CN108562709A - A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine - Google Patents
A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine Download PDFInfo
- Publication number
- CN108562709A CN108562709A CN201810378369.4A CN201810378369A CN108562709A CN 108562709 A CN108562709 A CN 108562709A CN 201810378369 A CN201810378369 A CN 201810378369A CN 108562709 A CN108562709 A CN 108562709A
- Authority
- CN
- China
- Prior art keywords
- convolution
- learning machine
- extreme learning
- coder
- sewage disposal
- 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.)
- Pending
Links
- 239000010865 sewage Substances 0.000 title claims abstract description 35
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 11
- 230000009467 reduction Effects 0.000 claims abstract description 5
- 230000005856 abnormality Effects 0.000 claims abstract description 4
- 239000003814 drug Substances 0.000 claims abstract description 3
- 229940079593 drug Drugs 0.000 claims abstract description 3
- 238000012986 modification Methods 0.000 claims abstract description 3
- 230000004048 modification Effects 0.000 claims abstract description 3
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 8
- 238000005273 aeration Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000005284 excitation Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 238000000386 microscopy Methods 0.000 claims description 2
- 230000001537 neural effect Effects 0.000 claims description 2
- 239000010802 sludge Substances 0.000 claims description 2
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims 1
- 230000009471 action Effects 0.000 claims 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims 1
- 238000007689 inspection Methods 0.000 claims 1
- 229910052760 oxygen Inorganic materials 0.000 claims 1
- 239000001301 oxygen Substances 0.000 claims 1
- 229910052698 phosphorus Inorganic materials 0.000 claims 1
- 239000011574 phosphorus Substances 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241001236093 Bulbophyllum maximum Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
- G01N33/1806—Biological oxygen demand [BOD] or chemical oxygen demand [COD]
-
- 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
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Medicinal Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Food Science & Technology (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Biodiversity & Conservation Biology (AREA)
- Emergency Medicine (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a kind of based on convolution from the sewage disposal system monitoring and pre-alarming method of coder extreme learning machine, the method includes：Data pre-processing unit, the correlation water factor data for being obtained from sewage treatment plant carry out noise reduction, rejecting abnormalities value, smooth and standardization；Unit, for according to pretreated data, establishing convolution from coder extreme learning machine model, being learnt；As a result output unit, for, from coder extreme learning machine model, obtaining sewage treatment plant's outlet water quality prediction value using convolution；Whether early warning decision unit determines alert status level, timely feedbacks for the predicted value according to outlet water quality, and provide and need to carry out process modification, parameter regulation, the respective handlings decision such as increase and decrease of drug dosage.The present invention is by the prediction and early warning to sewage disposal system effluent quality situation, so that each monitoring personnel understands the operating status of sewage disposal system in time, realizes that dynamic manages, improves treatment effeciency.
Description
Technical field
The present invention relates to a kind of based on convolution from the sewage disposal system monitoring and pre-alarming method of coder extreme learning machine, specifically
It is the sewage disposal system water quality early-warning method based on convolution self-encoding encoder extreme learning machine that ground, which is said,.
Background technology
With being increasingly enhanced for China's environmental management dynamics, the requirement to sewage disposal system effluent quality is also increasingly tight
How lattice rationally reduce process operation cost under the premise of meeting relevant national standard, become sewage disposal system i.e. by face
The new issue faced.
Change of water quality causes significant Spatial-Temporal Variability because being influenced by factors so that the ductility when problem is existing,
The features such as structural relationship, uncertainty, non-linear show certain tendency again.The variation tendency for predicting water quality, can be with
It is apparent from water quality condition and carries out early warning, provide reference frame for treatment process robot control system(RCS), exist to sewage disposal system
Ensure under the premise of purification efficiency with lower cost stable operation has actively and important role.
Traditional recurrence and time series models is typically based on some mathematical theories and it is assumed that by deducting foundation
Mathematical model is difficult abundant essence, the feature of immanent structure and complexity for disclosing dynamic data.In recent years, machine learning and depth
Degree study is widely used in Nonlinear Time Series, achieves good prediction effect.This depends primarily on its generalization
Energy is good, difficulty in computation is low, study is pored over soon, has universal adaptability.In water quality prediction analysis, machine learning and depth
Degree study is increasingly becoming the focus for analysis and research of numerous scholars.Present invention combination machine learning and deep learning
Sewage disposal system effluent quality is predicted, the precision of measurement can be improved, realizes the fast of sewage disposal system effluent quality
Fast high-precision forecast provides a kind of feasible method for sewage disposal plant effluent water quality on-line prediction early warning.
