Industrial pollution tracing method and system based on machine learning

Abstract

The invention relates to the technical field of industrial pollution monitoring, in particular to an industrial pollution source tracing method and system based on machine learning, which can accurately and efficiently determine a pollution source in an industrial park and meet high requirements of environmental protection laws and regulations and the public on environmental protection. The method is used in an industrial park, when an industrial pollution monitoring point monitors that pollution indexes exceed the standard and the emission of each factory in the park meets the emission standard for pollution discharge, pollution is subjected to traceability analysis, and a pollution source with the maximum participation degree in the pollution exceeding event is determined. The method comprises the following steps: acquiring pollution monitoring data information monitored by an industrial pollution monitoring point; carrying out standard-exceeding pollutant feature extraction on the pollution monitoring data information to obtain a park pollutant feature portrait; the park pollutant feature portrait comprises the components of the standard-exceeding pollutants in the park and the real-time concentration of each standard-exceeding pollutant; and matching the park pollutant feature portraits in a pre-established factory pollutant discharge database.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial pollution monitoring, and in particular to an industrial pollution source tracing method and system based on machine learning. Background Art

[0002] In the current social context of rapid industrialization, industrial parks, as one of the main driving forces of economic development, face unprecedented challenges in environmental management, especially pollution prevention and control. With increasingly stringent environmental laws and regulations and the improvement of public environmental awareness, accurately and effectively tracking and controlling industrial pollution sources has become a key link in environmental protection work. However, in the complex environment of industrial parks, it is often difficult to accurately determine the responsible party for pollution by relying solely on traditional pollution source monitoring methods, especially in the complex situation where all factories appear to be compliant with emissions, but pollution monitoring points still record pollution exceeding the standard. This problem is more prominent.

[0003] Existing industrial pollution source tracing methods usually rely on data from fixed monitoring stations and regular inspections of each factory's emission outlets. This method is not only ineffective, but also incapable of coping with complex pollution, cross-contamination or instantaneous emission events. In addition, due to the influence of meteorological conditions and geographical environmental factors on the diffusion path and concentration distribution of pollutants, it is difficult to accurately locate the party responsible for the actual environmental pollution based solely on emission outlet monitoring data. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides an industrial pollution tracing method and system based on machine learning, which can accurately and efficiently determine the pollution sources in industrial parks and meet the environmental protection laws and regulations and the public's high requirements for environmental protection.

[0005] In a first aspect, the present invention provides an industrial pollution source tracing method based on machine learning. The method is used to trace the pollution source in an industrial park when the industrial pollution monitoring point detects that the pollution index exceeds the standard, and the emissions of various factories in the park meet the emission standards for discharge. The method determines the pollution source with the greatest involvement in the pollution exceeding the standard event. The method includes:

[0006] Obtain pollution monitoring data information monitored by industrial pollution monitoring points;

[0007] Extract the characteristics of pollutants exceeding the standard from the pollution monitoring data information to obtain a characteristic profile of pollutants in the park; the characteristic profile of pollutants in the park includes the composition of pollutants exceeding the standard in the park and the real-time concentration of each pollutant exceeding the standard;

[0008] Match the pollutant characteristic profile of the industrial park with the pre-built factory pollutant emission database to obtain multiple first-order suspicious factories involved in pollution emission;

[0009] Obtaining a set of pollution diffusion environmental impact parameters and a position vector of each first-order suspicious factory relative to the industrial pollution monitoring point, wherein the set of pollution diffusion environmental impact parameters includes wind speed, wind direction, temperature, humidity and air pressure;

[0010] Based on the pollution diffusion environmental impact parameter set and the position vectors of each first-order suspicious factory, a diffusion analysis is performed on each first-order suspicious factory to determine multiple second-order suspicious factories involved in this pollution exceeding standard event;

[0011] Control the drone equipped with mobile monitoring sensors to monitor the pollution data of each second-level suspicious factory and obtain the pollutant characteristic portrait of each second-level suspicious factory;

[0012] The pollutant characteristic profiles of each second-order suspicious factory are compared and analyzed with the pollutant characteristic profiles of the industrial park to obtain the degree of involvement of each second-order suspicious factory in the pollution incident;

[0013] The second-order suspicious factory with the greatest involvement in the pollution incident is regarded as the source of pollution in this pollution incident in the industrial park.

[0014] Furthermore, the method for obtaining the pollution incident participation degree of the second-order suspicious factory includes:

[0015] For each second-order suspicious factory, calculate the similarity of the components of pollutants exceeding the standard in the factory pollutant characteristic profile and the industrial park pollutant characteristic profile;

[0016] Count the concentration ratios of each pollutant exceeding the standard in the pollutant characteristic profile of the park, and use the concentration ratios of each pollutant exceeding the standard as the weight coefficient of each pollutant exceeding the standard;

[0017] According to the weight coefficient of each pollutant exceeding the standard, the real-time concentration of the same type of pollutants in the factory pollutant characteristic portrait and the park pollutant characteristic portrait is weighted and calculated to obtain the pollutant concentration contribution index of the second-order suspicious factory;

[0018] Based on the preset weights, the similarity of the composition of pollutants exceeding the standard and the contribution index of pollutant concentration are weightedly calculated to obtain the degree of participation in the pollution incident.

[0019] Furthermore, the calculation formula for obtaining the pollution event participation degree of the second-order suspicious factory is:

[0020] Dj = α·Sj + β·Pj;

[0021] Where Dj represents the participation of the second-order suspicious factory in the pollution incident, α represents the weight factor of the similarity of the pollutant composition, β represents the weight factor of the pollutant concentration contribution, Sj represents the similarity of the component composition, and Pj represents the pollutant concentration contribution index.

[0022] Furthermore, the method for obtaining the characteristic portrait of pollutants in the park includes:

[0023] Pre-process the pollution monitoring data information obtained from industrial pollution monitoring points, including data cleaning, standardization and time series analysis;

[0024] Set a pollution threshold, analyze the pollutant concentration at each monitoring point in the monitoring data based on the pollution threshold, and identify pollutants and their concentrations that exceed the pollution threshold and have actual concentrations higher than the pollution threshold;

[0025] Extract features of pollutants exceeding the standard, including composition and real-time concentration:

[0026] The extracted characteristics of pollutants exceeding the standard are combined into a comprehensive pollutant characteristic portrait of the park.

