and historical holiday data;
J3. the model is defined by adopting an LSTM algorithm structure and various parameters as shown in the step G, single-layer hidden neurons are adopted, and short-term water pollution/atmospheric pollution prediction data of a drainage basin dynamic monitoring area are output;
J4. based on a gradient descent strategy, the parameters are adjusted in the direction of the negative gradient of the target by combining the diffusion weight from the pollution monitoring point to the pollution discharge enterprise,
in the formula,
is a predicted value of pollution, h ', output at time t'tThe actual pollution value at the time t, alpha is the diffusion weight from the pollution monitoring point to the pollution discharge enterprise, and the normalization definition is carried out based on the distance and the number of the enterprises;
J5. iteratively feeding back and optimizing neuron parameters until the neuron parameters are accumulated within a self-defined time period EtIf the epsilon is less than or equal to the expected accumulated error, the training of the basin dynamic monitoring early warning model is finished;
the acquired short-term pollution discharge prediction data is combined with the acquired meteorological data and holiday data to serve as input data of the basin dynamic monitoring early warning model, and environmental protection index prediction in a basin dynamic monitoring area is output, so that an environmental protection department is assisted to make preventive treatment measures in advance
13. The yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis according to claim 12, wherein in the step J1, if a small portion of sample real detection data exists, historical short-term pollution discharge prediction data is corrected, and the difference data is used as feedback to update the scaling factor d of the step H, so that the accuracy of historical pollution discharge fitting data of highly polluted enterprises is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111429817.7A CN114118580B (en) | 2021-11-29 | 2021-11-29 | Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111429817.7A CN114118580B (en) | 2021-11-29 | 2021-11-29 | Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114118580A true CN114118580A (en) | 2022-03-01 |
| CN114118580B CN114118580B (en) | 2023-04-07 |
Family
ID=80371114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111429817.7A Active CN114118580B (en) | 2021-11-29 | 2021-11-29 | Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114118580B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114819773A (en) * | 2022-06-29 | 2022-07-29 | 天津大学 | Enterprise green production management and control method and system based on big data |
| CN114997310A (en) * | 2022-06-02 | 2022-09-02 | 河南省开封生态环境监测中心 | Environment-friendly monitoring data processing method and system |
| CN115471145A (en) * | 2022-11-15 | 2022-12-13 | 碳管家智能云平台有限公司 | Enterprise energy consumption double-control management method, device and medium |
| CN115689396A (en) * | 2022-12-30 | 2023-02-03 | 天津友美环保科技有限公司 | Pollutant discharge control method, device, equipment and medium |
| CN115860590A (en) * | 2023-03-02 | 2023-03-28 | 广东慧航天唯科技有限公司 | Intelligent analysis early warning method and system for enterprise emission pollution data |
| CN115908082A (en) * | 2023-01-06 | 2023-04-04 | 佰聆数据股份有限公司 | Enterprise pollution discharge monitoring method and device based on electricity utilization characteristic indexes |
| CN116434857A (en) * | 2023-03-24 | 2023-07-14 | 青岛思普润水处理股份有限公司 | Intelligent dosing setting method of sewage treatment system |
| CN116976733A (en) * | 2023-07-31 | 2023-10-31 | 青岛熙正数字科技有限公司 | Atmospheric pollution source on-line monitoring data evaluation system based on big data |
| CN117335416A (en) * | 2023-11-24 | 2024-01-02 | 国网浙江省电力有限公司 | Method, device, equipment and storage medium for optimizing power load |
| CN117455124A (en) * | 2023-12-25 | 2024-01-26 | 杭州烛微智能科技有限责任公司 | Environment-friendly equipment monitoring method, system, medium and electronic equipment for enterprises |
| CN117829614A (en) * | 2024-03-06 | 2024-04-05 | 四川国蓝中天环境科技集团有限公司 | Industrial enterprise pollution discharge risk classification calculation method based on multi-source data fusion |
| CN118396193A (en) * | 2024-06-27 | 2024-07-26 | 国网山东省电力公司营销服务中心(计量中心) | Transformer reverse heavy/overload early warning method and system based on neural network |