Invention content
The present invention utilizes the water quality factor data that sewage disposal system is provided, and establishes a kind of determining discharge of pollutant sources monitoring
The method of threshold value of warning, and monitoring and warning system is constructed based on this, so that each monitoring personnel understands sewage disposal in time
The operating status of system realizes that dynamic manages, improves treatment effeciency.
The present invention provides water quality index data by sewage disposal system, its volume is taken after carrying out data prediction to the data
Product obtains convolution matrix, then acquired convolution matrix input convolution self-encoding encoder and extreme learning machine is trained, final
To prediction result, it is characterised in that following steps：
(1) data pre-processing unit, the correlation water factor for being obtained from sewage disposal include：Water inlet BOD, COD,
NH3-N, TN, TP, SS and water outlet COD, carry out the pretreatment of data --- noise reduction, rejecting abnormalities value, smooth and standardization
Processing；
(2) convolution is inputted by pretreated data from coder extreme learning machine to learn；
(3) using convolution sewage disposal plant effluent water quality is predicted from coder extreme learning machine；
(4) it according to the predicted value of outlet water quality, determines alert grade status level, timely feedbacks, and provide and whether need to carry out
Process modification, parameter are adjusted, the corresponding decisions such as increase and decrease of drug dosage.
The present invention is directed to the prediction and warning problem of sewage disposal system process effluent quality, can find sewage disposal work in time
The problem of in the presence of skill, obtains the prediction side of sewage disposal system effluent quality based on convolution self-encoding encoder extreme learning machine
Method realizes online, quick, the accurate early warning of effluent quality in sewage disposal process.
It is important to note that：The present invention is intended merely to description conveniently, using to being discharged the pre- of COD in sewage disposal process
It surveys, the prediction of other crucial water quality index in sewage disposal process can be used in the same invention, as long as using the present invention's
Principle, which carries out prediction, should belong to the scope of the present invention.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not constitute any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the system flow chart of the present invention；
Fig. 2 is the training process figure of the convolution autocoding of the present invention；
Fig. 3 is the incremental limit learning network structural schematic diagram of the present invention；
Fig. 4 is the implementation schematic block diagram of the present invention.
Specific implementation mode
(1) data prediction
Using the index of correlation data for the influent quality that sewage treatment plant provides, including：BOD, COD, NH3-N, TN, P, SS
And water outlet COD to the data of experiment carry out successively noise reduction, abnormal data noise reduction, rejecting abnormalities value, at smooth and standardization
Reason
(2) convolution own coding extreme learning machine learns pretreated data
1) according to formulaConvolutional calculation is carried out to input sample, (wherein xn is defeated
Enter signal, hn is unit response, and yn is corresponding output), and obtain corresponding convolution matrix；
2) obtained convolution matrix is utilized into convolution self-encoding encoder, autocoding output is carried out to it, it is self-editing to obtain convolution
The output of code device first layer；
3) input by the output of first layer as the second layer repeats step 1) and 2), obtains second layer output；
4) step 3) is repeated, the output of last layer is learnt as next layer of input, to the last one layer of n, and
The n convolution autocoding storehouse that will be obtained；
5) input of the output that last layer of convolution self-encoding encoder obtains as extreme learning machine；
6) output that last layer of convolution self-encoding encoder obtains, the present invention select incremental extreme learning machine and learn
Training, process are as follows：
A. single hidden layer feedforward neural network of a linear convergent rate node has L hidden node, mathematical model can be with table
It is shown as：
Wherein gi (x) indicates the output of i-th of hidden node, and β i indicate the defeated of i-th of hidden layer node and output node
Go out weight, ai is the input weights connected between input layer and i-th of hidden node, and bi is the threshold value of i-th of hidden node.
B. maximum hidden node number is set as M, and hidden node number L increases since 1 works as L<M and error, which are more than, it is expected to miss
When poor：L=L+1；
C. the weights a and threshold value b of current hidden neuron are obtained at random；
D. the input x of Current neural member excitation function g (x) is calculated；
A addition hidden layer neurons：See that b is extended to the matrix b of a 1 × U, then calculate x=aX+b, wherein X be n ×
The matrix of U.
B radial direction base hidden neurons：A is extended to the matrix of a U × n, then calculates x=b | | XT-a||。
E. current hidden layer output is calculated：
A addition hidden neurons：H=g (x),
B radial direction base hidden neurons:H=gT(x),
F. the output weights of the hidden neuron are then calculated：
Wherein E is remaining poor (matrix of differences between network reality output and target output)
It repeats the above steps, stops study until error is less than anticipation error, if error is always more than anticipation error, when
L>Stop study when M, this is because input weights a and threshold value b is caused at random, at this moment will restart to learn.
(3) above-mentioned established convolution self-encoding encoder extreme learning machine input model is utilized, sewage treatment plant goes out to the later stage
Water COD is predicted.
(4) according to water outlet COD predicted values, warning grade is determined.Specifically, determining whether early warning and warning grade
When, generally by will be discharged COD prediction or detection calculated value respectively with or long term monitoring data delimitation be compared, and according to than
Relatively result determines warning grade.
Detailed process is as follows：
1) if being discharged COD (prediction or monitoring) is less than 60mg/L, alert status at this time is normal, and determination is currently not required to
Carry out water quality early-warning；
If 2) be discharged COD (prediction or monitoring) between in 60-80mg/L, alert status at this time is general；
If 3) be discharged COD (prediction or monitoring) between 80-100mg/L, alert status at this time is abnormal；
4) if being discharged COD (prediction or monitoring) is more than 100mg/L, alert status at this time is abnormal；
If 5) water outlet COD alert status is abnormal or abnormal, will carry out below setting about analyzing：
A. examine whether influent quality changes；
B. examine whether water temperature changes；
C. sludge state is examined, and does microscopy and does lower observation；
D. check whether that spoil disposal is excessive；
E. examine whether aeration quantity changes.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although being explained in detail to the present invention with reference to preferred embodiment, those skilled in the art answer
Work as understanding, the technical solution of invention can be modified or replaced equivalently, without departing from the essence of technical solution of the present invention
And range.
Claims (8)
1. it is a kind of based on convolution from the sewage disposal system monitoring and pre-alarming method of coder extreme learning machine, which is characterized in that the party
Method includes：
(1) data are collected into sewage disposal system, carry out data prediction；
(2) learnt from coder extreme learning machine by pretreated data input convolution；
(3) using convolution sewage disposal system effluent quality is predicted from coder extreme learning machine；
(4) it according to the predicted value of outlet water quality, determines alert grade state, timely feedbacks, and provide and whether need to carry out previous stage
Process modification, parameter adjust, the respective handlings decision such as increase and decrease of drug dosage.
2. according to the method described in claim 1, it is characterized in that, the data that the sewage disposal system is collected into include：Into
Aquatic organism oxygen demand (BOD), COD (COD), ammonia nitrogen (NH3-N), total nitrogen (TN), total phosphorus (TP), suspended matter (SS) with
And water outlet COD；Data prediction includes noise reduction, rejecting abnormalities value, smooth and standardization.
3. according to the method described in claim 1, it is characterized in that, the tool that the convolution is learnt from coder extreme learning machine
Steps are as follows for body：
(1) convolutional calculation is done to input sample data, obtains corresponding convolution matrix；
(2) convolution matrix will be obtained, using convolution from coder, it is defeated to obtain convolution autocoder first layer for autocoding output
Go out；
(3) input by the output of first layer as the second layer, repeats step (1) and (2), obtains the output of the second layer；
(4) step (3) is repeated, the output of last layer is learnt as next layer of input, to the last one layer, obtains the
The output of n-layer finally obtains n convolution autocoder storehouse；
(5) input by the output of n-layer as extreme learning machine, the output of extreme learning machine is as the result learnt.
4. according to the method described in claim 1, it is characterized in that：Using volume machine effluent quality is obtained from coder extreme learning machine
The specific method of prediction result is：
It new will be collected into sewage treatment plant's water quality factor data and input convolution from coder extreme learning machine, convolution is from the coder limit
The output of habit machine is prediction result.
5. according to the method described in claim 1, it is characterized in that：It is pre- that from coder extreme learning machine water quality is obtained out by convolution
It surveys as a result, carrying out early warning decision according to prediction result, method includes：
(1) alert status level determination module；
(2) sewage disposal system inspection module.
6. according to the method described in claim 3, it is characterized in that：Through convolution from the output of coder n-layer as extreme learning machine
Input, the present invention selects incremental extreme learning machine, and learning process method is as follows：
(1) maximum hidden node number is set as M, and hidden node number L increases since 1, works as L<M and error are more than anticipation error
When：L=L+1；
(2) weights and threshold value of current hidden neuron are obtained at random；
(3) the defeated x of Current neural member excitation function is calculated；
(4) current hidden layer output is calculated；
(5) the output weights of the hidden neuron are calculated and then.
7. according to the method described in claim 5, it is characterized in that：Alert status level determination module, specific method are：
(1) if water outlet COD (prediction or monitoring) is less than 60mg/L, alert status at this time is normal, and determination does not need currently
Carry out water quality early-warning；
(2) if water outlet COD (prediction or monitoring) is between in 60-80mg/L, alert status at this time is general；
(3) if water outlet COD (prediction or monitoring) is between 80-100mg/L, alert status at this time is abnormal；
(4) if water outlet COD (prediction or monitoring) is more than 100mg/L, alert status at this time is abnormal.
8. according to the method described in claim 5, it is characterized in that：It is abnormal or abnormal for predicted state, incites somebody to action
Carrying out following examine to sewage disposal system is specially：
(1) examine whether influent quality changes；
(2) examine whether water temperature changes；
(3) sludge state is examined, and does microscopy and does lower observation；
(4) check whether that spoil disposal is excessive；
(5) examine whether aeration quantity changes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810378369.4A CN108562709A (en) | 2018-04-25 | 2018-04-25 | A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810378369.4A CN108562709A (en) | 2018-04-25 | 2018-04-25 | A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108562709A true CN108562709A (en) | 2018-09-21 |
Family
ID=63536446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810378369.4A Pending CN108562709A (en) | 2018-04-25 | 2018-04-25 | A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108562709A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057918A (en) * | 2019-05-29 | 2019-07-26 | 山东大学 | Damage of composite materials quantitative identification method and system under strong noise background |
| CN110567558A (en) * | 2019-08-28 | 2019-12-13 | 华南理工大学 | Ultrasonic guided wave detection method based on deep convolution characteristics |
| CN111103416A (en) * | 2019-12-30 | 2020-05-05 | 重庆商勤科技有限公司 | Water source pollution early warning method and system |
| CN111404274A (en) * | 2020-04-29 | 2020-07-10 | 平顶山天安煤业股份有限公司 | Online monitoring and early warning system for displacement of power transmission system |
| CN111427265A (en) * | 2020-03-19 | 2020-07-17 | 中南大学 | Method and device for intelligently monitoring abnormal working conditions in heavy metal wastewater treatment process based on transfer learning and storage medium |
| CN111650834A (en) * | 2020-06-16 | 2020-09-11 | 湖南工业大学 | Sewage treatment process prediction control method based on Extreme Learning Machine (ELM) |
| CN112308169A (en) * | 2020-11-10 | 2021-02-02 | 浙江大学 | Effluent quality prediction method based on improved online sequence extreme learning machine |
| CN112485394A (en) * | 2020-11-10 | 2021-03-12 | 浙江大学 | Water quality soft measurement method based on sparse self-coding and extreme learning machine |
| CN113050567A (en) * | 2021-03-17 | 2021-06-29 | 北京理工大学 | Dynamic scheduling method for intelligent manufacturing system |
| TWI746059B (en) * | 2020-07-15 | 2021-11-11 | 方達科技股份有限公司 | Artificial intelligence auxiliary operating system for optimizing the efficiency of sewage treatment facilities and artificial intelligence optimization method for sewage water quality using it |
| CN114580570A (en) * | 2022-04-01 | 2022-06-03 | 澳门大学 | Classification model training method, in-car object classification method, device and medium |
| CN117037929A (en) * | 2023-10-10 | 2023-11-10 | 天科院环境科技发展（天津）有限公司 | MBBR pool sewage treatment method based on convolutional neural network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103728431A (en) * | 2014-01-09 | 2014-04-16 | 重庆科技学院 | Industrial sewage COD (chemical oxygen demand) online soft measurement method based on ELM (extreme learning machine) |
| CN103942461A (en) * | 2014-05-14 | 2014-07-23 | 浙江师范大学 | Water quality parameter prediction method based on online sequential extreme learning machine |
| CN204310865U (en) * | 2014-12-22 | 2015-05-06 | 重庆德利欧环保有限公司 | For the sewage toxicity early warning system of Sewage Plant |
| CN105335554A (en) * | 2015-10-08 | 2016-02-17 | 大连海洋大学 | Dissolved oxygen concentration soft measurement method based on improved extreme learning machine |
| CN105372995A (en) * | 2015-12-17 | 2016-03-02 | 镇江市高等专科学校 | Measurement and control method for sewage disposal system |
| CN107741738A (en) * | 2017-10-20 | 2018-02-27 | 重庆华绿环保科技发展有限责任公司 | A kind of sewage disposal process monitoring intelligent early warning cloud system and sewage disposal monitoring and pre-alarming method |
-
2018
- 2018-04-25 CN CN201810378369.4A patent/CN108562709A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103728431A (en) * | 2014-01-09 | 2014-04-16 | 重庆科技学院 | Industrial sewage COD (chemical oxygen demand) online soft measurement method based on ELM (extreme learning machine) |
| CN103942461A (en) * | 2014-05-14 | 2014-07-23 | 浙江师范大学 | Water quality parameter prediction method based on online sequential extreme learning machine |
| CN204310865U (en) * | 2014-12-22 | 2015-05-06 | 重庆德利欧环保有限公司 | For the sewage toxicity early warning system of Sewage Plant |
| CN105335554A (en) * | 2015-10-08 | 2016-02-17 | 大连海洋大学 | Dissolved oxygen concentration soft measurement method based on improved extreme learning machine |
| CN105372995A (en) * | 2015-12-17 | 2016-03-02 | 镇江市高等专科学校 | Measurement and control method for sewage disposal system |
| CN107741738A (en) * | 2017-10-20 | 2018-02-27 | 重庆华绿环保科技发展有限责任公司 | A kind of sewage disposal process monitoring intelligent early warning cloud system and sewage disposal monitoring and pre-alarming method |
Non-Patent Citations (5)
| Title |
|---|
| L.J.ZHAO等: "KPCA and ELM ensemble modeling of wastewater effluent quality indices", 《PROCEDIA ENGINEERING》 * |
| LIJIE ZHAO等: "Estimation of effluent quality using PLS-based extreme learning machines", 《NEURAL COMPUT & APPLIC》 * |
| WEN TAO ZHU等: "Hierarchical Extreme Learning Machine for Unsupervised Representation Learning", 《IEEE》 * |
| 殷云华等: "基于混合卷积自编码极限学习机的RGB-D物体识别", 《红外与激光工程》 * |
| 谢智歌等: "基于卷积-自动编码机的三维形状特征学习", 《计算机辅助设计与图形学学报》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057918B (en) * | 2019-05-29 | 2020-11-06 | 山东大学 | Method and system for quantitatively identifying damage of composite material under strong noise background |
| CN110057918A (en) * | 2019-05-29 | 2019-07-26 | 山东大学 | Damage of composite materials quantitative identification method and system under strong noise background |
| CN110567558B (en) * | 2019-08-28 | 2021-08-10 | 华南理工大学 | Ultrasonic guided wave detection method based on deep convolution characteristics |
| CN110567558A (en) * | 2019-08-28 | 2019-12-13 | 华南理工大学 | Ultrasonic guided wave detection method based on deep convolution characteristics |
| CN111103416A (en) * | 2019-12-30 | 2020-05-05 | 重庆商勤科技有限公司 | Water source pollution early warning method and system |
| CN111427265A (en) * | 2020-03-19 | 2020-07-17 | 中南大学 | Method and device for intelligently monitoring abnormal working conditions in heavy metal wastewater treatment process based on transfer learning and storage medium |
| CN111427265B (en) * | 2020-03-19 | 2021-03-16 | 中南大学 | Method and device for intelligently monitoring abnormal working conditions in heavy metal wastewater treatment process based on transfer learning and storage medium |
| CN111404274A (en) * | 2020-04-29 | 2020-07-10 | 平顶山天安煤业股份有限公司 | Online monitoring and early warning system for displacement of power transmission system |
| CN111650834A (en) * | 2020-06-16 | 2020-09-11 | 湖南工业大学 | Sewage treatment process prediction control method based on Extreme Learning Machine (ELM) |
| CN111650834B (en) * | 2020-06-16 | 2022-08-30 | 湖南工业大学 | Sewage treatment process prediction control method based on extreme learning machine |
| TWI746059B (en) * | 2020-07-15 | 2021-11-11 | 方達科技股份有限公司 | Artificial intelligence auxiliary operating system for optimizing the efficiency of sewage treatment facilities and artificial intelligence optimization method for sewage water quality using it |
| CN112485394A (en) * | 2020-11-10 | 2021-03-12 | 浙江大学 | Water quality soft measurement method based on sparse self-coding and extreme learning machine |
| CN112308169B (en) * | 2020-11-10 | 2022-05-03 | 浙江大学 | Effluent quality prediction method based on improved online sequence extreme learning machine |
| CN112308169A (en) * | 2020-11-10 | 2021-02-02 | 浙江大学 | Effluent quality prediction method based on improved online sequence extreme learning machine |
| CN113050567A (en) * | 2021-03-17 | 2021-06-29 | 北京理工大学 | Dynamic scheduling method for intelligent manufacturing system |
| CN113050567B (en) * | 2021-03-17 | 2022-02-01 | 北京理工大学 | Dynamic scheduling method for intelligent manufacturing system |
| CN114580570A (en) * | 2022-04-01 | 2022-06-03 | 澳门大学 | Classification model training method, in-car object classification method, device and medium |
| CN117037929A (en) * | 2023-10-10 | 2023-11-10 | 天科院环境科技发展（天津）有限公司 | MBBR pool sewage treatment method based on convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108562709A (en) | A kind of sewage disposal system water quality monitoring method for early warning based on convolution self-encoding encoder extreme learning machine | |
| US11709463B2 (en) | Control method based on adaptive neural network model for dissolved oxygen of aeration system | |
| Elkiran et al. | Artificial intelligence-based approaches for multi-station modelling of dissolve oxygen in river | |
| CN108898215B (en) | Intelligent sludge bulking identification method based on two-type fuzzy neural network | |
| CN105510546B (en) | A kind of biochemical oxygen demand (BOD) BOD intelligent detecting methods based on self-organizing Recurrent RBF Neural Networks | |
| CN111553468B (en) | Method for accurately predicting water quality of effluent of sewage treatment plant | |
| CN109879410A (en) | Sewage treatment aeration control system | |
| CN102313796B (en) | Soft measuring method of biochemical oxygen demand in sewage treatment | |
| CN109828089B (en) | DBN-BP-based water quality parameter nitrous acid nitrogen online prediction method | |
| Hamada et al. | Application of artificial neural networks for the prediction of Gaza wastewater treatment plant performance-Gaza strip | |
| CN106295800A (en) | A kind of water outlet total nitrogen TN intelligent detecting method based on recurrence Self organizing RBF Neural Network | |
| CN114037163A (en) | Sewage treatment effluent quality early warning method based on dynamic weight PSO (particle swarm optimization) optimization BP (Back propagation) neural network | |
| CN108536106B (en) | Aeration system dissolved oxygen online regulation and control method based on Kalman filtering-extreme learning machine | |
| CN107402586A (en) | Dissolved Oxygen concentration Control method and system based on deep neural network | |
| Wang et al. | A full-view management method based on artificial neural networks for energy and material-savings in wastewater treatment plants | |
| CN118210237B (en) | Intelligent dosing control system of integrated sewage treatment equipment | |
| CN113011661A (en) | Aeration control system for river ecological restoration and control method thereof | |
| CN112465206A (en) | Water resource optimization configuration and optimization result evaluation feedback method | |
| CN112782975A (en) | Sewage treatment aeration intelligent control method and system based on deep learning | |
| CN114858207A (en) | Soft measurement-based gridding source tracing investigation method for drain outlet of river channel | |
| CN111125907A (en) | Sewage treatment ammonia nitrogen soft measurement method based on hybrid intelligent model | |
| Türkmenler et al. | Performance assessment of advanced biological wastewater treatment plants using artificial neural networks | |
| CN113627506B (en) | Intelligent detection method for total phosphorus in effluent based on information fusion-interval two-type fuzzy neural network | |
| CN115422850A (en) | Method for judging pollution contribution rate of river inflow river drain outlet based on EFDC and edge calculation | |
| CN117690518A (en) | Method and system for determining drug addition amount for treating coal water slurry wastewater |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180921 |