[0027] Furthermore, the method for building the factory pollutant emission database includes:

[0028] Collect basic information and emission data of all factories in the park, and clarify the types of pollutants allowed to be emitted by each factory, the maximum emission amount and the emission standards;

[0029] Clean and standardize the collected data;

[0030] Design database architecture, including plant basic information table, emission record table and pollutant characteristic table;

[0031] Based on the geographical location information of the factory, an index and association mechanism is established in the database to support subsequent data query and matching operations.

[0032] Furthermore, the method for obtaining the factory pollutant characteristic portrait of the second-order suspicious factory includes:

[0033] According to the location information of the second-order suspicious factory, formulate a UAV flight plan, including flight path, monitoring altitude and stay time;

[0034] Before carrying out the mission, all onboard monitoring sensors must be calibrated;

[0035] The drone automatically takes off according to the predetermined plan, and after arriving above each suspicious second-level factory, it turns on the monitoring sensor and starts collecting air sample data in real time;

[0036] The monitoring data on the drone is transmitted to the ground control center in real time through wireless communication technology, and the data is analyzed instantly to generate a dynamic factory pollutant characteristic portrait, and obtain the factory pollutant characteristic portrait of each second-order suspicious factory.

[0037] Furthermore, the method for determining the pollution source of the pollution incident includes:

[0038] Sort all the second-order suspicious factories from high to low according to their involvement in the pollution incident;

[0039] The second-tier suspicious factory ranked first, that is, the factory with the highest score for participation in the pollution incident, was preliminarily identified as the primary suspect source of the pollution incident;

[0040] Organize personnel to conduct on-site inspections of the factory, including on-site sampling and analysis of its emissions, comparison with emission permit standards, inspection of the operation of its environmental protection facilities, and review of its daily operation records;

[0041] Combine drone mobile monitoring data, fixed monitoring station data, and on-site sampling analysis results to cross-verify multi-source evidence and identify the source of pollution;

[0042] Prepare an investigation report that clearly points out the polluting behavior, degree of pollution and specific impact of the primary suspect factory on the environment.

[0043] On the other hand, the present application also provides an industrial pollution source tracing system based on machine learning, the system comprising:

[0044] Data collection module, used to obtain pollution monitoring data information monitored by industrial pollution monitoring points;

[0045] A feature extraction module is used to extract the features of pollutants exceeding the standard from the pollution monitoring data information to obtain a characteristic profile of pollutants in the park; the characteristic profile of pollutants in the park includes the composition of pollutants exceeding the standard in the park and the real-time concentration of each pollutant exceeding the standard;

[0046] The emission data matching module is used to match the characteristic profile of the park pollutants with the pre-built factory pollutant emission database to obtain multiple first-order suspicious factories involved in pollution emissions;

[0047] A diffusion analysis module is used to obtain a set of pollution diffusion environmental impact parameters and a position vector of each first-order suspicious factory relative to the industrial pollution monitoring point, wherein the pollution diffusion environmental impact parameter set includes wind speed, wind direction, temperature, humidity and air pressure; based on the pollution diffusion environmental impact parameter set and the position vector of each first-order suspicious factory, a diffusion analysis is performed on each first-order suspicious factory to determine multiple second-order suspicious factories involved in the pollution exceeding standard event;

[0048] The drone monitoring module is used to control drones equipped with mobile monitoring sensors to monitor pollution data of each second-order suspicious factory and obtain the characteristic portrait of factory pollutants of each second-order suspicious factory;

[0049] The comparison and analysis module is used to compare and analyze the pollutant characteristic profiles of each second-order suspicious factory with the pollutant characteristic profiles of the industrial park to obtain the degree of involvement of each second-order suspicious factory in the pollution incident;

[0050] The source determination module regards the second-order suspicious factory with the greatest involvement in the pollution incident as the pollution source of this pollution incident in the industrial park.

[0051] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0052] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0053] Compared with the prior art, the present invention has the following beneficial effects: by extracting pollutant characteristics in the park and establishing characteristic portraits, the method can more precisely identify the types of pollutants and their concentrations, and can more accurately reflect the pollution situation than traditional methods; combined with the matching of machine learning models in the factory emission database, it can efficiently screen out suspicious factories with high matching degrees with pollution characteristics, thereby improving the accuracy of preliminary screening;

[0054] The use of real-time monitoring data for analysis significantly improves the response speed to pollution incidents and enables the activation of emergency response mechanisms more quickly compared to the traditional method of relying on fixed monitoring stations and regular inspections;

[0055] Incorporating environmental parameters such as wind speed and direction into diffusion analysis can simulate the diffusion path and concentration distribution of pollutants more closely to the actual situation, so that the pollution source can be located more accurately in a complex environment, solving the problem of difficulty in accurate positioning based on emission port data alone;

[0056] Using drones for mobile monitoring not only expands the monitoring scope and flexibility, but also enables a more scientific assessment of the pollution contribution of each factory by obtaining real-time pollutant data from the second-order suspicious factories and combining it with machine learning for comparative analysis.

[0057] This method can objectively determine the responsible party for pollution based on data analysis, reducing the subjectivity and errors of human judgment, helping to make environmental law enforcement more fair and efficient, while also prompting companies to pay more attention to their own environmental compliance;

[0058] By continuously accumulating monitoring data and optimizing models, we can promote a deeper understanding of pollution patterns in industrial parks and provide a scientific basis for formulating more effective preventive measures and environmental management policies;

[0059] In summary, this method can accurately and efficiently determine the pollution sources in industrial parks by collecting pollution data in real time, constructing a characteristic portrait of pollutants in the industrial park, and combining the factory emission database and pollution diffusion analysis, thereby meeting environmental protection laws and regulations and the public's high requirements for environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a flow chart of the present invention;

[0061] Figure 2 It is a flow chart of the method for obtaining the pollution incident participation degree of the second-order suspicious factory;

[0062] Figure 3 This is the structural diagram of the industrial pollution source tracing system based on machine learning. DETAILED DESCRIPTION

[0063] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0064] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0065] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0066] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0067] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0068] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0069] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0070] The present application is described below in conjunction with the drawings in the present application.

[0071] Embodiment 1: Figure 1 to Figure 2 As shown, the industrial pollution source tracing method based on machine learning of the present invention specifically includes the following steps:

[0072] S1. Obtain pollution monitoring data information monitored by industrial pollution monitoring points;

[0073] Step S1 uses advanced sensing technology and network communication technology to collect real-time environmental quality data at key locations within the industrial park. The following is a detailed introduction to Step S1:

[0074] Scientifically and rationally arrange monitoring stations in the industrial park; the monitoring stations should cover key areas of the entire park, including the vicinity of industrial emission outlets, around environmentally sensitive areas, and along the pollutant diffusion path; factors such as terrain, wind direction, and population density should be considered during the arrangement to ensure that the monitoring network can fully reflect the pollution status of the park;

[0075] Each monitoring site is equipped with a variety of highly sensitive sensors to detect common air and water pollutants, including sulfur dioxide, nitrogen oxides, particulate matter and volatile organic compounds;

[0076] The monitored data is transmitted to the central data processing system in real time via wired and wireless networks; the data transmission protocol must ensure the security and integrity of the data to avoid distortion or loss during the transmission process;

[0077] The collected data is preprocessed, including data cleaning, format unification, and preliminary analysis, to facilitate subsequent feature extraction and analysis.

[0078] In this step, by scientifically arranging monitoring stations in key areas of industrial parks, it is possible to achieve all-weather, all-round monitoring of various pollutants in the air and water, timely capture pollution anomalies, provide early warning signals for environmental protection, and help respond quickly to reduce the impact of environmental pollution incidents; the application of high-sensitivity sensors ensures the accuracy of monitoring data. Combined with coverage monitoring of industrial emission outlets, environmentally sensitive areas and pollutant diffusion paths, it can more accurately locate potential pollution sources and lay the foundation for subsequent pollution tracing work; the use of wired and wireless networks to transmit monitoring data in real time and adopt secure data transmission protocols to ensure the integrity and security of the data transmission process, so that the information received by the central data processing system is accurate, enhancing the effectiveness of data analysis and the reliability of decision-making; the data preprocessing process improves the quality and availability of data, simplifies the complexity of subsequent feature extraction and in-depth analysis, accelerates the transformation process from data to insight, and improves overall work efficiency.

[0079] S2. Extract the characteristics of pollutants exceeding the standard from the pollution monitoring data information to obtain a characteristic profile of pollutants in the park; the characteristic profile of pollutants in the park includes the composition of pollutants exceeding the standard in the park and the real-time concentration of each pollutant exceeding the standard;

[0080] Step S2 is to conduct an in-depth analysis of the large amount of pollution data collected from the monitoring points to identify the specific types of pollutants and their concentration distribution, and form an accurate pollutant characteristic profile of the park; the following is a detailed introduction to this step:

[0081] Preprocess the collected monitoring data, including data cleaning, standardization and time series analysis;

[0082] Set a pollution threshold, analyze the pollutant concentration at each monitoring point in the monitoring data based on the pollution threshold, and identify pollutants and their concentrations that exceed the pollution threshold and have actual concentrations higher than the pollution threshold;

[0083] Extract features of pollutants exceeding the standard, including composition and real-time concentration:

[0084] The extracted characteristics of pollutants exceeding the standard are combined into a comprehensive park pollutant characteristic portrait; the park pollutant characteristic portrait reflects the real-time situation of various pollutants exceeding the standard at different monitoring points in the industrial park, providing a comprehensive perspective to understand the distribution and source of pollutants.

[0085] In this step, through the detailed analysis of the monitoring data, it is possible to accurately identify which pollutants have concentrations exceeding the specified threshold, and then lock in the specific types of pollutants that exceed the standard, and accurately trace the source of pollution; the preprocessing step removes invalid or erroneous data, ensuring the accuracy and efficiency of subsequent analysis, so that when faced with sudden pollution incidents, the problem can be quickly located and response measures can be initiated in a timely manner; the constructed park pollutant characteristic portrait not only reveals the real-time concentration of each pollutant that exceeds the standard, but also presents the characteristics of their spatial distribution in the park, which helps the regulatory authorities to accurately implement policies and take effective control measures for key areas and pollutants; the comprehensive information provided by this step provides a scientific basis for environmental protection decision-making; decision makers can formulate or adjust environmental protection policies and optimize resource allocation based on the detailed data of the pollutant characteristic portrait; the pollutant characteristic portrait data accumulated over a long period of time helps to analyze pollution trends, evaluate the effectiveness of existing prevention and control measures, provide data support for the park's environmental governance and sustainable development strategies, and realize forward-looking planning for pollution prevention and control; step S2 not only promotes the rapid response and effective handling of pollution incidents, but also lays a solid foundation for scientific decision-making and long-term planning of park pollution management.

[0086] S3. Match the pollutant characteristic profile of the industrial park with the pre-built factory pollutant emission database to obtain multiple first-order suspicious factories involved in pollution emission;

[0087] Step S3 is to preliminarily screen out the first-order suspicious factories that may contribute to the current pollution incident by matching the pollutant characteristic profile of the park with the existing factory pollutant emission database;

[0088] The method for building the factory pollutant emission database includes:

[0089] Collect basic information of all factories in the park, including factory name, address, business type and emission type; collect relevant emission data, including emission concentration, emission amount, emission period and emission port location of various pollutants, and clarify the types of pollutants allowed to be emitted by each factory, the maximum emission amount and emission standards;

[0090] Clean and standardize the collected data to ensure data accuracy and consistency; check whether the data is complete, handle possible outliers or erroneous data, and unify the data format and unit to facilitate subsequent data analysis and matching;

[0091] Design a reasonable database architecture, including multiple related tables such as factory basic information table, emission record table, pollutant characteristic table, etc., to facilitate data management and query;

[0092] Establish appropriate indexing and association mechanisms in the database to support subsequent data query and matching operations; the indexing and association mechanisms are built based on information such as the factory's unique identifier or geographic location to quickly locate and identify potential pollution sources;

[0093] The factory pollutant emission database includes:

[0094] Basic factory information, including factory name, geographical location coordinates, industry category, main products or processes, environmental rating, pollutant discharge permit number and validity period, etc. This basic information helps to quickly locate and analyze potential pollution sources;

[0095] Emission outlet information, recording the location of each factory’s emission outlet, emission outlet number, type of emitted substances and their corresponding emission standard limits;

[0096] Pollutant emission records, which shall record historical and real-time emission data in detail, including emission concentration, emission rate, total emission amount and emission period of various pollutants; these data shall be updated regularly and shall include abnormal emission records and treatment situations;

[0097] Pollutant composition analysis: For emissions, the database should include detailed chemical composition analysis reports, including major pollutants and potential trace pollutants, to help build a more accurate pollutant profile;

[0098] Environmental impact assessment report: a summary of the environmental impact assessment report submitted by the factory, covering the assessment of the potential impact of its production activities on the surrounding environment, as well as the preventive and mitigation measures taken;

[0099] Monitoring and testing reports, including factory self-monitoring reports, third-party testing reports, and spot check results from environmental protection departments. These reports verify whether the factory’s actual emissions comply with the permit regulations and provide a basis for assessing the factory’s compliance;

[0100] Emergency response records record the response measures, cause analysis, post-event handling and rectification of previous emergency emission incidents, which helps to evaluate the factory's emergency management level and prevention strategies for similar incidents in the future.

[0101] In this step, by quickly comparing the pollutant characteristics monitored in the park with the factory emission information in the database, the factories that match the characteristics of the pollution incident, namely the first-order suspicious factories, can be preliminarily screened out. This process significantly improves the efficiency and pertinence of pollution source identification, making the investigation more targeted; the detailed factory emission data, component analysis and environmental assessment information in the database provide a solid foundation for pollution source analysis, so that pollution source tracing is based on scientific and comprehensive data, improving the accuracy and reliability of judgment, and avoiding the limitations of relying solely on on-site observations or empirical judgments; this method is not only used to trace pollution incidents, but also through comprehensive analysis of historical emission records, monitoring and detection reports and emergency response records, it enhances the supervision of daily environmental protection compliance of factories, and encourages enterprises to strengthen their own I manage, comply with emission standards, and reduce illegal emissions; the integrated factory information and emission data provide the environmental management department with rich decision-making support information, helping decision makers to quickly grasp the pollution situation in the park, adjust the supervision strategy in time, formulate or optimize pollution prevention and control measures, and effectively respond to sudden environmental incidents; through this method, the responsible party for pollution can be more accurately located, providing a direct basis for subsequent law enforcement actions, environmental restoration and compensation, thereby accelerating the pollution control process and protecting the ecological environment, while also maintaining the seriousness and fairness of the law; the implementation of step S3 not only improves the timeliness and accuracy of the response to pollution incidents, but also promotes the systematization and scientificization of the environmental management of the entire industrial park through strengthening supervision and data analysis, laying the foundation for achieving green and sustainable development.

[0102] S4. Obtain a set of pollution diffusion environmental impact parameters and a position vector of each first-order suspicious factory relative to the industrial pollution monitoring point, wherein the set of pollution diffusion environmental impact parameters includes wind speed, wind direction, temperature, humidity and air pressure;

[0103] The environmental impact parameters and position vectors obtained in the S4 stage can be effectively combined with machine learning algorithms to simulate and analyze pollution diffusion, so as to accurately determine the pollution impact range of each first-order suspicious factory and provide basic data support for subsequent monitoring and analysis of second-order suspicious factories. The following is a detailed introduction to this step:

[0104] Deploy wind speed and direction sensors in industrial parks to obtain data in real time or periodically. Sensors should be located at key locations in the industrial park to cover various wind conditions that affect pollutant dispersion.

[0105] Install temperature, humidity and air pressure sensors, together with wind speed and direction sensors, to comprehensively record environmental parameters; regularly collect and integrate data on these environmental parameters to reflect the spread and diffusion of pollutants under different meteorological conditions;

[0106] The accurate location information of each first-order suspicious factory relative to the industrial pollution monitoring point is obtained through GPS positioning or map data to ensure the accuracy and real-time nature of the position vector.

[0107] In this step, by deploying a multi-dimensional sensor network in the industrial park and real-time monitoring of key parameters such as wind speed, wind direction, temperature, humidity and air pressure, it is possible to accurately capture the tiny environmental changes that affect the diffusion of pollutants, significantly improving the accuracy of the simulated pollutant diffusion model; real-time monitoring of environmental parameters and location information obtained using technologies such as GPS ensures a rapid response to pollution incidents; once the monitoring point finds that the pollution exceeds the standard, it can immediately analyze it based on the latest environmental data and quickly identify the possible source of pollution, providing valuable time for timely control measures; the diffusion simulation that comprehensively considers meteorological conditions and geographic location information provides environmental managers with a scientific and quantitative decision-making basis; step S4 greatly enhances the rapid response capability and traceability accuracy to industrial pollution incidents through high-tech monitoring methods and data integration analysis.

[0108] S5. Based on the pollution diffusion environmental impact parameter set and the position vectors of each first-order suspicious factory, a diffusion analysis is performed on each first-order suspicious factory to determine multiple second-order suspicious factories involved in the pollution exceeding standard event;

[0109] Step S5 is to conduct diffusion analysis on the identified first-order suspicious factories to further accurately locate the second-order suspicious factories that may cause pollution exceeding the standard. The following is a detailed introduction to this step:

[0110] According to the geographical characteristics and environmental conditions of the industrial park, a suitable pollutant diffusion model is selected; the pollutant diffusion model includes a Gaussian diffusion model, a computational fluid dynamics model and a diffusion model based on statistics;

[0111] Set the environmental parameters required by the model, including wind speed, wind direction, temperature, humidity and air pressure;

[0112] The real-time pollution data of the monitoring points, the emission data of the first-order suspicious factories and the environmental parameters are input into the model for preliminary simulation;

[0113] Use historical data and actual monitoring results to calibrate the model to ensure that the simulation results are as consistent as possible with the actual situation;

[0114] Based on the known concentration of pollution monitoring points, reverse tracing technology is used to simulate the source direction and path of pollutants from the monitoring points in reverse. This helps to narrow the scope of suspected pollution sources and determine which first-order suspicious factories are most likely to cause pollution exceeding the standard at the monitoring points;

[0115] Simulate the emission scenario of each first-order suspicious factory to evaluate its contribution to the pollution concentration at the monitoring point; including changing the emission rate and emission time of a single or multiple factories, observing the changes in the simulation results to determine which factors have the greatest impact on the pollution incident;

[0116] Based on the results of diffusion simulation, several first-order suspicious factories whose emissions contribute most to the pollution at the monitoring points under various simulation scenarios are identified and upgraded to second-order suspicious factories.

[0117] In this step, through the diffusion analysis of the first-order suspicious factories, it is possible to go beyond the single emission data comparison and comprehensively consider the actual impact of meteorological conditions and geographical factors on the diffusion of pollutants, so as to locate the pollution source more accurately; it is possible to effectively distinguish between the direct responsible parties and the indirect influencers in a complex environment, and improve the accuracy of tracing the source of pollution incidents; simulation analysis provides quantitative data support, enabling environmental managers to make decisions based on scientific evidence and determine which factories are most likely to be involved in pollution incidents, providing a solid foundation for taking further regulatory measures or legal actions; by accurately locating the second-order suspicious factories, limited monitoring and law enforcement resources can be deployed in a targeted manner, avoiding blind inspections, and improving work efficiency and the effectiveness of intervention; reverse tracking and emission scenario simulation help identify which combinations of emission characteristics and environmental conditions are most likely to cause pollution to exceed the standard, providing factories with specific guidance for improving emission management and preventing future pollution incidents, and promoting the transition from passive response to active prevention; step S5 not only enhances the traceability of specific pollution incidents, but also provides strong support for the long-term environmental protection strategy and efficient use of resources in industrial parks.

[0118] S6. Control the drone equipped with mobile monitoring sensors to monitor pollution data of each second-order suspicious factory, and obtain the characteristic portrait of factory pollutants of each second-order suspicious factory;

[0119] Step S6 involves using drones equipped with mobile monitoring sensors to monitor pollution data of identified second-level suspicious factories. The drones should be professional-grade drones with long endurance and stable flight performance to ensure safe execution of tasks in complex and changing industrial park environments.

[0120] Mobile monitoring sensors are mounted under the drone or integrated into the drone structure. The sensors need to have high sensitivity and rapid response capabilities to monitor specific pollutant types and concentrations in the atmosphere in real time. The sensors also need to adapt to various meteorological conditions to ensure the accuracy of data collection.

[0121] The integrated GPS and inertial navigation system ensures that the drone can accurately reach the predetermined monitoring location above each suspicious second-order factory, and at the same time cooperate with the preset flight route to achieve automated inspection;

[0122] The method for obtaining the factory pollutant characteristic profile of the second-order suspicious factory includes:

[0123] Based on the location information of the second-order suspicious factories, professional software is used to develop a detailed drone flight plan, including flight path, monitoring altitude, and dwell time, to cover the key emission areas of each factory;

[0124] Before carrying out the task, all monitoring sensors on board are calibrated to ensure the reliability and consistency of the monitoring data; the working mode and parameter settings of the sensors are adjusted according to the known pollutant types in the park to achieve the best monitoring effect;

[0125] The drone automatically takes off according to the predetermined plan, and after arriving above each second-level suspicious factory, it turns on the monitoring sensor to start collecting air sample data in real time; this process includes vertical sampling at different altitudes to better understand the vertical diffusion of pollutants;

[0126] The monitoring data on the drone is transmitted to the ground control center in real time through wireless communication technology, and the data is analyzed immediately to generate a dynamic factory pollutant characteristic portrait, and obtain the factory pollutant characteristic portrait of each second-order suspicious factory;

[0127] In this step, by utilizing the mobility and flexibility of drones, it is possible to cover the key emission areas above multiple second-order suspicious factories in a short period of time. Compared with traditional ground monitoring methods, it significantly improves monitoring efficiency and spatial coverage, and helps to quickly identify potential sources of pollution; the high-sensitivity sensors carried by drones can monitor the concentrations of a variety of specific pollutants in real time, and combined with calibration procedures, ensure the accuracy and consistency of monitoring data, and ensure the validity of data even under complex meteorological conditions, thereby enhancing the scientific nature and authority of pollution monitoring; vertical sampling strategies at different altitudes are implemented, so that monitoring is no longer limited to the ground level, but covers the vertical diffusion characteristics of pollutants. This three-dimensional monitoring method provides more comprehensive information for analyzing pollutant diffusion paths and concentration distributions. , which helps to more accurately evaluate the pollution contribution rate of each factory; the data monitored by the drone is transmitted back to the ground control center in real time through wireless communication, which enables instant analysis of the pollution situation, provides a basis for the environmental protection department to quickly respond to pollution incidents, accelerates the deployment of pollution control and emergency treatment measures, and effectively reduces the duration and scope of environmental pollution; the integrated GPS and inertial navigation system ensures that the drone can accurately perform preset flight missions, reduces the errors and risks of manual operations, ensures the safe conduct of monitoring activities, and also reduces the labor intensity of personnel and improves the overall intelligence level of monitoring tasks; the implementation of the S6 step not only greatly improves the efficiency and accuracy of industrial pollution monitoring, but also enhances the timeliness and effectiveness of environmental supervision through high-tech means.

[0128] S7. Compare and analyze the pollutant characteristic profiles of each second-order suspicious factory with the pollutant characteristic profiles of the industrial park to obtain the degree of involvement of each second-order suspicious factory in the pollution incident;

[0129] Step S7 is to conduct a more detailed comparative analysis of the second-level suspicious factories based on the data and analysis collected in the early stage, so as to obtain an assessment of the involvement of each second-level suspicious factory in the pollution incident;

[0130] The method for obtaining the pollution incident participation degree of the second-order suspicious factory includes:

[0131] The pollutant characteristic profile of the park and the pollutant characteristic profile of each second-order suspicious factory are converted into characteristic vectors; each pollutant component is regarded as a dimension, and its concentration value or existence is regarded as the value of the dimension;

[0132] The cosine similarity algorithm is used to measure the similarity between the pollutant composition of the second-order suspicious factory and the characteristic portrait of the pollutants in the industrial park; the cosine similarity can effectively reflect the similarity in the direction of two vectors, and can accurately evaluate the matching degree of the component structure even when the absolute concentration difference is large;

[0133] Based on the pollutant profile of the park, the proportion of each pollutant concentration exceeding the standard to the total pollutant concentration exceeding the standard is calculated and used as the weight coefficient of the pollutant; high-concentration pollutants have a greater impact on the overall pollution level and should be given a higher weight;

[0134] For each second-order suspicious factory, the pollutant concentration in its pollutant characteristic profile that is the same as the park's pollutant characteristic profile is multiplied by its corresponding weight coefficient, and then the weighted concentrations of all pollutants are summed to obtain the pollutant concentration contribution index of the factory, ensuring that pollutants with greater environmental impact are given more consideration;

[0135] Two preset weight factors are set, one for considering the similarity of pollutant composition and the other for considering the contribution of pollutant concentration; these two weight factors need to be adjusted according to actual conditions to balance the importance of composition matching and concentration impact;

[0136] According to the preset weight factor, the pollutant composition similarity and pollutant concentration contribution index of each second-order suspicious factory are weighted and summed; if the component similarity is considered more important, a higher weight is given; vice versa; the final score is the factory's participation in the pollution incident;

[0137] The calculation formula for obtaining the pollution event participation degree of the second-order suspicious factory is:

[0138] Dj=α·Sj+β·Pj

[0139] Where Dj represents the participation of the second-order suspicious factory in the pollution incident, α represents the weight factor of the similarity of the pollutant composition, β represents the weight factor of the pollutant concentration contribution, Sj represents the similarity of the component composition, and Pj represents the pollutant concentration contribution index.

[0140] In this step, by conducting in-depth comparative analysis of the second-order suspicious factories, it is possible to more accurately identify which factories played a key role in a specific pollution incident; it helps to go beyond the initial screening and get to the core of the pollution problem, providing accurate targets for subsequent supervision and governance; by converting complex environmental monitoring data into feature vectors and applying the cosine similarity algorithm and weighted concentration contribution calculation, a method for quantitatively evaluating the pollution contribution of each factory is provided; this quantitative method makes the attribution of pollution incidents more objective and scientific, and reduces the error of subjective judgment; this step combines the two aspects of information, component similarity and concentration contribution, greatly improving the efficiency and accuracy of pollution tracing; it can lock in the most likely source of pollution in a short time and accelerate the implementation of response measures; by setting adjustable weight factors, this method can flexibly adjust the evaluation focus according to different industrial park characteristics, seasonal changes, pollutant types and other factors, ensuring the flexibility and adaptability of the method; accurately identifying the main participants in pollution incidents can enable environmental protection departments and park managers to more reasonably allocate limited regulatory resources, concentrate on solving the most critical problems, and improve the overall environmental protection and governance effects.

[0141] S8. The second-order suspicious factory with the greatest involvement in the pollution incident is regarded as the pollution source of this pollution incident in the industrial park;

[0142] Each second-order suspicious factory has obtained its own pollution event participation score through detailed comparative analysis; these scores comprehensively reflect the similarity of the pollutant emission characteristics of each factory and the pollutant characteristics of the park, the relative importance of the emission concentration, and the degree of influence predicted by the diffusion model;

[0143] Methods for determining the pollution source of a pollution incident include:

[0144] Sort all the second-order suspicious factories from high to low according to their involvement in the pollution incident;

[0145] The second-tier suspicious factory ranked first, that is, the factory with the highest score for participation in the pollution incident, was preliminarily identified as the primary suspect source of the pollution incident;

[0146] In order to make the final confirmation, a professional team needs to be organized to conduct an on-site inspection of the factory; this includes on-site sampling and analysis of its emissions, comparison with emission permit standards, inspection of the operation of its environmental protection facilities, and review of its daily operation records;

[0147] Combine drone mobile monitoring data, fixed monitoring station data and on-site sampling analysis results to cross-validate multi-source evidence; eliminate the possibility of misjudgment and ensure that the source of pollution is determined scientifically and rigorously;

[0148] After completing all verification procedures, a detailed investigation report will be compiled to clearly point out the pollution behavior, degree of pollution and specific impact of the primary suspect factory on the environment; this report will serve as the basis for official notification and also provide a basis for subsequent legal accountability and rectification measures.

[0149] In this step, by identifying the second-order suspicious factory with the greatest involvement in the pollution incident as the primary suspect source, the factory most likely to cause pollution can be located efficiently and accurately, significantly improving the efficiency and accuracy of pollution tracing compared to traditional methods; taking into account factors such as the similarity of pollutant emission characteristics, concentration contribution and diffusion model prediction, each second-order suspicious factory is assigned a participation score and ranked, ensuring the objectivity and comprehensiveness of the assessment; the factory ranked first as the primary suspect source provides a clear target for subsequent on-site verification, enhances the pertinence of the investigation, and reduces unnecessary waste of resources; by organizing professional teams to conduct on-site verification, sampling analysis, facility inspection and operation Multi-dimensional verification such as record review not only enhanced the scientific nature of the judgment, but also effectively avoided misjudgment and ensured the reliability of the investigation results; the multi-source evidence cross-verification combined with drone monitoring, fixed-site data and on-site sampling results promoted information sharing and collaboration among environmental protection departments, monitoring agencies and the companies involved, and increased the transparency of the handling process; the final investigation report recorded in detail the pollution behavior, degree and environmental impact of the primary suspect factory, providing a solid factual basis and legal basis for official government notification, initiation of legal accountability procedures and formulation of specific rectification measures, which is conducive to accelerating the effective resolution of pollution problems and providing guidance for the prevention and management of similar incidents in the future.

[0150] Embodiment 2: Figure 3 As shown, the industrial pollution source tracing system based on machine learning of the present invention specifically includes the following modules:

[0151] Data collection module, used to obtain pollution monitoring data information monitored by industrial pollution monitoring points;

[0152] A feature extraction module is used to extract the features of pollutants exceeding the standard from the pollution monitoring data information to obtain a characteristic profile of pollutants in the park; the characteristic profile of pollutants in the park includes the composition of pollutants exceeding the standard in the park and the real-time concentration of each pollutant exceeding the standard;

[0153] The emission data matching module is used to match the characteristic profile of the park pollutants with the pre-built factory pollutant emission database to obtain multiple first-order suspicious factories involved in pollution emissions;

[0154] A diffusion analysis module is used to obtain a set of pollution diffusion environmental impact parameters and a position vector of each first-order suspicious factory relative to the industrial pollution monitoring point, wherein the pollution diffusion environmental impact parameter set includes wind speed, wind direction, temperature, humidity and air pressure; based on the pollution diffusion environmental impact parameter set and the position vector of each first-order suspicious factory, a diffusion analysis is performed on each first-order suspicious factory to determine multiple second-order suspicious factories involved in the pollution exceeding standard event;

[0155] The drone monitoring module is used to control drones equipped with mobile monitoring sensors to monitor pollution data of each second-order suspicious factory and obtain the characteristic portrait of factory pollutants of each second-order suspicious factory;

[0156] The comparison and analysis module is used to compare and analyze the pollutant characteristic profiles of each second-order suspicious factory with the pollutant characteristic profiles of the industrial park to obtain the degree of involvement of each second-order suspicious factory in the pollution incident;

[0157] The source determination module regards the second-order suspicious factory with the greatest involvement in the pollution incident as the pollution source of this pollution incident in the industrial park.

[0158] The system uses real-time monitoring data and feature extraction modules to quickly form a characteristic profile of pollutants in the park; it can quickly identify pollutants that exceed the standard and their real-time concentrations, helping to locate potential pollution sources in a timely manner;

[0159] By establishing a factory pollutant emission database and using machine learning algorithms, it is possible to intelligently match the pollutant characteristic profiles of the park with factory emission data and identify multiple first-order suspicious factories, thereby improving the accuracy and efficiency of tracing.

[0160] The system not only considers static monitoring data, but also handles complex pollution, cross-contamination or instantaneous emission events through diffusion analysis modules and real-time monitoring drone modules, greatly improving the system's adaptability in dealing with changing environmental conditions;

[0161] The comparative analysis module uses detailed factory pollutant feature portraits to accurately assess the involvement of each second-order suspicious factory in the pollution incident. It can not only qualitatively determine the pollution source, but also quantitatively analyze the contribution of different factories to the pollution incident, which helps to accurately determine the main pollution source.

[0162] The system's source determination module can quickly identify the largest participants in pollution incidents, provide scientific basis and decision-making support for environmental management departments, and help quickly formulate and implement effective pollution prevention and control measures to protect the environment and public health;

[0163] In summary, the industrial pollution source tracing system based on machine learning effectively addresses pollution tracing problems in the complex environment of industrial parks by integrating real-time monitoring, big data analysis and machine learning technologies, thereby improving the efficiency and accuracy of environmental protection work.

[0164] The various variations and specific embodiments of the industrial pollution source tracing method based on machine learning in the aforementioned embodiment 1 are also applicable to the industrial pollution source tracing system based on machine learning in this embodiment. Through the aforementioned detailed description of the industrial pollution source tracing method based on machine learning, those skilled in the art can clearly understand the implementation method of the industrial pollution source tracing system based on machine learning in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0165] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0166] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for tracing the source of industrial pollution based on machine learning, characterized in that: The method is used in an industrial park, when the industrial pollution monitoring point detects that the pollution index exceeds the standard, and the emissions of various factories in the park meet the emission standards for discharge, to trace the pollution source and determine the pollution source with the greatest involvement in the pollution exceeding the standard event. The method includes: Obtain pollution monitoring data information monitored by industrial pollution monitoring points; Extract the characteristics of pollutants exceeding the standard from the pollution monitoring data information to obtain a characteristic profile of pollutants in the park; the characteristic profile of pollutants in the park includes the composition of pollutants exceeding the standard in the park and the real-time concentration of each pollutant exceeding the standard; Match the pollutant characteristic profile of the industrial park with the pre-built factory pollutant emission database to obtain multiple first-order suspicious factories involved in pollution emission; Obtaining a set of pollution diffusion environmental impact parameters and a position vector of each first-order suspicious factory relative to the industrial pollution monitoring point, wherein the set of pollution diffusion environmental impact parameters includes wind speed, wind direction, temperature, humidity and air pressure; Based on the pollution diffusion environmental impact parameter set and the position vectors of each first-order suspicious factory, a diffusion analysis is performed on each first-order suspicious factory to determine multiple second-order suspicious factories involved in this pollution exceeding standard event; Control the drone equipped with mobile monitoring sensors to monitor the pollution data of each second-level suspicious factory and obtain the pollutant characteristic portrait of each second-level suspicious factory; The pollutant characteristic profiles of each second-order suspicious factory are compared and analyzed with the pollutant characteristic profiles of the industrial park to obtain the degree of involvement of each second-order suspicious factory in the pollution incident; The second-order suspicious factory with the greatest involvement in the pollution incident is regarded as the source of pollution in this pollution incident in the industrial park.

2. The method for tracing the source of industrial pollution based on machine learning according to claim 1, characterized in that: The method for obtaining the pollution incident participation degree of the second-order suspicious factory includes: For each second-order suspicious factory, calculate the similarity of the components of pollutants exceeding the standard in the factory pollutant characteristic profile and the industrial park pollutant characteristic profile; Count the concentration ratio of each pollutant exceeding the standard in the pollutant characteristic profile of the park, and use the concentration ratio of each pollutant exceeding the standard as the weight coefficient of each pollutant exceeding the standard; According to the weight coefficient of each pollutant exceeding the standard, the real-time concentration of the same type of pollutants in the factory pollutant characteristic portrait and the park pollutant characteristic portrait is weighted and calculated to obtain the pollutant concentration contribution index of the second-order suspicious factory; Based on the preset weights, the similarity of the composition of pollutants exceeding the standard and the contribution index of pollutant concentration are weightedly calculated to obtain the degree of participation in the pollution incident.

3. The method for tracing the source of industrial pollution based on machine learning as claimed in claim 2, characterized in that: The calculation formula for obtaining the pollution event participation degree of the second-order suspicious factory is: Dj = α·Sj + β·Pj; Where Dj represents the participation of the second-order suspicious factory in the pollution incident, α represents the weight factor of the similarity of the pollutant composition, β represents the weight factor of the pollutant concentration contribution, Sj represents the similarity of the component composition, and Pj represents the pollutant concentration contribution index.

4. The method for tracing the source of industrial pollution based on machine learning according to claim 1, characterized in that: The method for obtaining the characteristic portrait of pollutants in the park includes: Pre-process the pollution monitoring data information obtained from industrial pollution monitoring points, including data cleaning, standardization and time series analysis; Set a pollution threshold, analyze the pollutant concentration at each monitoring point in the monitoring data based on the pollution threshold, and identify pollutants and their concentrations that exceed the pollution threshold and have actual concentrations higher than the pollution threshold; Feature extraction of pollutants exceeding the standard, including component composition and real-time concentration: The extracted characteristics of pollutants exceeding the standard are combined into a comprehensive pollutant characteristic portrait of the park.

5. The method for tracing the source of industrial pollution based on machine learning according to claim 1, characterized in that: The method for building the factory pollutant emission database includes: Collect basic information and emission data of all factories in the park, and clarify the types of pollutants allowed to be emitted by each factory, the maximum emission amount and the emission standards; Clean and standardize the collected data; Design database architecture, including plant basic information table, emission record table and pollutant characteristic table; Based on the geographical location information of the factory, an index and association mechanism is established in the database to support subsequent data query and matching operations.

6. The method for tracing the source of industrial pollution based on machine learning according to claim 1, characterized in that: The method for obtaining the factory pollutant characteristic profile of the second-order suspicious factory includes: According to the location information of the second-order suspicious factory, formulate a UAV flight plan, including flight path, monitoring altitude and stay time; Before carrying out the mission, all onboard monitoring sensors must be calibrated; The drone automatically takes off according to the predetermined plan, and after arriving above each suspicious second-level factory, it turns on the monitoring sensor and starts collecting air sample data in real time; The monitoring data on the drone is transmitted to the ground control center in real time through wireless communication technology, and the data is analyzed instantly to generate a dynamic factory pollutant characteristic portrait, and obtain the factory pollutant characteristic portrait of each second-order suspicious factory.

7. The method for tracing the source of industrial pollution based on machine learning according to claim 1, characterized in that: Methods for determining the pollution source of a pollution incident include: Sort all the second-order suspicious factories from high to low according to their involvement in the pollution incident; The second-tier suspicious factory ranked first, that is, the factory with the highest score for participation in the pollution incident, was preliminarily identified as the primary suspect source of the pollution incident; Organize personnel to conduct on-site inspections of the factory, including on-site sampling and analysis of its emissions, comparison with emission permit standards, inspection of the operation of its environmental protection facilities, and review of its daily operation records; Combine drone mobile monitoring data, fixed monitoring station data, and on-site sampling analysis results to cross-verify multi-source evidence and identify the source of pollution; Prepare an investigation report that clearly points out the polluting behavior, degree of pollution and specific impact of the primary suspect factory on the environment.

8. An industrial pollution tracing system based on machine learning, characterized in that: The system comprises: Data collection module, used to obtain pollution monitoring data information monitored by industrial pollution monitoring points; A feature extraction module is used to extract the features of pollutants exceeding the standard from the pollution monitoring data information to obtain a characteristic profile of pollutants in the park; the characteristic profile of pollutants in the park includes the composition of pollutants exceeding the standard in the park and the real-time concentration of each pollutant exceeding the standard; The emission data matching module is used to match the characteristic profile of the park pollutants with the pre-built factory pollutant emission database to obtain multiple first-order suspicious factories involved in pollution emissions; A diffusion analysis module is used to obtain a set of pollution diffusion environmental impact parameters and a position vector of each first-order suspicious factory relative to the industrial pollution monitoring point, wherein the pollution diffusion environmental impact parameter set includes wind speed, wind direction, temperature, humidity and air pressure; based on the pollution diffusion environmental impact parameter set and the position vector of each first-order suspicious factory, a diffusion analysis is performed on each first-order suspicious factory to determine multiple second-order suspicious factories involved in the pollution exceeding standard event; The drone monitoring module is used to control drones equipped with mobile monitoring sensors to monitor pollution data of each second-order suspicious factory and obtain the characteristic portrait of factory pollutants of each second-order suspicious factory; The comparison and analysis module is used to compare and analyze the pollutant characteristic profiles of each second-order suspicious factory with the pollutant characteristic profiles of the industrial park to obtain the degree of involvement of each second-order suspicious factory in the pollution incident; The source determination module regards the second-order suspicious factory with the greatest involvement in the pollution incident as the pollution source of this pollution incident in the industrial park.

9. An industrial pollution source tracing electronic device based on machine learning, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Images