CN109934377A - A kind of the interaction factor control analysis of industrial pollution source synthesis and prediction technique of fine particle - Google Patents
A kind of the interaction factor control analysis of industrial pollution source synthesis and prediction technique of fine particle Download PDFInfo
- Publication number
- CN109934377A CN109934377A CN201811638904.1A CN201811638904A CN109934377A CN 109934377 A CN109934377 A CN 109934377A CN 201811638904 A CN201811638904 A CN 201811638904A CN 109934377 A CN109934377 A CN 109934377A
- Authority
- CN
- China
- Prior art keywords
- data
- analysis
- fine particle
- model
- pollution
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004458 analytical method Methods 0.000 title claims abstract description 43
- 239000010419 fine particle Substances 0.000 title claims abstract description 26
- 230000003993 interaction Effects 0.000 title claims abstract description 19
- 230000015572 biosynthetic process Effects 0.000 title description 3
- 238000003786 synthesis reaction Methods 0.000 title description 3
- 238000003915 air pollution Methods 0.000 claims abstract description 37
- 238000009792 diffusion process Methods 0.000 claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 238000006116 polymerization reaction Methods 0.000 claims abstract description 15
- 230000007613 environmental effect Effects 0.000 claims abstract description 11
- 238000007405 data analysis Methods 0.000 claims abstract description 9
- 238000009776 industrial production Methods 0.000 claims abstract description 9
- 241001269238 Data Species 0.000 claims abstract description 7
- 238000013499 data model Methods 0.000 claims abstract description 3
- 239000003344 environmental pollutant Substances 0.000 claims description 26
- 231100000719 pollutant Toxicity 0.000 claims description 26
- 230000000694 effects Effects 0.000 claims description 22
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 230000002452 interceptive effect Effects 0.000 claims description 12
- 239000000654 additive Substances 0.000 claims description 11
- 230000000996 additive effect Effects 0.000 claims description 11
- 239000002131 composite material Substances 0.000 claims description 7
- 239000013618 particulate matter Substances 0.000 claims description 7
- 238000011160 research Methods 0.000 claims description 7
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 6
- 238000013459 approach Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 239000003500 flue dust Substances 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 230000001932 seasonal effect Effects 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000011835 investigation Methods 0.000 claims description 2
- 229910052757 nitrogen Inorganic materials 0.000 claims description 2
- 230000003647 oxidation Effects 0.000 claims description 2
- 238000007254 oxidation reaction Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims description 2
- 241000894007 species Species 0.000 claims description 2
- 241000638935 Senecio crassissimus Species 0.000 claims 1
- 230000008846 dynamic interplay Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000012795 verification Methods 0.000 abstract description 3
- 238000012800 visualization Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 13
- 230000002265 prevention Effects 0.000 description 5
- 238000011109 contamination Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 239000003245 coal Substances 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000007474 system interaction Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000002440 industrial waste Substances 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000010186 staining Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle and prediction technique, the first step, the related datas such as acquisition related data parameter, including industrial production data, meteorological data, environmental monitoring data and geographic information data；Each data are carried out real-time big data analysis by second step alone or in combination, the analysis model for being spread and being polymerize with the remote dynamic that this big data analysis result establishes corresponding fine particle industrial pollution discharge；Pollution source data is loaded into above-mentioned big data model, quantitatively calculates its influence to any longitude and latitude of metropolitan district, the fine particle concentration of arbitrary height by third step.This method realizes air pollution in the diffusion polymerization of specified space-time.The visualization of the big datas such as the following pollution prediction is presented based on GIS technology, realizes the dynamic interaction of current and future air pollution；By the customizable and dynamic interaction of air pollution regulation and control scheme, the soundness verification of pollution regulation and control scheme is realized.
Description
Technical field
The present invention relates to air pollution analysis and prediction field, in particular to the industrial pollution source of a kind of fine particle is comprehensive
Interaction factor control analysis and prediction technique.
Background technique
But that there are prevention and control targets is single for existing air contamination analysis equation, regulation and control scheme is dedicated, modification scope limitation, implements
The problems such as process is complicated, when establishing model, only in accordance with point, line, source linear superposition, that is, Gauss diffusion model is folded
Add.
Summary of the invention
For above-mentioned there are problem, the comprehensive interaction factor control analysis of the industrial pollution source of a kind of fine particle and pre- is proposed
Survey method.
A kind of the interaction factor control analysis of industrial pollution source synthesis and prediction technique of fine particle,
The first step acquires related data parameter, including industrial production data, meteorological data, environmental monitoring data and geographical letter
Cease the related datas such as data；
Each data are carried out real-time big data analysis by second step alone or in combination, establish phase with this big data analysis result
The analysis model for answering the remote dynamic of fine particle industrial pollution discharge to spread and polymerize；
Pollution source data is loaded into above-mentioned big data model by third step, quantitatively calculate its to any longitude and latitude of metropolitan district,
The influence of the fine particle concentration of arbitrary height.
Further, single discharge of pollutant sources data of the controlled monitoring of environmental protection administration, i.e. flue dust, sulfur dioxide and nitrogen oxidation are utilized
Three kinds of data of object, are loaded into the analysis model of above-mentioned diffusion and polymerization, obtain single discharge of pollutant sources to any position and
The fine particle concentration of elevation influences.
Further, in monitoring space, each individual pollution source effect particle related data is loaded into diffusion and polymerization
Analysis model carry out independent analysis, obtain analyze data accordingly, then, in conjunction with particulate matter quantity rank factor integrate divide
Analysis, considers seasonal factor later, and analysis obtains influential effect of the respective pollution sources in space, and it is more that the above results are added to
The non-linear interactive Additive Model of pollution sources show that Nonlinear Superposition analyzes result.
Further, the particulate matter quantity rank factor is the factors such as quantity, size and the quality of particulate matter；The season
Section factor is the factors such as wind direction, wind speed, temperature and humidity and distance.
Further, in conjunction with the special case in city and the current intelligence of time, it is above-mentioned more that data loading will be acquired accordingly
Pollution sources Nonlinear Superposition model obtains analysis result in real time.
Further, city is monitored the landform in space to classify, monitoring data is loaded into the analysis of diffusion and polymerization
Model and the non-linear interactive Additive Model of multiple pollutant sources, obtain corresponding model data, and by the data investigation to various species
Landform on, obtain the expanding effect result in the Particulate Pollution source of different terrain.
Further, the transfer between each model is determined by Markov transferring matrix, transition probability dynamic change.
Further, the non-linear interactive Additive Model of the multiple pollutant sources is using overall fit method, i.e., according to region institute
Some elevation point datas are fitted unified ground elevation curved surface with fourier series and high-order moment.
Further, the non-linear interactive Additive Model of the multiple pollutant sources is local fit method, by earth's surface complex surface point
Partitioned searching is carried out at the roughly equal irregular area of square regular domain or area, shape is fitted according to limited point
At elevation curved surface.
Further, using the composite framework air combined based on extremely short timing ARIMA built-up pattern and BP neural network
Pollution prediction.
Further, it is described based on extremely short timing ARIMA built-up pattern to city air pressure in recent years, temperature, humidity, wind direction
It is trained with data such as wind speed, establishes the shallow-layer prediction model of Air Pollution Forecast, realize the short-term forecast of air pollution.
Further, binding time sequence and Multi-layer BP Neural Network are based on data of short-time series and neural network design air
The high-speed decision mechanism of pollution establishes the sky of composite framework by the other intensive training study of phase sorting, feedback and assessment
Model is strengthened in gas pollution prediction, realizes the Air Pollution Forecast to the short, medium and long phase and assessment.
Further, for the prediction of PM2.5, trend is extracted first with higher order polynomial, residual error is examined to meet zero-mean
Then stationary time series uses feature ARIMA Combined model forecast PM2.5 predicted value variation tendency.
Further, using piecewise differentiable function, according to the history number including air pressure, temperature, humidity, wind direction, wind speed factor
According to the feature of research object is divided into different parts or incited somebody to action by the segmentation feature of consideration each stage factor of piecewise smooth function
One feature is divided into different piece, by segmentation feature, more fully understands characteristic related with identification feature, thus more accurately into
Row identification object or feature identification, and the influence to PM2.5, using it is ultrashort when ARIMA combined method to carry out PM2.5 pre- in short term
It surveys, based on history air pollution data, settling time series model carries out the air pollution mould of arbitrary point on map
It is quasi-.
Further, 3 layers or more of neural network and the neuron number of enough hidden layers, model is arranged in BP neural network
Some can be accomplished to approach with enough precision with limited discontinuous point, the i.e. nonlinear function of dirichlet condition.
This method supervises industrial pollution discharge situation, ground transaucer atmospheric environment using multiple pollutant sources diffusion Additive Model
The high-speed parallel of the atmospheric environment Value of Remote Sensing Data of measured data and optics and microwave is analyzed, and realizes air pollution when specified
Empty diffusion polymerization.It is big to environment monitoring, meteorology, air pollution and geographical location and the following pollution prediction etc. based on GIS technology
The visualization of data is presented, and realizes the dynamic interaction of current and future air pollution；Pass through determining for air pollution regulation and control scheme
System and dynamic interaction realize the soundness verification of pollution regulation and control scheme.
Specific embodiment
Based on data such as industrial production, meteorology, environmental monitoring, geography information, dynamic big data analysis in real time is carried out, is built
The remote dynamic diffusion of vertical emission of industrial pollutants and polymerization model, quantitatively calculate its to any longitude and latitude of metropolitan district, times
The influence of the fine particle concentration for height of anticipating, comprising the following steps:
(1) to the quantitative analysis of single industrial pollution source emission, using the controlled monitoring data of environmental protection administration, (measurement point is polluting
Source, merely with three kinds of flue dust, sulfur dioxide, nitrogen oxides monitoring data), diffusion, polymerization and the chemical combination established by this method
Model show that single discharge of pollutant sources influences the fine particle concentration on any position and elevation in conjunction with big data analysis.This
Step only completes the data collection of the space-pollution point of the blowdown stack of single pollution sources.
(2) after the dynamic analysis for completing single pollution sources, the multiple relatively independent industrial pollution of secondary consideration
Reciprocal effect between source emission, including diffusion, polymerization and industrial conspiracy relation between pollutant, to be studied
The effect of specific area of space, pollution belongs to the fine grain comprehensive reciprocation of each pollution sources polluting effect, it is necessary to will
They carry out effect decomposition, obtain the quantitative analysis of the individual effect of each pollution sources, interactive model algorithm is by each dirt
Particle diameter, quantity of the polluting effect in dye source according to its emission, the personality factors such as quality size are divided into several numbers
Measure grade, and (1) obtained aggregation of data correspondence analysis, it is also contemplated that the wind direction, wind speed of seasonal effect, warm and humid in real time
The setting of the factors such as degree, distance, decomposites each pollution sources in the respective influential effect of spatial domain, then recycles this method
The multiple pollution sources pollution sources non-linear interactive Additive Models proposed carry out the Nonlinear Superposition of multiple pollutant sources pollution effect,
Rather than only in accordance with (Gauss diffusion model) point, line, source linear superposition；
The hierarchical environmental message processing flow for supporting space partition zone control, time upper dynamical feedback, realization have also been devised simultaneously
The air quality data of efficiently and accurately is handled and monitoring is traced to the source, and is realized to surrounding city or even provincial and area above multiplexing industry
It is quantitative that discharge of pollutant sources influences progress dynamic space.
(3) then it is also contemplated that due to complicated landform institute caused by hypsography, rough and uneven in surface and surface buildings
The diffusion of bring contaminant particle changes, and thinking is that topography variation is summarized as to several feature terrains, all complexity
Landform is the combined result of these feature terrains nothing but, then (1) (2) obtained contaminative diffusion model is added in the ground of feature
In shape, the pollutant diffusion effect in each height of complicated landform is obtained.Transfer between each model is by Ma Erke
Husband's transfer matrix is determining, transition probability dynamic change.The model supports landform, urban architecture, weather environment dynamic change and
The interactive Nonlinear Superposition of multiple pollution sources polluting effects, assembly effect realize the dynamic that multiple pollutant sources dynamic spreads, polymerize
Trace simulation.
So the program of interactive algorithm design is: acquiring the data acquisition system of single pollution sources；From the certain of area of space
Point acquires the comprehensive function of multiple pollution sources polluting effects, it be a multifactor interaction influence as a result, therefore it is necessary to
Effect decomposition is carried out, is then superimposed, this is a non-linear, adaptive model.
(4) in industrial pollution, pollution that caused by coal burning is important component part.For prevention and control in existing air pollution descriptive equation
The problems such as target is single, regulation and control scheme is dedicated, modification scope limits to, implementation process is complicated, proposes the work driven based on big data
Industry pollution prevention intelligence aided decision mechanism；Establish collection multi-source polluted information acquisition with processing, intellectual analysis and deduce decision,
It pollutes regulation and control scheme formulation and air pollution prevention and control is applied to the air pollution assistant decision support system of one, support comprehensive, more
The automation and intelligent industrial air pollution prevention and control of mode, multi-scheme, multiple target；It is proposed what forward and reverse analysis combined
Regulate and control thinking, i.e., since pollution sources polymerization and chemical combination analysis, analyze pollution sources to space arbitrary point influence (divide elevation, can
Specified arbitrary height), utilize the monitoring data of mobile and fixed air station, the influence of backtracking analysis pollution sources.
It is granular material discharged for starting point based on PM2.5 to reduce, comprehensively consider intercity equilibrium, Region homogenization, area
Interior industrial production is balanced, discharge of industrial wastes transformation is horizontal and production economy, proposes reasonable Coal-fired capacity distribution and industrial
Scheduling strategy.Asking for production and energy-saving and emission-reduction is influenced for many-sided complicated factor such as industrial production, Coal-fired capacity and disposal of pollutants
Topic establishes the Coal-fired capacity distribution model based on robust optimization, proposes the industrial production adjustment intelligence based on Coal-fired capacity distribution
Aid decision reduces coal consumption amount and pollutant emission.Based on the inter-provincial Coal-fired capacity point with the adjustment of ground section and industry environmental protection nargin
Match, industry environmental protection nargin and industrial production time and locating spatial position factor comprehensively consider, carried out industrial coal ring
It protects consumption prediction to calculate, the correlation model between each pollution sources in metropolitan district periphery is established, using Air Quality Forecast as a result, reality
Show the science of the production plan of industry, effectively prescribed, reduces the particulate matter based on PM2.5 as much as possible to the shadow of metropolitan district
It rings.
For the problem that existing Air Pollution Forecast real-time is poor, accuracy is low, propose subregion, distinguish at times into
The method of row analysis and processing.Namely for the further improvement of Gauss diffusion model, Gauss model considers three-dimensional space
Plume contamination object is normal distribution, and consider the wind speed for influencing diffusion be it is uniform, it is stable, continuous conservation, this reality
Be on border it is very inappeasable, only in time, spatially, be split, study respectively, corresponding control just can be with so control
Method processed is actually the control strategy and behavior after the detailed parsing of apparent pollution sources, is expanded by the pollution that front is described
Scattered mechanism, it is recognised that the variation of pollution sources be it is cracking, have extremely short periodicity, short time interval tendency and randomness
Effect.The method for relying solely on traditional simple regression analysis is obviously difficult to meet, so, when this method devises multiple extremely short
Between series model, feature short run models, using a variety of very short time series arrangements, combination, constructed have it is manifold
The composite framework Air Pollution Forecast method that ARIMA and BP neural network combine.When establishing the combination of air quality index
Between sequence Controlling model, combined based on very short time series model, track the cyclically-varying rule of dispersion of pollutants, realize empty
The cyclic forecast of makings amount.
The feasibility problems of built-up pattern: for nonlinear function, gradation study can be carried out to it, as long as it meets Di
Family name's condition (Dirichlet condition) can accomplish to approach some with enough precision with the non-thread of limited removable discontinuity point
Property function.Therefore, this combined prediction algorithm can satisfy calculating demand.
The data such as air pressure, temperature, humidity, wind direction, wind speed based on extremely short ARIMA built-up pattern to city in recent years carry out
Training, establishes the shallow-layer prediction model of Air Pollution Forecast, realizes the short-term forecast of air pollution.Binding time sequence and multilayer
BP neural network, the composite framework Air Pollution Forecast method of proposition are dirty based on data of short-time series and neural network design air
The high-speed decision mechanism of dye establishes the air of composite framework by the other intensive training study of phase sorting, feedback and assessment
Model is strengthened in pollution prediction, realizes the Air Pollution Forecast to the short, medium and long phase and assessment:
(1) contamination data according to key cities in recent years, for statistical analysis, research contamination data becomes with the variation in season
Gesture carries out Controlling model design using short time interval Feature Selection.Reason there are three doing so: simplified model is allowed to be easier to
In research and understand, shorten the training time, improves versatility, reduction over-fitting (i.e. reduction variance) establishes multiple extremely short spies
Sign selection Time Series Analysis Model, is combined using the method that extremely short trend prediction, cycle analysis in short-term are combined with ARIMA
Innovative approach carries out the prediction of longer period of time to PM2.5 pollution condition；Using extremely short period, short time period trends combination prediction side
Method extracts trend first with higher order polynomial, residual error is examined to meet the stationary time series of zero-mean, then uses feature
ARIMA Combined model forecast PM2.5 predicted value variation tendency.
(2) function that piecewise smooth function (piecewise smooth function) refers to piecewise differential is pollution
The popularization of object Controlling model smooth function.Controlling model is according to the history number including air pressure, temperature, humidity, wind direction, wind speed factor
According to the feature of research object is divided into different parts or incited somebody to action by the segmentation feature of consideration each stage factor of piecewise smooth function
One feature is divided into different piece.By segmentation feature, more fully understand characteristic related with identification feature, thus more accurately into
Row identification object or feature identification, and the influence to PM2.5, using it is ultrashort when ARIMA combined method to carry out PM2.5 pre- in short term
It surveys, based on history air pollution data, settling time series model carries out the air pollution mould of arbitrary point on map
It is quasi-, the scientific forecasting of multicycle is carried out to the following air quality.The prediction algorithm time granularity that this method proposes is thinner, realizes
The prediction of minute dimension accuracy, and ARIMA method and BP neural network are that sectionally smooth carries out
(3) it theoretically can sufficiently prove and have the neural network more than having three layers, as long as the neuron number for meeting hidden layer is enough
When, model can accomplish to approach some with enough precision with the non-thread of limited discontinuous point (Dirichlet dirichlet condition)
Property function.Therefore, BP combinational algorithm can satisfy calculating demand.
By Data Analysis Model according to meteorology, motor vehicle flow, geography, industrial production, dust from construction sites and all movements
Environmental protection prison equipment carries out the knot that automatic big data calculates selection short time interval ARIMA combined method or the prediction of BP combination neural net
Fruit is exported, and precision of prediction is higher, and prediction result exports faster.
For complexity, the uncertainty, dynamic of air pollution diffusion polymerization, propose folded based on multiple pollutant sources diffusion
Add the three-dimension GIS dynamic deduction method of model.
The representation method of digital elevation model: mathematically expressing, and can use overall fit method, i.e., according to area
All elevation point datas in domain, unified ground elevation curved surface is fitted with fourier series and high-order moment.Part can also be used
Earth's surface complex surface is divided into square regular domain or the roughly equal irregular area of area carries out piecemeal and searches by approximating method
Rope is fitted to form elevation curved surface according to limited point.
As previously mentioned, having studied the decomposition of the comprehensive function of the coupling interaction of multiple pollution source points first, obtain each
The independent polluting effect and cross staining effect of pollution sources, secondly, analyzing feature selecting, the feature of the certain points of Polluted area
Extraction and feature learning have constructed the combination of Short Time Domain ARIMA model and neural network model based on feature, disclose pollutant
The problem of particles diffusion contains is essential.The following image understanding is the important applied field of machine theory, Feature Engineering
It is natural to occupy very important status in whole image understanding.(in recent years, the research of image overall scenario items and engineering practice
In illustrate brilliant performance, the model based on probability theory and graph theory can portray this globality well, become current
The model generallyd use in overall scenario understanding.) but understand that (conspicuousness is examined using the method for probability graph model development overall scenario
Survey, scene classification, multiclass image segmentation, model integrated etc.) research, data needed for obtaining overall scenario understanding are to extract related spy
Sign be it is highly difficult, therefore, primary basic work is exactly the interaction data by the pollution particle in the extremely short period with three-dimensional
GIS dynamic, which is deduced, combines closely, and mutual seamless insertion, this, which is one, has challenge and initiative work.
This method supervises industrial pollution discharge situation, ground transaucer atmospheric environment using multiple pollutant sources diffusion Additive Model
The high-speed parallel of the atmospheric environment Value of Remote Sensing Data of measured data and optics and microwave is analyzed, and realizes air pollution when specified
Empty diffusion polymerization.It is big to environment monitoring, meteorology, air pollution and geographical location and the following pollution prediction etc. based on GIS technology
The visualization of data is presented, and realizes the dynamic interaction of current and future air pollution；Pass through determining for air pollution regulation and control scheme
System and dynamic interaction realize the soundness verification of pollution regulation and control scheme.
The aforementioned description to specific exemplary embodiment of the invention is in order to illustrate and illustration purpose.These descriptions
It is not wishing to limit the invention to disclosed precise forms, and it will be apparent that according to the above instruction, can much be changed
And variation.The purpose of selecting and describing the exemplary embodiment is that explaining specific principle of the invention and its actually answering
With so that those skilled in the art can be realized and utilize a variety of different exemplary implementation schemes of the invention and
Various chooses and changes.The scope of the present invention is intended to be limited by claims and its equivalents.
Claims (10)
1. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle and prediction technique, it is characterised in that:
The first step acquires related data parameter, including industrial production data, meteorological data, environmental monitoring data
And the related datas such as geographic information data；
Each data are carried out real-time big data analysis by second step alone or in combination, with this big data analysis knot
The remote dynamic that fruit establishes corresponding fine particle industrial pollution discharge is spread and the analysis model of polymerization；
Pollution source data is loaded into above-mentioned big data model, quantitatively calculates it and appoint to metropolitan district by third step
The influence of the fine particle concentration of meaning longitude and latitude, arbitrary height.
2. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 1 and prediction side
Method, it is characterised in that: utilize single discharge of pollutant sources data of the controlled monitoring of environmental protection administration, i.e. flue dust, sulfur dioxide and nitrogen oxidation
Three kinds of data of object, are loaded into the analysis model of above-mentioned diffusion and polymerization, obtain single discharge of pollutant sources to any position and
The fine particle concentration of elevation influences；In monitoring space, each individual pollution source effect particle related data is loaded into and is expanded
It dissipates and the analysis model of polymerization carries out independent analysis, obtain analyzing data accordingly, then, in conjunction with particulate matter quantity rank factor
Comprehensive analysis considers seasonal factor later, and analysis obtains influential effect of the respective pollution sources in space, and the above results are folded
It is added to the non-linear interactive Additive Model of multiple pollutant sources, show that Nonlinear Superposition analyzes result.
3. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 2 and prediction side
Method, it is characterised in that: the particulate matter quantity rank factor is the factors such as quantity, size and the quality of particulate matter；The season
Section factor is the factors such as wind direction, wind speed, temperature and humidity and distance；In conjunction with the special case in city and the current intelligence of time,
Corresponding acquisition data are loaded into above-mentioned multiple pollutant sources Nonlinear Superposition model and obtain analysis result in real time.
4. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 3 and prediction side
Method, it is characterised in that: city is monitored into the landform in space and is classified, monitoring data are loaded into the analysis mould of diffusion and polymerization
Type and the non-linear interactive Additive Model of multiple pollutant sources, obtain corresponding model data, and by the data investigation to various species
In landform, the expanding effect result in the Particulate Pollution source of different terrain is obtained.
5. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 4 and prediction side
Method, it is characterised in that: the transfer between each model determines by Markov transferring matrix, transition probability dynamic change；It is described
The non-linear interactive Additive Model of multiple pollutant sources is using overall fit method, i.e., elevation point datas all according to region uses Fu
Vertical leaf sum of series high-order moment is fitted unified ground elevation curved surface.
6. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 5 and prediction side
Method, it is characterised in that: the non-linear interactive Additive Model of multiple pollutant sources is local fit method, and earth's surface complex surface is divided into
Square regular domain or the roughly equal irregular area of area carry out partitioned searching, are fitted to be formed according to limited point
Elevation curved surface.
7. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 1-6
And prediction technique, it is characterised in that: using the composite frame combined based on extremely short timing ARIMA built-up pattern and BP neural network
Structure Air Pollution Forecast.
8. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 7 and prediction side
Method, it is characterised in that: it is described based on extremely short timing ARIMA built-up pattern to city air pressure in recent years, temperature, humidity, wind direction
It is trained with data such as wind speed, establishes the shallow-layer prediction model of Air Pollution Forecast, realize the short-term forecast of air pollution；Knot
Time series and Multi-layer BP Neural Network are closed, the high-speed decision machine polluted based on data of short-time series and neural network design air
System strengthens mould by the other intensive training study of phase sorting, feedback and assessment, the Air Pollution Forecast for establishing composite framework
Type realizes the Air Pollution Forecast to the short, medium and long phase and assessment.
9. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 8 and prediction side
Method, it is characterised in that: the prediction for PM2.5 extracts trend first with higher order polynomial, and residual error is examined to meet the flat of zero-mean
Then steady time series uses feature ARIMA Combined model forecast PM2.5 predicted value variation tendency；Using piecewise differentiable function,
According to the historical data including air pressure, temperature, humidity, wind direction, wind speed factor, point of each stage factor of piecewise smooth function is considered
The feature of research object is divided into different part or a feature is divided into different piece by Duan Tezheng, by segmentation feature,
Characteristic related with identification feature is more fully understood, to more accurately carry out identification object or feature identification, and to PM2.5's
Influence, using it is ultrashort when ARIMA combined method carry out PM2.5 short-term forecast, based on history air pollution data, when establishing
Between series model, carry out map on arbitrary point air pollution simulation.
10. a kind of comprehensive interaction factor control analysis of the industrial pollution source of fine particle according to claim 7 and prediction
Method, it is characterised in that: 3 layers or more of neural network and the neuron number of enough hidden layers, mould is arranged in BP neural network
Type can accomplish to approach some with enough precision with limited discontinuous point, the i.e. nonlinear function of dirichlet condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811638904.1A CN109934377A (en) | 2018-12-29 | 2018-12-29 | A kind of the interaction factor control analysis of industrial pollution source synthesis and prediction technique of fine particle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811638904.1A CN109934377A (en) | 2018-12-29 | 2018-12-29 | A kind of the interaction factor control analysis of industrial pollution source synthesis and prediction technique of fine particle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109934377A true CN109934377A (en) | 2019-06-25 |
Family
ID=66984850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811638904.1A Pending CN109934377A (en) | 2018-12-29 | 2018-12-29 | A kind of the interaction factor control analysis of industrial pollution source synthesis and prediction technique of fine particle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109934377A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288256A (en) * | 2019-06-28 | 2019-09-27 | 中科三清科技有限公司 | Condition analysis method and device |
| CN110531030A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of method and device based on the analysis of Internet of Things big data atmosphere pollution |
| CN110851777A (en) * | 2019-08-01 | 2020-02-28 | 天津城建大学 | PM2.5 concentration analysis model based on FFT |
| CN111157682A (en) * | 2020-01-06 | 2020-05-15 | 上海应用技术大学 | Air quality monitoring and predicting system and method |
| CN111611729A (en) * | 2020-07-16 | 2020-09-01 | 山东省科技发展战略研究所 | Resource management system based on environmental data acquisition |
| CN112304831A (en) * | 2020-10-08 | 2021-02-02 | 大连理工大学 | Mass conservation-based student behavior vs. PM in classroom2.5Concentration calculating method |
| CN112749478A (en) * | 2020-12-11 | 2021-05-04 | 江苏汇环环保科技有限公司 | Atmospheric pollution source-tracing diffusion analysis system and method based on Gaussian diffusion model |
| CN112801337A (en) * | 2020-12-07 | 2021-05-14 | 河北志晟信息技术股份有限公司 | Regional enterprise pollution discharge control method and system based on pollution data |
| CN113723534A (en) * | 2021-09-02 | 2021-11-30 | 南京润内克西信息科技有限公司 | Urban raise dust on-line monitoring system based on BP neural network |
| CN115017679A (en) * | 2022-05-07 | 2022-09-06 | 深圳中兴智坪科技有限公司 | Simulation method and device for atmospheric pollution diffusion, storage medium and electronic equipment |
| CN115455814A (en) * | 2022-08-31 | 2022-12-09 | 南京云创大数据科技股份有限公司 | Pollution source searching and pollutant distribution predicting method and system based on deep learning |
| CN115755722A (en) * | 2022-11-30 | 2023-03-07 | 国网福建省电力有限公司 | Pollutant prevention and control system for mineral oil leakage |
| CN116779056A (en) * | 2023-08-24 | 2023-09-19 | 石家庄兆荣科技有限公司 | Polymorphic fusion assessment environment quality method |
| CN116859006A (en) * | 2023-09-04 | 2023-10-10 | 北京亦庄智能城市研究院集团有限公司 | Air pollution monitoring system and method based on atmospheric diffusion mechanism |
| CN117370772A (en) * | 2023-12-08 | 2024-01-09 | 北京英视睿达科技股份有限公司 | PM2.5 diffusion analysis method and system based on urban street topography classification |
| CN117473398A (en) * | 2023-12-26 | 2024-01-30 | 四川国蓝中天环境科技集团有限公司 | Urban dust pollution source classification method based on slag transport vehicle activity |
| CN117538492A (en) * | 2024-01-10 | 2024-02-09 | 深圳市恒义建筑技术有限公司 | On-line detection method and system for pollutants in building space |
| CN117972381A (en) * | 2024-04-02 | 2024-05-03 | 华侨大学 | Internet insurance user feature screening method and device based on diffusion model |
| CN118411458A (en) * | 2024-07-01 | 2024-07-30 | 深圳大学 | Inhalable particle pollution visualization method and system based on nerve radiation field |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015013249A2 (en) * | 2013-07-22 | 2015-01-29 | Saint Louis University | Apparatus and method for providing environmental predictive indicators to emergency response managers |
| CN104537462A (en) * | 2014-12-11 | 2015-04-22 | 廖鹰 | Thermal power pollution factor control method of air fine particles |
| CN104598692A (en) * | 2015-02-02 | 2015-05-06 | 廖鹰 | Analogue simulation method for discharged smoke dust pollution of thermal power plant |
| CN107202750A (en) * | 2017-05-17 | 2017-09-26 | 河北中科遥感信息技术有限公司 | A kind of satellite-ground integrated monitoring quantitative remote sensing method for amalgamation processing of Atmospheric particulates |
| CN107229834A (en) * | 2017-06-27 | 2017-10-03 | 国网江苏省电力公司电力科学研究院 | A kind of complicated landform emergency response air pollution DIFFUSION PREDICTION method |
| CN107894492A (en) * | 2017-11-24 | 2018-04-10 | 成都立威斯科技有限公司 | A kind of urban atmospheric pollution method of real-time |
| CN108182491A (en) * | 2017-12-27 | 2018-06-19 | 宇星科技发展(深圳)有限公司 | The real-time source resolution localization method of airborne fine particulate matter (PM2.5) |
-
2018
- 2018-12-29 CN CN201811638904.1A patent/CN109934377A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015013249A2 (en) * | 2013-07-22 | 2015-01-29 | Saint Louis University | Apparatus and method for providing environmental predictive indicators to emergency response managers |
| CN104537462A (en) * | 2014-12-11 | 2015-04-22 | 廖鹰 | Thermal power pollution factor control method of air fine particles |
| CN104598692A (en) * | 2015-02-02 | 2015-05-06 | 廖鹰 | Analogue simulation method for discharged smoke dust pollution of thermal power plant |
| CN107202750A (en) * | 2017-05-17 | 2017-09-26 | 河北中科遥感信息技术有限公司 | A kind of satellite-ground integrated monitoring quantitative remote sensing method for amalgamation processing of Atmospheric particulates |
| CN107229834A (en) * | 2017-06-27 | 2017-10-03 | 国网江苏省电力公司电力科学研究院 | A kind of complicated landform emergency response air pollution DIFFUSION PREDICTION method |
| CN107894492A (en) * | 2017-11-24 | 2018-04-10 | 成都立威斯科技有限公司 | A kind of urban atmospheric pollution method of real-time |
| CN108182491A (en) * | 2017-12-27 | 2018-06-19 | 宇星科技发展(深圳)有限公司 | The real-time source resolution localization method of airborne fine particulate matter (PM2.5) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288256B (en) * | 2019-06-28 | 2020-07-03 | 中科三清科技有限公司 | Scene analysis method and device |
| CN110288256A (en) * | 2019-06-28 | 2019-09-27 | 中科三清科技有限公司 | Condition analysis method and device |
| CN110851777A (en) * | 2019-08-01 | 2020-02-28 | 天津城建大学 | PM2.5 concentration analysis model based on FFT |
| CN110531030B (en) * | 2019-08-16 | 2021-11-12 | 北京慧辰资道资讯股份有限公司 | Method and device for analyzing atmospheric pollutants based on Internet of things big data |
| CN110531030A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of method and device based on the analysis of Internet of Things big data atmosphere pollution |
| CN111157682A (en) * | 2020-01-06 | 2020-05-15 | 上海应用技术大学 | Air quality monitoring and predicting system and method |
| CN111611729A (en) * | 2020-07-16 | 2020-09-01 | 山东省科技发展战略研究所 | Resource management system based on environmental data acquisition |
| CN111611729B (en) * | 2020-07-16 | 2023-07-14 | 山东省科技发展战略研究所 | Resource management system based on environmental data acquisition |
| CN112304831A (en) * | 2020-10-08 | 2021-02-02 | 大连理工大学 | Mass conservation-based student behavior vs. PM in classroom2.5Concentration calculating method |
| CN112304831B (en) * | 2020-10-08 | 2021-09-24 | 大连理工大学 | Mass conservation-based student behavior vs. PM in classroom2.5Concentration calculating method |
| CN112801337A (en) * | 2020-12-07 | 2021-05-14 | 河北志晟信息技术股份有限公司 | Regional enterprise pollution discharge control method and system based on pollution data |
| CN112749478B (en) * | 2020-12-11 | 2024-02-09 | 江苏汇环环保科技有限公司 | Atmospheric pollution traceable diffusion analysis system and method based on Gaussian diffusion model |
| CN112749478A (en) * | 2020-12-11 | 2021-05-04 | 江苏汇环环保科技有限公司 | Atmospheric pollution source-tracing diffusion analysis system and method based on Gaussian diffusion model |
| CN113723534A (en) * | 2021-09-02 | 2021-11-30 | 南京润内克西信息科技有限公司 | Urban raise dust on-line monitoring system based on BP neural network |
| CN115017679A (en) * | 2022-05-07 | 2022-09-06 | 深圳中兴智坪科技有限公司 | Simulation method and device for atmospheric pollution diffusion, storage medium and electronic equipment |
| CN115455814A (en) * | 2022-08-31 | 2022-12-09 | 南京云创大数据科技股份有限公司 | Pollution source searching and pollutant distribution predicting method and system based on deep learning |
| CN115755722A (en) * | 2022-11-30 | 2023-03-07 | 国网福建省电力有限公司 | Pollutant prevention and control system for mineral oil leakage |
| CN116779056A (en) * | 2023-08-24 | 2023-09-19 | 石家庄兆荣科技有限公司 | Polymorphic fusion assessment environment quality method |
| CN116779056B (en) * | 2023-08-24 | 2023-10-20 | 石家庄兆荣科技有限公司 | Polymorphic fusion assessment environment quality method |
| CN116859006B (en) * | 2023-09-04 | 2023-12-01 | 北京亦庄智能城市研究院集团有限公司 | Air pollution monitoring system and method based on atmospheric diffusion mechanism |
| CN116859006A (en) * | 2023-09-04 | 2023-10-10 | 北京亦庄智能城市研究院集团有限公司 | Air pollution monitoring system and method based on atmospheric diffusion mechanism |
| CN117370772B (en) * | 2023-12-08 | 2024-04-16 | 北京英视睿达科技股份有限公司 | PM2.5 diffusion analysis method and system based on urban street topography classification |
| CN117370772A (en) * | 2023-12-08 | 2024-01-09 | 北京英视睿达科技股份有限公司 | PM2.5 diffusion analysis method and system based on urban street topography classification |
| CN117473398A (en) * | 2023-12-26 | 2024-01-30 | 四川国蓝中天环境科技集团有限公司 | Urban dust pollution source classification method based on slag transport vehicle activity |
| CN117473398B (en) * | 2023-12-26 | 2024-03-19 | 四川国蓝中天环境科技集团有限公司 | Urban dust pollution source classification method based on slag transport vehicle activity |
| CN117538492A (en) * | 2024-01-10 | 2024-02-09 | 深圳市恒义建筑技术有限公司 | On-line detection method and system for pollutants in building space |
| CN117538492B (en) * | 2024-01-10 | 2024-03-26 | 深圳市恒义建筑技术有限公司 | On-line detection method and system for pollutants in building space |
| CN117972381A (en) * | 2024-04-02 | 2024-05-03 | 华侨大学 | Internet insurance user feature screening method and device based on diffusion model |
| CN117972381B (en) * | 2024-04-02 | 2024-08-27 | 华侨大学 | Internet insurance user feature screening method and device based on diffusion model |
| CN118411458A (en) * | 2024-07-01 | 2024-07-30 | 深圳大学 | Inhalable particle pollution visualization method and system based on nerve radiation field |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934377A (en) | A kind of the interaction factor control analysis of industrial pollution source synthesis and prediction technique of fine particle | |
| Liao et al. | Deep learning for air quality forecasts: a review | |
| Chen et al. | Predict the effect of meteorological factors on haze using BP neural network | |
| Zhao et al. | Long short-term memory-Fully connected (LSTM-FC) neural network for PM2. 5 concentration prediction | |
| Quan et al. | GIS-based landslide susceptibility mapping using analytic hierarchy process and artificial neural network in Jeju (Korea) | |
| He et al. | Modeling the urban landscape dynamics in a megalopolitan cluster area by incorporating a gravitational field model with cellular automata | |
| CN106651036A (en) | Air quality forecasting system | |
| CN112163367B (en) | Firefly algorithm and cellular automaton fused city expansion simulation prediction method | |
| Wu et al. | Development of an on-line source-tagged model for sulfate, nitrate and ammonium: A modeling study for highly polluted periods in Shanghai, China | |
| CN105243435A (en) | Deep learning cellular automaton model-based soil moisture content prediction method | |
| Liu et al. | Spatio-temporal prediction and factor identification of urban air quality using support vector machine | |
| Abdullah et al. | Methods in forecasting carbon dioxide emissions: a decade review | |
| Casallas et al. | Long short-term memory artificial neural network approach to forecast meteorology and PM 2.5 local variables in Bogotá, Colombia | |
| CN110346518A (en) | A kind of traffic emission pollution visualization method for early warning and its system | |
| Lim et al. | Air pollution matter prediction using recurrent neural networks with sequential data | |
| Chen et al. | Simulating the effects of land urbanization on regional meteorology and air quality in Yangtze River Delta, China | |
| CN112712169A (en) | Model building method and application of full residual depth network based on graph convolution | |
| Schornobay-Lui et al. | Prediction of short and medium term PM10 concentration using artificial neural networks | |
| Lin et al. | Dynamic system approach for improved PM 2.5 prediction in Taiwan | |
| Al-Ahmadi et al. | A fuzzy cellular automata urban growth model (FCAUGM) for the city of Riyadh, Saudi Arabia. Part 1: Model structure and validation | |
| Wang et al. | Geographic information system and system dynamics combination technique for municipal solid waste treatment station site selection | |
| Sahoo et al. | Application of hybrid MLP-GWO for monthly rainfall forecasting in Cachar, Assam: a case study | |
| CH719974A2 (en) | Method for planning settlement development with an empirical densification approach. | |
| Wang et al. | P-DBL: a deep traffic flow prediction architecture based on trajectory data | |
| Sihag et al. | Predictive modelling of nitrogen dioxide using soft computing techniques in the Agra, Uttar Pradesh, India |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190625 |
|
| RJ01 | Rejection of invention patent application after publication |