| CN118569890A (en) * | 2024-07-29 | 2024-08-30 | 张家港保税区达安进口汽车检验有限公司 | Whole car operating mode tail gas emission test system |
| CN118710327A (en) * | 2024-08-29 | 2024-09-27 | 北京市生态环境监测中心 | Enterprise gas-related pollution discharge link production behavior prediction method based on equipment power consumption |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651200A (en) * | 2016-12-29 | 2017-05-10 | 中国西电电气股份有限公司 | Electrical load management method and system for industrial enterprise aggregate user |
| CN109242169A (en) * | 2018-08-28 | 2019-01-18 | 贵州电网有限责任公司 | A kind of short-term load forecasting method towards large power customers |
| CN110991700A (en) * | 2019-11-08 | 2020-04-10 | 北京博望华科科技有限公司 | Weather and electricity utilization correlation prediction method and device based on deep learning improvement |
| AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
| CN113298422A (en) * | 2021-06-16 | 2021-08-24 | 福建亿力优能电力科技有限公司 | Pollution source enterprise illegal production monitoring method based on electricity consumption data |
-
2021
- 2021-11-29 CN CN202111429817.7A patent/CN114118580B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651200A (en) * | 2016-12-29 | 2017-05-10 | 中国西电电气股份有限公司 | Electrical load management method and system for industrial enterprise aggregate user |
| CN109242169A (en) * | 2018-08-28 | 2019-01-18 | 贵州电网有限责任公司 | A kind of short-term load forecasting method towards large power customers |
| CN110991700A (en) * | 2019-11-08 | 2020-04-10 | 北京博望华科科技有限公司 | Weather and electricity utilization correlation prediction method and device based on deep learning improvement |
| AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
| CN113298422A (en) * | 2021-06-16 | 2021-08-24 | 福建亿力优能电力科技有限公司 | Pollution source enterprise illegal production monitoring method based on electricity consumption data |
Non-Patent Citations (2)
| Title |
|---|
| 林琳等: "基于空气质量指数与k近邻理论的居民用电负荷超短期预测研究", 《电子测量技术》 * |
| 郑一新等: "基于GIS的工业水污染调查研究――以滇池流域为例", 《环境保护科学》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997310A (en) * | 2022-06-02 | 2022-09-02 | 河南省开封生态环境监测中心 | Environment-friendly monitoring data processing method and system |
| CN114997310B (en) * | 2022-06-02 | 2024-11-05 | 河南省开封生态环境监测中心 | Environment-friendly monitoring data processing method and system |
| CN114819773A (en) * | 2022-06-29 | 2022-07-29 | 天津大学 | Enterprise green production management and control method and system based on big data |
| CN115471145A (en) * | 2022-11-15 | 2022-12-13 | 碳管家智能云平台有限公司 | Enterprise energy consumption double-control management method, device and medium |
| CN115471145B (en) * | 2022-11-15 | 2024-06-04 | 碳管家智能云平台有限公司 | Dual-control management method, device and medium for enterprise energy consumption |
| CN115689396A (en) * | 2022-12-30 | 2023-02-03 | 天津友美环保科技有限公司 | Pollutant discharge control method, device, equipment and medium |
| CN115689396B (en) * | 2022-12-30 | 2023-08-08 | 天津友美环保科技有限公司 | Pollutant emission control method, device, equipment and medium |
| CN115908082A (en) * | 2023-01-06 | 2023-04-04 | 佰聆数据股份有限公司 | Enterprise pollution discharge monitoring method and device based on electricity utilization characteristic indexes |
| CN115860590A (en) * | 2023-03-02 | 2023-03-28 | 广东慧航天唯科技有限公司 | Intelligent analysis early warning method and system for enterprise emission pollution data |
| CN115860590B (en) * | 2023-03-02 | 2023-04-28 | 广东慧航天唯科技有限公司 | Intelligent analysis and early warning method and system for enterprise emission pollution data |
| CN116434857B (en) * | 2023-03-24 | 2024-03-15 | 青岛思普润水处理股份有限公司 | Intelligent dosing setting method of sewage treatment system |
| CN116434857A (en) * | 2023-03-24 | 2023-07-14 | 青岛思普润水处理股份有限公司 | Intelligent dosing setting method of sewage treatment system |
| CN116976733B (en) * | 2023-07-31 | 2024-04-02 | 青岛熙正数字科技有限公司 | Atmospheric pollution source on-line monitoring data evaluation system based on big data |
| CN116976733A (en) * | 2023-07-31 | 2023-10-31 | 青岛熙正数字科技有限公司 | Atmospheric pollution source on-line monitoring data evaluation system based on big data |
| CN117335416B (en) * | 2023-11-24 | 2024-03-01 | 国网浙江省电力有限公司 | Method, device, equipment and storage medium for optimizing power load |
| CN117335416A (en) * | 2023-11-24 | 2024-01-02 | 国网浙江省电力有限公司 | Method, device, equipment and storage medium for optimizing power load |
| CN117455124B (en) * | 2023-12-25 | 2024-03-08 | 杭州烛微智能科技有限责任公司 | Environment-friendly equipment monitoring method, system, medium and electronic equipment for enterprises |
| CN117455124A (en) * | 2023-12-25 | 2024-01-26 | 杭州烛微智能科技有限责任公司 | Environment-friendly equipment monitoring method, system, medium and electronic equipment for enterprises |
| CN117829614A (en) * | 2024-03-06 | 2024-04-05 | 四川国蓝中天环境科技集团有限公司 | Industrial enterprise pollution discharge risk classification calculation method based on multi-source data fusion |
| CN117829614B (en) * | 2024-03-06 | 2024-05-07 | 四川国蓝中天环境科技集团有限公司 | Industrial enterprise pollution discharge risk classification calculation method based on multi-source data fusion |
| CN118396193A (en) * | 2024-06-27 | 2024-07-26 | 国网山东省电力公司营销服务中心(计量中心) | Transformer reverse heavy/overload early warning method and system based on neural network |
| CN118569890A (en) * | 2024-07-29 | 2024-08-30 | 张家港保税区达安进口汽车检验有限公司 | Whole car operating mode tail gas emission test system |
| CN118710327A (en) * | 2024-08-29 | 2024-09-27 | 北京市生态环境监测中心 | Enterprise gas-related pollution discharge link production behavior prediction method based on equipment power consumption |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114118580B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114118580B (en) | Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis | |
| Ye et al. | Tackling environmental challenges in pollution controls using artificial intelligence: A review | |
| Bagherzadeh et al. | Prediction of energy consumption and evaluation of affecting factors in a full-scale WWTP using a machine learning approach | |
| Singh et al. | Artificial intelligence and machine learning-based monitoring and design of biological wastewater treatment systems | |
| Ihsanullah et al. | Recent advances in applications of artificial intelligence in solid waste management: A review | |
| Farhi et al. | Prediction of wastewater treatment quality using LSTM neural network | |
| Cheng et al. | Forecasting of wastewater treatment plant key features using deep learning-based models: A case study | |
| Farzin et al. | Introducing a framework for modeling of drug electrochemical removal from wastewater based on data mining algorithms, scatter interpolation method, and multi criteria decision analysis (DID) | |
| Haiyan | Assessment and prediction of overall environmental quality of Zhuzhou City, Hunan Province, China | |
| Abbasi et al. | Monthly and seasonal modeling of municipal waste generation using radial basis function neural network | |
| CN112465206B (en) | Water resource optimization configuration and optimization result evaluation feedback method | |
| CN113313399A (en) | Underground water pollution tracing method based on characteristic pollutant source analysis | |
| Yang et al. | Cloud-model-based feature engineering to analyze the energy–water nexus of a full-scale wastewater treatment plant | |
| Yang et al. | Cloud model driven assessment of interregional water ecological carrying capacity and analysis of its spatial-temporal collaborative relation | |
| Aldaghi et al. | The evaluation of wastewater treatment plant performance: A data mining approach | |
| Sheik et al. | Machine learning-based design and monitoring of algae blooms: Recent trends and future perspectives–A short review | |
| Narayanan et al. | Artificial intelligence driven advances in wastewater treatment: Evaluating techniques for sustainability and efficacy in global facilities | |
| Hou et al. | Integrated machine learning methods with oversampling technique for regional suitability prediction of waste-to-energy incineration projects | |
| Nejsum et al. | Population dynamics of Ascaris suum in trickle-infected pigs | |
| Valente et al. | Fuzzy modelling of acid mine drainage environments using geochemical, ecological and mineralogical indicators | |
| Olatunji et al. | Evolutionary optimization of biogas production from food, fruit, and vegetable (FFV) waste | |
| Abba et al. | Bio-communal wastewater treatment plant real-time modeling using an intelligent meta-heuristic approach: A sustainable and green ecosystem | |
| Liu et al. | An air quality grade forecasting approach based on ensemble learning | |
| Lu et al. | Feature fusion improves performance and interpretability of machine learning models in identifying soil pollution of potentially contaminated sites | |
| Wang et al. | Artificial intelligence algorithm application in wastewater treatment plants: Case study for COD load prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |