CN116485202A - Industrial pollution real-time monitoring method and system based on Internet of things - Google Patents
Industrial pollution real-time monitoring method and system based on Internet of things Download PDFInfo
- Publication number
- CN116485202A CN116485202A CN202310451705.4A CN202310451705A CN116485202A CN 116485202 A CN116485202 A CN 116485202A CN 202310451705 A CN202310451705 A CN 202310451705A CN 116485202 A CN116485202 A CN 116485202A
- Authority
- CN
- China
- Prior art keywords
- pollution
- information
- monitoring
- monitoring information
- different
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 319
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003912 environmental pollution Methods 0.000 claims abstract description 22
- 230000004927 fusion Effects 0.000 claims abstract description 20
- 238000011161 development Methods 0.000 claims abstract description 17
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims description 36
- 238000011112 process operation Methods 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 14
- 238000004220 aggregation Methods 0.000 claims description 12
- 230000002776 aggregation Effects 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 210000000349 chromosome Anatomy 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000004519 manufacturing process Methods 0.000 claims description 10
- 230000007246 mechanism Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000012876 topography Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000003860 storage Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000006378 damage Effects 0.000 description 3
- 238000003900 soil pollution Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 239000012298 atmosphere Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004737 colorimetric analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000017105 transposition Effects 0.000 description 2
- 238000003911 water pollution Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000003895 groundwater pollution Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002912 waste gas Substances 0.000 description 1
- 239000002351 wastewater Substances 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
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
-
- 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
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0068—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a computer specifically programmed
-
- 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
- G01N33/24—Earth materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- Immunology (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Pathology (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Combustion & Propulsion (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Life Sciences & Earth Sciences (AREA)
Abstract
The invention discloses an industrial pollution real-time monitoring method and system based on the Internet of things, comprising the following steps: acquiring environmental pollution information in a preset area range, and determining pollution sources and pollution monitoring indexes according to the environmental pollution information; generating a sensor layout scheme within a preset area according to the pollution monitoring index and the pollution source information, acquiring pollution monitoring information acquired by different sensors, performing feature extraction on multi-source pollution monitoring information, constructing a multi-mode feature fusion model of the pollution monitoring information, acquiring associated features of different pollution monitoring information, monitoring industrial pollution conditions within the preset area by utilizing the associated features, and analyzing pollution development trend to generate pollution prediction information for pollution early warning. According to the invention, the industrial pollution is remotely monitored in real time through the Internet of things, the correlation among different pollution information is analyzed after the multi-mode pollution information is acquired, and the environmental pollution analysis and prediction are performed, so that the intelligent real-time industrial pollution monitoring is realized.
Description
Technical Field
The invention relates to the technical field of pollution monitoring, in particular to an industrial pollution real-time monitoring method and system based on the Internet of things.
Background
Industrial pollution refers to the invasion of enterprises in the production process to natural environments where living and reproduction of organisms including people are required. Since a large amount of harmful substances such as waste water or waste gas generated by enterprises in industrial production can seriously damage the ecological balance of agriculture if directly discharged into natural environment, and cause great harm to the development of agricultural production, the discharge of the harmful substances can also seriously harm the health condition of human beings, and industrial pollution is one of important factors causing soil pollution and groundwater pollution, the comprehensive monitoring and treatment of industrial pollution is particularly important.
The industrial pollution has the characteristics of complexity, concealment, difficulty in management and the like, and the monitoring data has the defects of single data, data lag, data redundancy and the like. In order to adapt to the current repair standard of pollution control, industrial pollution monitoring needs to collect key parameters such as process parameters and electrical parameters of pollution source enterprise production facilities and pollution control facilities on the premise of not influencing the normal operation of equipment, and comprehensively monitors the operation of the enterprise production facilities and control facilities, the pollution control effect and the discharge amount condition of the terminal pollutant emission monitoring data by combining the enterprise production process principle, and provides a basis for the environment supervision management application of the pollution source automatic monitoring data in total amount verification, pollution discharge declaration charge, pollution discharge right transaction and the like. How to utilize the internet of things technology and the modern remote monitoring technology in the real-time monitoring platform of industrial pollution, ensuring the accurate and effective monitoring data is an urgent problem which can not be solved.
Disclosure of Invention
In order to solve the technical problems, the invention provides a real-time industrial pollution monitoring method and system based on the Internet of things.
The invention provides a real-time monitoring method for industrial pollution based on the Internet of things, which comprises the following steps:
acquiring environmental pollution information in a preset area range, and determining pollution sources and pollution monitoring indexes according to the environmental pollution information;
generating a sensor layout scheme within a preset area range according to the pollution monitoring index and the pollution source information, and acquiring real-time data of an industrial pollution source through remote monitoring;
acquiring pollution monitoring information acquired by different sensors, performing feature extraction on multi-source pollution monitoring information, constructing a multi-mode feature fusion model of the pollution monitoring information, and acquiring associated features of different pollution monitoring information;
and monitoring the industrial pollution condition of the preset area range by utilizing the association characteristics, analyzing the pollution development trend to generate pollution prediction information, and carrying out pollution early warning.
In this scheme, according to pollution monitoring index and pollution source information generate the sensor layout scheme of predetermineeing regional within range, specifically do:
obtaining geographic information and pollution source position information in a preset area range, determining sensor quantity information according to production process information of the pollution source, and obtaining a pollution source monitoring range according to monitoring experience by a big data means;
Determining the topography and water information in the monitoring range according to the position information of each pollution source, and sequentially optimizing the sensor layout positions in the monitoring range of each pollution source through a genetic algorithm;
in sensor layout position optimization, using a pollution source position as an initial position, using mean square distance information between sensors as a fitness function, initializing chromosome population parameters, calculating individual fitness by adopting binary codes, selecting through iterative training, crossing, and mutating until the maximum iteration number, and obtaining a chromosome individual corresponding to the highest accuracy precision;
decoding a chromosome individual corresponding to the highest accuracy and precision to obtain the layout positions of the sensors in the pollution source monitoring range, and summarizing the sensor layout positions of the pollution sources to obtain a sensor layout scheme in the preset area range.
In this scheme, acquire the pollution monitoring information that different sensors gathered, carry out the characteristic extraction with multisource pollution monitoring information, specifically do:
setting a collection period of pollution monitoring information according to the position information and the monitoring type information of the sensor, carrying out data encryption on the collected pollution monitoring information through the characteristics of different pollution sources, and eliminating the pollution monitoring information in a database when unknown data which is inconsistent with the monitoring type information is contained in the data collected by the sensor;
The collected pollution monitoring information is packaged and transmitted to a database, data preprocessing is carried out in the database, the preprocessed pollution monitoring information is stored, and data history playback of the pollution monitoring information is realized;
extracting data characteristics of multi-source pollution monitoring information in a database, setting characteristic labels according to monitoring category information, and constructing characteristic sets of different pollution monitoring information;
the sensor acquisition threshold value is adaptively set on the basis of the acquisition period through the pollution monitoring concentration of different pollution monitoring information, and when the acquisition times of the sensor are greater than the preset acquisition threshold value, the characteristic extraction parameters in the database are optimized.
In the scheme, a multi-mode feature fusion model of pollution monitoring information is constructed, and associated features of different pollution monitoring information are acquired, specifically:
constructing a multi-mode feature fusion model based on the self-encoder and the graph convolution neural network, and converting feature sets of different pollution monitoring information into a pollution feature time sequence by combining time stamps;
coding and learning a pollution characteristic time sequence corresponding to each pollution monitoring information through a self-encoder to obtain a single-mode characteristic representation, and performing layer-by-layer learning according to the single-mode characteristic representation to obtain the correlation among different single-mode characteristic representations;
Marking a pollution characteristic time sequence with correlation, constructing a graph structure through a graph convolution neural network, using a single-mode characteristic representation corresponding to each pollution characteristic time sequence as a node structure, and selecting marking nodes with correlation with the node structure to construct an adjacent matrix;
the attention information between any two nodes is obtained through a global self-attention mechanism, an attention matrix is constructed, and new feature representations corresponding to each single-mode feature representation are generated through weighted aggregation of the attention moment matrix;
and processing new feature representations corresponding to the single-mode feature representations by utilizing neighbor aggregation, outputting a final feature matrix, and obtaining associated features of different pollution monitoring information.
In the scheme, the related characteristics are utilized to monitor the industrial pollution condition of a preset area range, pollution development trend is analyzed to generate pollution prediction information for pollution early warning, and the method specifically comprises the following steps:
acquiring process operation parameters corresponding to each pollution source in a preset area range, generating a process operation parameter time sequence in preset time, matching the associated features of different pollution monitoring information, and acquiring process operation features corresponding to each associated feature;
Analyzing the correlation between the development trend of various types of pollution and the process operation parameters through the matched time sequence to obtain process related characteristics;
building an industrial pollution condition monitoring model based on LSTM, acquiring historical pollution monitoring information of different sensors and historical process operation parameters from a database to build a data set, extracting relevant characteristics of the pollution monitoring information in the data set and relevant characteristics of the process to generate a training set;
training the monitoring model through the training set, outputting a model with prediction accuracy meeting a preset standard, and predicting pollution prediction information at the next moment through the associated characteristics of different pollution monitoring information and the process operation characteristics of a pollution source in a preset time period;
and generating dynamic display of different monitoring category information according to the pollution prediction information, and generating related early warning information.
In the scheme, related early warning information is generated, specifically:
dividing a preset area range into a plurality of subareas according to a sensor layout scheme in the preset area range and a sensor category, wherein each subarea at least comprises one sensor category;
determining pollution data references and dynamic change references of monitoring types in the current time period of different subareas according to historical pollution monitoring information in a database and process operation parameters of current pollution sources, and acquiring current pollution monitoring information acquired by sensors in the subareas;
Comparing the current pollution monitoring information with a corresponding monitoring type pollution data reference to obtain data deviation, and if the data deviation is larger than the dynamic change reference, generating sub-region pollution alarm and generating alarm information with class labels;
updating the pollution data reference of the subarea according to the current pollution monitoring information after judging, and carrying out pollution prediction of the subarea according to the updated pollution data reference to obtain pollution prediction information of the subarea after preset time;
and presetting the pollution environment capacity in the area range by utilizing a big data means, summarizing the pollution prediction information of each subarea, comparing the summarized pollution prediction information with the pollution environment capacity, and if the summarized pollution prediction information is larger than the pollution environment capacity, acquiring early warning information with a time stamp and a category label according to the time stamp of the pollution prediction information.
The second aspect of the invention also provides a real-time monitoring system for industrial pollution based on the Internet of things, which comprises: the system comprises a memory and a processor, wherein the memory comprises an industrial pollution real-time monitoring method program based on the Internet of things, and the industrial pollution real-time monitoring method program based on the Internet of things realizes the following steps when being executed by the processor:
Acquiring environmental pollution information in a preset area range, and determining pollution sources and pollution monitoring indexes according to the environmental pollution information;
generating a sensor layout scheme within a preset area range according to the pollution monitoring index and the pollution source information, and acquiring real-time data of an industrial pollution source through remote monitoring;
acquiring pollution monitoring information acquired by different sensors, performing feature extraction on multi-source pollution monitoring information, constructing a multi-mode feature fusion model of the pollution monitoring information, and acquiring associated features of different pollution monitoring information;
and monitoring the industrial pollution condition of the preset area range by utilizing the association characteristics, analyzing the pollution development trend to generate pollution prediction information, and carrying out pollution early warning.
The invention discloses an industrial pollution real-time monitoring method and system based on the Internet of things, comprising the following steps: acquiring environmental pollution information in a preset area range, and determining pollution sources and pollution monitoring indexes according to the environmental pollution information; generating a sensor layout scheme within a preset area according to the pollution monitoring index and the pollution source information, acquiring pollution monitoring information acquired by different sensors, performing feature extraction on multi-source pollution monitoring information, constructing a multi-mode feature fusion model of the pollution monitoring information, acquiring associated features of different pollution monitoring information, performing real-time monitoring on industrial pollution conditions within the preset area by utilizing the associated features, and simultaneously analyzing pollution development trend to generate pollution prediction information for pollution early warning. According to the invention, the industrial pollution is remotely monitored in real time through the Internet of things, the correlation among different pollution information is analyzed after the multi-mode pollution information is acquired, and the environmental pollution analysis and prediction are performed, so that the intelligent real-time industrial pollution monitoring is realized
Drawings
FIG. 1 shows a flow chart of an industrial pollution real-time monitoring method based on the Internet of things;
FIG. 2 is a flow chart of a method for acquiring associated features by constructing a multi-modal feature fusion model of pollution monitoring information according to the present invention;
FIG. 3 is a flow chart of a method of generating relevant warning information in accordance with the present invention;
fig. 4 shows a block diagram of an industrial pollution real-time monitoring system based on the internet of things.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flow chart of the industrial pollution real-time monitoring method based on the internet of things.
As shown in fig. 1, the first aspect of the present invention provides a real-time industrial pollution monitoring method based on the internet of things, which comprises:
S102, acquiring environmental pollution information in a preset area range, and determining a pollution source and a pollution monitoring index according to the environmental pollution information;
s104, generating a sensor layout scheme within a preset area range according to the pollution monitoring index and the pollution source information, and acquiring real-time data of the industrial pollution source through remote monitoring;
s106, acquiring pollution monitoring information acquired by different sensors, extracting characteristics of the multi-source pollution monitoring information, constructing a multi-mode characteristic fusion model of the pollution monitoring information, and acquiring associated characteristics of different pollution monitoring information;
s108, monitoring the industrial pollution condition of the preset area range by utilizing the correlation characteristics, analyzing the pollution development trend to generate pollution prediction information, and carrying out pollution early warning.
The method is characterized in that the environment pollution information such as water, atmosphere and soil in the preset area range is detected by a detector method, a colorimetry and other conventional environment detection methods and an orientation laboratory detection method, the matching tracing is carried out according to the environment pollution information and the determined pollution source information, and the corresponding pollution monitoring index is determined after the tracing. The technology of the Internet of things and the technology of the wireless sensor network are adopted, and the method is introduced into environmental pollution monitoring in a preset area range to collect information and analyze data of the environmental pollution, so that remote transmission of monitoring data of atmospheric pollution, water pollution, soil pollution and the like in industrial pollution detection is realized.
Obtaining geographic information and pollution source position information in a preset area range, determining sensor quantity information according to production process information of the pollution source, and obtaining a pollution source monitoring range according to monitoring experience by a big data means; determining the topography and water information in the monitoring range according to the position information of each pollution source, and sequentially optimizing the sensor layout positions in the monitoring range of each pollution source through a genetic algorithm; in sensor layout position optimization, using a pollution source position as an initial position, using mean square distance information between sensors as a fitness function, initializing chromosome population parameters, calculating individual fitness by adopting binary codes, selecting through iterative training, crossing, and mutating until the maximum iteration number, and obtaining a chromosome individual corresponding to the highest accuracy precision; decoding a chromosome individual corresponding to the highest accuracy and precision to obtain the layout positions of the sensors in the pollution source monitoring range, and summarizing the sensor layout positions of the pollution sources to obtain a sensor layout scheme in the preset area range.
The method is characterized in that the acquisition period of pollution monitoring information is set according to the position information and the monitoring type information of the sensor, enterprise production facilities of different pollution sources are different, so that the acquired pollution monitoring information is encrypted according to the characteristics of the different pollution sources to ensure that a network is not attacked, and when the data acquired by the sensor contains unknown data which is inconsistent with the monitoring type information, the unknown data are removed from a database; the collected pollution monitoring information is packaged and transmitted to a database, pretreatment such as data cleaning is carried out in the database, the pretreated pollution monitoring information is stored, and data history playback of the pollution monitoring information is realized; extracting data characteristics of multi-source pollution monitoring information in a database, setting characteristic labels according to monitoring category information, and constructing characteristic sets of different pollution monitoring information; the pollution monitoring concentration of different pollution monitoring information is adaptively set on the basis of the acquisition period to acquire a threshold value, when the acquisition times of the sensor is larger than a preset acquisition threshold value, the characteristic extraction parameters in the database are optimized, and when the pollution monitoring concentration is increased, the monitoring parameters are increased, so that the monitoring efficiency is improved.
FIG. 2 shows a flow chart of a method for acquiring associated features by constructing a multi-modal feature fusion model of pollution monitoring information.
According to the embodiment of the invention, a multi-mode feature fusion model of pollution monitoring information is constructed, and the associated features of different pollution monitoring information are obtained, specifically:
s202, constructing a multi-mode feature fusion model based on a self-encoder and a graph convolution neural network, and converting feature sets of different pollution monitoring information into a pollution feature time sequence by combining time stamps;
s204, coding and learning a pollution characteristic time sequence corresponding to each pollution monitoring information through a self-coder to obtain a single-mode characteristic representation, and performing layer-by-layer learning according to the single-mode characteristic representation to obtain correlation among different single-mode characteristic representations;
s206, marking the pollution characteristic time sequences with correlation, constructing a graph structure through a graph convolution neural network, using a single-mode characteristic representation corresponding to each pollution characteristic time sequence as a node structure, and selecting marking nodes with correlation with the node structure to construct an adjacent matrix;
s208, attention information between any two nodes is obtained through a global self-attention mechanism, an attention matrix is constructed, and new feature representations corresponding to each single-mode feature representation are generated through weighted aggregation of the attention moment matrix;
S210, processing new feature representations corresponding to the single-mode feature representations by utilizing neighbor aggregation, outputting a final feature matrix, and obtaining associated features of different pollution monitoring information.
The method comprises the steps of importing pollution characteristic time sequences acquired by different sensors into a self-encoder for training, extracting middle characteristics of the different pollution characteristic time sequences, learning single-mode characteristic representation of the different pollution characteristic time sequences, carrying out characteristic reconstruction on the pollution characteristic time sequences, taking a characteristic matrix after the characteristic reconstruction as an input of a second self-encoder, acquiring characteristic correlation among the different pollution characteristic time sequences according to the characteristics learned by the last self-encoder training, mining modal correlation among multi-mode pollution monitoring information through hidden layer representation of the two self-encoders, marking the different pollution characteristic time sequences with the correlation, and constructing an adjacent matrix by taking the adjacent node as a neighbor node of a target node in a graph structure; the attention information q is acquired according to a global self-attention mechanism, and the calculation formula is as follows: q=lrelu ([ f (x) i W)||f(x j W)]a T ) Wherein LRELU is an activation function, f is a normalized representation, x i x j Respectively representing any two nodes, W, a is learning weight, T is matrix transposition, I is vector splicing, an attention matrix is constructed on the basis of attention information, the characteristics corresponding to the nodes are weighted and aggregated to obtain a new characteristic matrix, the characteristic representation is updated through a neighbor aggregation mechanism of a graph convolution neural network, and finally, the associated characteristics of different pollution monitoring information are output: x is X * ＝LRELU(KW t Σexw), wherein X * For the aggregated representation of features, K is an adjacency matrix, W t The weight matrix is E, the attention matrix is E, and the node corresponding feature is X.
FIG. 3 is a flow chart of a method of generating relevant warning information in accordance with the present invention.
According to the embodiment of the invention, the related early warning information is generated, specifically:
s302, dividing a preset area range into a plurality of subareas according to a sensor layout scheme in the preset area range and a sensor category, wherein each subarea at least comprises one sensor category;
s304, determining pollution data references and dynamic change references of monitoring types in the current time period of different subareas according to historical pollution monitoring information in a database and process operation parameters of current pollution sources, and acquiring current pollution monitoring information acquired by sensors in the subareas;
s306, comparing the current pollution monitoring information with a pollution data reference of a corresponding monitoring type to obtain data deviation, and if the data deviation is larger than the dynamic change reference, generating sub-area pollution alarm and generating alarm information with category labels;
s308, updating the pollution data standard of the subarea according to the current pollution monitoring information after judging, and carrying out pollution prediction of the subarea according to the updated pollution data standard to obtain pollution prediction information of the subarea after preset time;
S310, presetting the pollution environment capacity in the area range by utilizing a big data means, summarizing the pollution prediction information of each subarea, comparing the summarized pollution prediction information with the pollution environment capacity, and if the summarized pollution prediction information is larger than the pollution environment capacity, acquiring early warning information with a time stamp and a category label according to the time stamp of the pollution prediction information.
It should be noted that, according to the historical pollution monitoring information in the database and the process operation parameters of the current pollution source, determining pollution data references and dynamic change references of each monitoring type in the current time period of different subareas, setting pollution thresholds of different monitoring types on the basis of the pollution data references, and if the current pollution monitoring information is greater than the pollution threshold, generating alarm information;
acquiring process operation parameters corresponding to each pollution source in a preset area range, generating a process operation parameter time sequence in preset time, matching the associated features of different pollution monitoring information, and acquiring process operation features corresponding to each associated feature; analyzing the correlation between the development trend of various types of pollution and the process operation parameters through the matched time sequence to obtain process related characteristics; building an industrial pollution condition monitoring model based on LSTM, acquiring historical pollution monitoring information of different sensors and historical process operation parameters from a database to build a data set, extracting relevant characteristics of the pollution monitoring information in the data set and relevant characteristics of the process to generate a training set; training the monitoring model through the training set, outputting a model with prediction accuracy meeting a preset standard, and predicting pollution prediction information at the next moment through the associated characteristics of different pollution monitoring information and the process operation characteristics of a pollution source in a preset time period; and generating dynamic display of different monitoring category information according to the pollution prediction information, and generating related early warning information.
According to the embodiment of the invention, the validity of the sensor in the preset area range is judged according to the pollution monitoring information, specifically:
acquiring a plurality of subareas in a preset area range, taking other subareas in the preset area of the subareas as adjacent areas, and taking the subareas with alarm information as target subareas;
extracting pollution monitoring information corresponding to alarm information in a target subarea, acquiring monitoring types of the pollution monitoring information, and acquiring pollution prediction information and corresponding pollution early warning information of the same monitoring type in an adjacent area;
selecting a subarea closest to the current time according to the early warning timestamp of the pollution early warning information, marking the corresponding subarea, and establishing a temporary key monitoring task according to the interval time;
judging the dynamic change corresponding to the pollution monitoring information of the mark sub-area during the key monitoring task, and if the dynamic change is smaller than a preset threshold value, generating failure early warning of the monitoring type sensor corresponding to the alarm information of the target sub-area;
and if the dynamic change is larger than the level preset threshold, ending the key monitoring task, analyzing the historical pollution monitoring information of the target subarea, and if the similarity between the pollution change characteristics of the current target subarea and the historical pollution monitoring information does not meet the preset standard, generating pollution source early warning to remind related personnel to trace new pollution sources in the target subarea.
Fig. 4 shows a block diagram of an industrial pollution real-time monitoring system based on the internet of things.
The second aspect of the present invention also provides a real-time industrial pollution monitoring system 4 based on the internet of things, which comprises: the device comprises a memory 41 and a processor 42, wherein the memory comprises an industrial pollution real-time monitoring method program based on the Internet of things, and the industrial pollution real-time monitoring method program based on the Internet of things realizes the following steps when being executed by the processor:
acquiring environmental pollution information in a preset area range, and determining pollution sources and pollution monitoring indexes according to the environmental pollution information;
generating a sensor layout scheme within a preset area range according to the pollution monitoring index and the pollution source information, and acquiring real-time data of an industrial pollution source through remote monitoring;
acquiring pollution monitoring information acquired by different sensors, performing feature extraction on multi-source pollution monitoring information, constructing a multi-mode feature fusion model of the pollution monitoring information, and acquiring associated features of different pollution monitoring information;
and monitoring the industrial pollution condition of the preset area range by utilizing the association characteristics, analyzing the pollution development trend to generate pollution prediction information, and carrying out pollution early warning.
The method is characterized in that the environment pollution information such as water, atmosphere and soil in the preset area range is detected by a detector method, a colorimetry and other conventional environment detection methods and an orientation laboratory detection method, the matching tracing is carried out according to the environment pollution information and the determined pollution source information, and the corresponding pollution monitoring index is determined after the tracing. The technology of the Internet of things and the technology of the wireless sensor network are adopted, and the method is introduced into environmental pollution monitoring in a preset area range to collect information and analyze data of the environmental pollution, so that remote transmission of monitoring data of atmospheric pollution, water pollution, soil pollution and the like in industrial pollution detection is realized.
Obtaining geographic information and pollution source position information in a preset area range, determining sensor quantity information according to production process information of the pollution source, and obtaining a pollution source monitoring range according to monitoring experience by a big data means; determining the topography and water information in the monitoring range according to the position information of each pollution source, and sequentially optimizing the sensor layout positions in the monitoring range of each pollution source through a genetic algorithm; in sensor layout position optimization, using a pollution source position as an initial position, using mean square distance information between sensors as a fitness function, initializing chromosome population parameters, calculating individual fitness by adopting binary codes, selecting through iterative training, crossing, and mutating until the maximum iteration number, and obtaining a chromosome individual corresponding to the highest accuracy precision; decoding a chromosome individual corresponding to the highest accuracy and precision to obtain the layout positions of the sensors in the pollution source monitoring range, and summarizing the sensor layout positions of the pollution sources to obtain a sensor layout scheme in the preset area range.
The method is characterized in that the acquisition period of pollution monitoring information is set according to the position information and the monitoring type information of the sensor, enterprise production facilities of different pollution sources are different, so that the acquired pollution monitoring information is encrypted according to the characteristics of the different pollution sources to ensure that a network is not attacked, and when the data acquired by the sensor contains unknown data which is inconsistent with the monitoring type information, the unknown data are removed from a database; the collected pollution monitoring information is packaged and transmitted to a database, pretreatment such as data cleaning is carried out in the database, the pretreated pollution monitoring information is stored, and data history playback of the pollution monitoring information is realized; extracting data characteristics of multi-source pollution monitoring information in a database, setting characteristic labels according to monitoring category information, and constructing characteristic sets of different pollution monitoring information; the pollution monitoring concentration of different pollution monitoring information is adaptively set on the basis of the acquisition period to acquire a threshold value, when the acquisition times of the sensor is larger than a preset acquisition threshold value, the characteristic extraction parameters in the database are optimized, and when the pollution monitoring concentration is increased, the monitoring parameters are increased, so that the monitoring efficiency is improved.
According to the embodiment of the invention, a multi-mode feature fusion model of pollution monitoring information is constructed, and the associated features of different pollution monitoring information are obtained, specifically:
constructing a multi-mode feature fusion model based on the self-encoder and the graph convolution neural network, and converting feature sets of different pollution monitoring information into a pollution feature time sequence by combining time stamps;
coding and learning a pollution characteristic time sequence corresponding to each pollution monitoring information through a self-encoder to obtain a single-mode characteristic representation, and performing layer-by-layer learning according to the single-mode characteristic representation to obtain the correlation among different single-mode characteristic representations;
marking a pollution characteristic time sequence with correlation, constructing a graph structure through a graph convolution neural network, using a single-mode characteristic representation corresponding to each pollution characteristic time sequence as a node structure, and selecting marking nodes with correlation with the node structure to construct an adjacent matrix;
the attention information between any two nodes is obtained through a global self-attention mechanism, an attention matrix is constructed, and new feature representations corresponding to each single-mode feature representation are generated through weighted aggregation of the attention moment matrix;
and processing new feature representations corresponding to the single-mode feature representations by utilizing neighbor aggregation, outputting a final feature matrix, and obtaining associated features of different pollution monitoring information.
The method is characterized in that the pollution characteristic time sequences acquired by different sensors are imported into a self-encoder for training, the middle characteristics of the different pollution characteristic time sequences are extracted, the single-mode characteristic representation of the different pollution characteristic time sequences is learned, the pollution characteristic time sequences are subjected to characteristic reconstruction, and a characteristic matrix after the characteristic reconstruction is used as a second self-encoderAccording to the characteristic learned by the last self-encoder training, obtaining the characteristic correlation among different pollution characteristic time sequences, mining the correlation among modes among multi-mode pollution monitoring information through the hidden layer representation of the two self-encoders, marking the different pollution characteristic time sequences with the correlation, and constructing an adjacent matrix by using the different pollution characteristic time sequences as neighbor nodes of target nodes in a graph structure; the attention information q is acquired according to a global self-attention mechanism, and the calculation formula is as follows: q=lrelu ([ f (x) i W)||f(x j W)]a T ) Wherein LRELU is an activation function, f is a normalized representation, x i x j Respectively representing any two nodes, W, a is learning weight, T is matrix transposition, I is vector splicing, an attention matrix is constructed on the basis of attention information, the characteristics corresponding to the nodes are weighted and aggregated to obtain a new characteristic matrix, the characteristic representation is updated through a neighbor aggregation mechanism of a graph convolution neural network, and finally, the associated characteristics of different pollution monitoring information are output: x is X * ＝LRELU(KW t Σexw), wherein X * For the aggregated representation of features, K is an adjacency matrix, W t The weight matrix is E, the attention matrix is E, and the node corresponding feature is X.
According to the embodiment of the invention, the related early warning information is generated, specifically:
dividing a preset area range into a plurality of subareas according to a sensor layout scheme in the preset area range and a sensor category, wherein each subarea at least comprises one sensor category;
determining pollution data references and dynamic change references of monitoring types in the current time period of different subareas according to historical pollution monitoring information in a database and process operation parameters of current pollution sources, and acquiring current pollution monitoring information acquired by sensors in the subareas;
comparing the current pollution monitoring information with a corresponding monitoring type pollution data reference to obtain data deviation, and if the data deviation is larger than the dynamic change reference, generating sub-region pollution alarm and generating alarm information with class labels;
updating the pollution data reference of the subarea according to the current pollution monitoring information after judging, and carrying out pollution prediction of the subarea according to the updated pollution data reference to obtain pollution prediction information of the subarea after preset time;
And presetting the pollution environment capacity in the area range by utilizing a big data means, summarizing the pollution prediction information of each subarea, comparing the summarized pollution prediction information with the pollution environment capacity, and if the summarized pollution prediction information is larger than the pollution environment capacity, acquiring early warning information with a time stamp and a category label according to the time stamp of the pollution prediction information.
It should be noted that, according to the historical pollution monitoring information in the database and the process operation parameters of the current pollution source, determining pollution data references and dynamic change references of each monitoring type in the current time period of different subareas, setting pollution thresholds of different monitoring types on the basis of the pollution data references, and if the current pollution monitoring information is greater than the pollution threshold, generating alarm information;
acquiring process operation parameters corresponding to each pollution source in a preset area range, generating a process operation parameter time sequence in preset time, matching the associated features of different pollution monitoring information, and acquiring process operation features corresponding to each associated feature; analyzing the correlation between the development trend of various types of pollution and the process operation parameters through the matched time sequence to obtain process related characteristics; building an industrial pollution condition monitoring model based on LSTM, acquiring historical pollution monitoring information of different sensors and historical process operation parameters from a database to build a data set, extracting relevant characteristics of the pollution monitoring information in the data set and relevant characteristics of the process to generate a training set; training the monitoring model through the training set, outputting a model with prediction accuracy meeting a preset standard, and predicting pollution prediction information at the next moment through the associated characteristics of different pollution monitoring information and the process operation characteristics of a pollution source in a preset time period; and generating dynamic display of different monitoring category information according to the pollution prediction information, and generating related early warning information.
The third aspect of the present invention also provides a computer readable storage medium, where the computer readable storage medium includes a real-time monitoring method program based on the internet of things, and when the real-time monitoring method program based on the internet of things is executed by a processor, the steps of the real-time monitoring method based on the internet of things are implemented.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The industrial pollution real-time monitoring method based on the Internet of things is characterized by comprising the following steps of:
acquiring environmental pollution information in a preset area range, and determining pollution sources and pollution monitoring indexes according to the environmental pollution information;
generating a sensor layout scheme within a preset area range according to the pollution monitoring index and the pollution source information, and acquiring real-time data of an industrial pollution source through remote monitoring;
acquiring pollution monitoring information acquired by different sensors, performing feature extraction on multi-source pollution monitoring information, constructing a multi-mode feature fusion model of the pollution monitoring information, and acquiring associated features of different pollution monitoring information;
and monitoring the industrial pollution condition of the preset area range by utilizing the association characteristics, analyzing the pollution development trend to generate pollution prediction information, and carrying out pollution early warning.
2. The industrial pollution real-time monitoring method based on the internet of things according to claim 1, wherein a sensor layout scheme within a preset area range is generated according to the pollution monitoring index and pollution source information, specifically:
obtaining geographic information and pollution source position information in a preset area range, determining sensor quantity information according to production process information of the pollution source, and obtaining a pollution source monitoring range according to monitoring experience by a big data means;
determining the topography and water information in the monitoring range according to the position information of each pollution source, and sequentially optimizing the sensor layout positions in the monitoring range of each pollution source through a genetic algorithm;
in sensor layout position optimization, using a pollution source position as an initial position, using mean square distance information between sensors as a fitness function, initializing chromosome population parameters, calculating individual fitness by adopting binary codes, selecting through iterative training, crossing, and mutating until the maximum iteration number, and obtaining a chromosome individual corresponding to the highest accuracy precision;
decoding a chromosome individual corresponding to the highest accuracy and precision to obtain the layout positions of the sensors in the pollution source monitoring range, and summarizing the sensor layout positions of the pollution sources to obtain a sensor layout scheme in the preset area range.
3. The industrial pollution real-time monitoring method based on the internet of things according to claim 1, wherein the pollution monitoring information acquired by different sensors is acquired, and the multi-source pollution monitoring information is subjected to characteristic extraction, specifically:
setting a collection period of pollution monitoring information according to the position information and the monitoring type information of the sensor, carrying out data encryption on the collected pollution monitoring information through the characteristics of different pollution sources, and eliminating the pollution monitoring information in a database when unknown data which is inconsistent with the monitoring type information is contained in the data collected by the sensor;
the collected pollution monitoring information is packaged and transmitted to a database, data preprocessing is carried out in the database, the preprocessed pollution monitoring information is stored, and data history playback of the pollution monitoring information is realized;
extracting data characteristics of multi-source pollution monitoring information in a database, setting characteristic labels according to monitoring category information, and constructing characteristic sets of different pollution monitoring information;
the sensor acquisition threshold value is adaptively set on the basis of the acquisition period through the pollution monitoring concentration of different pollution monitoring information, and when the acquisition times of the sensor are greater than the preset acquisition threshold value, the characteristic extraction parameters in the database are optimized.
4. The industrial pollution real-time monitoring method based on the internet of things according to claim 1, wherein a multi-mode feature fusion model of pollution monitoring information is constructed, and associated features of different pollution monitoring information are obtained, specifically:
constructing a multi-mode feature fusion model based on the self-encoder and the graph convolution neural network, and converting feature sets of different pollution monitoring information into a pollution feature time sequence by combining time stamps;
coding and learning a pollution characteristic time sequence corresponding to each pollution monitoring information through a self-encoder to obtain a single-mode characteristic representation, and performing layer-by-layer learning according to the single-mode characteristic representation to obtain the correlation among different single-mode characteristic representations;
marking a pollution characteristic time sequence with correlation, constructing a graph structure through a graph convolution neural network, using a single-mode characteristic representation corresponding to each pollution characteristic time sequence as a node structure, and selecting marking nodes with correlation with the node structure to construct an adjacent matrix;
the attention information between any two nodes is obtained through a global self-attention mechanism, an attention matrix is constructed, and new feature representations corresponding to each single-mode feature representation are generated through weighted aggregation of the attention moment matrix;
And processing new feature representations corresponding to the single-mode feature representations by utilizing neighbor aggregation, outputting a final feature matrix, and obtaining associated features of different pollution monitoring information.
5. The real-time monitoring method for industrial pollution based on the internet of things according to claim 1, wherein the industrial pollution condition of the preset area range is monitored by using the correlation characteristics, pollution development trend is analyzed to generate pollution prediction information for pollution early warning, and the method specifically comprises the following steps:
acquiring process operation parameters corresponding to each pollution source in a preset area range, generating a process operation parameter time sequence in preset time, matching the associated features of different pollution monitoring information, and acquiring process operation features corresponding to each associated feature;
analyzing the correlation between the development trend of various types of pollution and the process operation parameters through the matched time sequence to obtain process related characteristics;
building an industrial pollution condition monitoring model based on LSTM, acquiring historical pollution monitoring information of different sensors and historical process operation parameters from a database to build a data set, extracting relevant characteristics of the pollution monitoring information in the data set and relevant characteristics of the process to generate a training set;
Training the monitoring model through the training set, outputting a model with prediction accuracy meeting a preset standard, and predicting pollution prediction information at the next moment through the associated characteristics of different pollution monitoring information and the process operation characteristics of a pollution source in a preset time period;
and generating dynamic display of different monitoring category information according to the pollution prediction information, and generating related early warning information.
6. The method for monitoring industrial pollution in real time based on the internet of things according to claim 5, wherein the generation of the relevant early warning information is specifically as follows:
dividing a preset area range into a plurality of subareas according to a sensor layout scheme in the preset area range and a sensor category, wherein each subarea at least comprises one sensor category;
determining pollution data references and dynamic change references of monitoring types in the current time period of different subareas according to historical pollution monitoring information in a database and process operation parameters of current pollution sources, and acquiring current pollution monitoring information acquired by sensors in the subareas;
comparing the current pollution monitoring information with a corresponding monitoring type pollution data reference to obtain data deviation, and if the data deviation is larger than the dynamic change reference, generating sub-region pollution alarm and generating alarm information with class labels;
Updating the pollution data reference of the subarea according to the current pollution monitoring information after judging, and carrying out pollution prediction of the subarea according to the updated pollution data reference to obtain pollution prediction information of the subarea after preset time;
and presetting the pollution environment capacity in the area range by utilizing a big data means, summarizing the pollution prediction information of each subarea, comparing the summarized pollution prediction information with the pollution environment capacity, and if the summarized pollution prediction information is larger than the pollution environment capacity, acquiring early warning information with a time stamp and a category label according to the time stamp of the pollution prediction information.
7. Industrial pollution real-time monitoring system based on the Internet of things, which is characterized by comprising: the system comprises a memory and a processor, wherein the memory comprises an industrial pollution real-time monitoring method program based on the Internet of things, and the industrial pollution real-time monitoring method program based on the Internet of things realizes the following steps when being executed by the processor:
acquiring environmental pollution information in a preset area range, and determining pollution sources and pollution monitoring indexes according to the environmental pollution information;
generating a sensor layout scheme within a preset area range according to the pollution monitoring index and the pollution source information, and acquiring real-time data of an industrial pollution source through remote monitoring;
Acquiring pollution monitoring information acquired by different sensors, performing feature extraction on multi-source pollution monitoring information, constructing a multi-mode feature fusion model of the pollution monitoring information, and acquiring associated features of different pollution monitoring information;
and monitoring the industrial pollution condition of the preset area range in real time by utilizing the association characteristics, analyzing the pollution development trend to generate pollution prediction information, and carrying out pollution early warning.
8. The industrial pollution real-time monitoring system based on the internet of things according to claim 7, wherein the pollution monitoring information acquired by different sensors is acquired, and the multi-source pollution monitoring information is subjected to characteristic extraction, specifically:
setting a collection period of pollution monitoring information according to the position information and the monitoring type information of the sensor, carrying out data encryption on the collected pollution monitoring information through the characteristics of different pollution sources, and eliminating the pollution monitoring information in a database when unknown data which is inconsistent with the monitoring type information is contained in the data collected by the sensor;
the collected pollution monitoring information is packaged and transmitted to a database, data preprocessing is carried out in the database, the preprocessed pollution monitoring information is stored, and data history playback of the pollution monitoring information is realized;
Extracting data characteristics of multi-source pollution monitoring information in a database, setting characteristic labels according to monitoring category information, and constructing characteristic sets of different pollution monitoring information;
the sensor acquisition threshold value is adaptively set on the basis of the acquisition period through the pollution monitoring concentration of different pollution monitoring information, and when the acquisition times of the sensor are greater than the preset acquisition threshold value, the characteristic extraction parameters in the database are optimized.
9. The industrial pollution real-time monitoring system based on the internet of things according to claim 7, wherein the multi-mode feature fusion model of the pollution monitoring information is constructed, and the associated features of different pollution monitoring information are obtained, specifically:
constructing a multi-mode feature fusion model based on the self-encoder and the graph convolution neural network, and converting feature sets of different pollution monitoring information into a pollution feature time sequence by combining time stamps;
coding and learning a pollution characteristic time sequence corresponding to each pollution monitoring information through a self-encoder to obtain a single-mode characteristic representation, and performing layer-by-layer learning according to the single-mode characteristic representation to obtain the correlation among different single-mode characteristic representations;
marking a pollution characteristic time sequence with correlation, constructing a graph structure through a graph convolution neural network, using a single-mode characteristic representation corresponding to each pollution characteristic time sequence as a node structure, and selecting marking nodes with correlation with the node structure to construct an adjacent matrix;
The attention information between any two nodes is obtained through a global self-attention mechanism, an attention matrix is constructed, and new feature representations corresponding to each single-mode feature representation are generated through weighted aggregation of the attention moment matrix;
and processing new feature representations corresponding to the single-mode feature representations by utilizing neighbor aggregation, outputting a final feature matrix, and obtaining associated features of different pollution monitoring information.
10. The industrial pollution real-time monitoring system based on the internet of things according to claim 7, wherein the industrial pollution condition of the preset area range is monitored by using the correlation characteristics, pollution development trend is analyzed to generate pollution prediction information for pollution early warning, and specifically:
acquiring process operation parameters corresponding to each pollution source in a preset area range, generating a process operation parameter time sequence in preset time, matching the associated features of different pollution monitoring information, and acquiring process operation features corresponding to each associated feature;
analyzing the correlation between the development trend of various types of pollution and the process operation parameters through the matched time sequence to obtain process related characteristics;
building an industrial pollution condition monitoring model based on LSTM, acquiring historical pollution monitoring information of different sensors and historical process operation parameters from a database to build a data set, extracting relevant characteristics of the pollution monitoring information in the data set and relevant characteristics of the process to generate a training set;
Training the monitoring model through the training set, outputting a model with prediction accuracy meeting a preset standard, and predicting pollution prediction information at the next moment through the associated characteristics of different pollution monitoring information and the process operation characteristics of a pollution source in a preset time period;
and generating dynamic display of different monitoring category information according to the pollution prediction information, and generating related early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310451705.4A CN116485202B (en) | 2023-04-25 | 2023-04-25 | Industrial pollution real-time monitoring method and system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310451705.4A CN116485202B (en) | 2023-04-25 | 2023-04-25 | Industrial pollution real-time monitoring method and system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116485202A true CN116485202A (en) | 2023-07-25 |
| CN116485202B CN116485202B (en) | 2024-03-08 |
Family
ID=87226436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310451705.4A Active CN116485202B (en) | 2023-04-25 | 2023-04-25 | Industrial pollution real-time monitoring method and system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485202B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117557044A (en) * | 2023-11-22 | 2024-02-13 | 山东德才建设有限公司 | Building operation environment monitoring method and equipment based on Internet of things platform |
| CN117706045A (en) * | 2024-02-06 | 2024-03-15 | 四川省德阳生态环境监测中心站 | Combined control method and system for realizing atmospheric ozone monitoring equipment based on Internet of things |
| CN118604289A (en) * | 2024-08-08 | 2024-09-06 | 杭州分形环保科技有限公司 | Intelligent water pollution monitoring method and system based on Internet of things and edge calculation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104270773A (en) * | 2014-10-17 | 2015-01-07 | 长江水利委员会长江科学院 | Drainage basin sensor coverage net optimizing method based on genetic algorithm multi-objective optimization |
| FR3083553A1 (en) * | 2018-07-09 | 2020-01-10 | Suez Groupe | IMPROVED PLACEMENT OF PHYSICO-CHEMICAL PARAMETER SENSORS IN A FLUID |
| CN112783988A (en) * | 2020-12-29 | 2021-05-11 | 同济大学 | Monitoring feedback and analysis method for internal environmental parameters of air-conditioning ventilation system |
| CN113837361A (en) * | 2021-09-01 | 2021-12-24 | 中咨公路养护检测技术有限公司 | Air pollutant concentration prediction method and system |
| CN113984969A (en) * | 2021-10-26 | 2022-01-28 | 西安交通大学 | Air quality prediction method and system based on multi-source space-time data fusion |
| CN114841400A (en) * | 2022-03-25 | 2022-08-02 | 哈尔滨工程大学 | Air quality prediction method based on multi-task space-time diagram convolution |
-
2023
- 2023-04-25 CN CN202310451705.4A patent/CN116485202B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104270773A (en) * | 2014-10-17 | 2015-01-07 | 长江水利委员会长江科学院 | Drainage basin sensor coverage net optimizing method based on genetic algorithm multi-objective optimization |
| FR3083553A1 (en) * | 2018-07-09 | 2020-01-10 | Suez Groupe | IMPROVED PLACEMENT OF PHYSICO-CHEMICAL PARAMETER SENSORS IN A FLUID |
| CN112424599A (en) * | 2018-07-09 | 2021-02-26 | 苏伊士集团 | Improved placement of a physical-chemical parameter sensor in a fluid |
| US20210272028A1 (en) * | 2018-07-09 | 2021-09-02 | Suez Groupe | Placement of physico-chemical parameter sensors in a fluid |
| CN112783988A (en) * | 2020-12-29 | 2021-05-11 | 同济大学 | Monitoring feedback and analysis method for internal environmental parameters of air-conditioning ventilation system |
| CN113837361A (en) * | 2021-09-01 | 2021-12-24 | 中咨公路养护检测技术有限公司 | Air pollutant concentration prediction method and system |
| CN113984969A (en) * | 2021-10-26 | 2022-01-28 | 西安交通大学 | Air quality prediction method and system based on multi-source space-time data fusion |
| CN114841400A (en) * | 2022-03-25 | 2022-08-02 | 哈尔滨工程大学 | Air quality prediction method based on multi-task space-time diagram convolution |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117557044A (en) * | 2023-11-22 | 2024-02-13 | 山东德才建设有限公司 | Building operation environment monitoring method and equipment based on Internet of things platform |
| CN117557044B (en) * | 2023-11-22 | 2024-04-09 | 山东德才建设有限公司 | Building operation environment monitoring method and equipment based on Internet of things platform |
| CN117706045A (en) * | 2024-02-06 | 2024-03-15 | 四川省德阳生态环境监测中心站 | Combined control method and system for realizing atmospheric ozone monitoring equipment based on Internet of things |
| CN117706045B (en) * | 2024-02-06 | 2024-05-10 | 四川省德阳生态环境监测中心站 | Combined control method and system for realizing atmospheric ozone monitoring equipment based on Internet of things |
| CN118604289A (en) * | 2024-08-08 | 2024-09-06 | 杭州分形环保科技有限公司 | Intelligent water pollution monitoring method and system based on Internet of things and edge calculation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116485202B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116485202B (en) | Industrial pollution real-time monitoring method and system based on Internet of things | |
| CN115578015B (en) | Sewage treatment whole process supervision method, system and storage medium based on Internet of things | |
| CN116186566B (en) | Diffusion prediction method and system based on deep learning | |
| CN116385689B (en) | Visual information management method, system and medium for site pollution data | |
| CN116384754B (en) | Deep learning-based environmental pollution risk assessment method in chemical industry park | |
| CN109656793A (en) | A kind of information system performance stereoscopic monitoring method based on multi-source heterogeneous data fusion | |
| CN117220978B (en) | Quantitative evaluation system and evaluation method for network security operation model | |
| CN111223027A (en) | Urban earthquake disaster risk assessment method and system | |
| CN117171695B (en) | Method and system for evaluating ecological restoration effect of antibiotic contaminated soil | |
| CN117391727B (en) | Carbon neutralization method and system for negative carbon emission | |
| CN117196350B (en) | Mine geological environment characteristic monitoring and recovery treatment method and system | |
| CN117291781B (en) | Sudden water pollution tracing method, equipment and medium | |
| CN116109462A (en) | Pollution monitoring and early warning method and system for drinking water source area after natural disaster | |
| CN118037047A (en) | Mine safety monitoring system based on AI | |
| CN117171223A (en) | Microorganism culture scheme recommendation method and system in microorganism repair process | |
| CN118171920B (en) | LLM model-based park safety emergency response method, device and medium | |
| CN118094266B (en) | Intelligent terminal nuclear radiation detection analysis method and system | |
| CN117992861B (en) | Electric power data accuracy checking method and system | |
| CN113486754B (en) | Event evolution prediction method and system based on video | |
| CN117172996B (en) | Microbial activity identification monitoring method and system for ecological environment restoration | |
| CN117811843A (en) | Network intrusion detection method and system based on big data analysis and autonomous learning | |
| Zhang et al. | Situational-aware multi-graph convolutional recurrent network (sa-mgcrn) for travel demand forecasting during wildfires | |
| CN116384775B (en) | Management method, system and storage medium of pollution site monitoring equipment | |
| CN117675335A (en) | Analysis computer network security prediction method based on big data information | |
| CN116633608B (en) | Risk prediction method and system for network security |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |