Monitoring and early warning method for rapid and accurate traceability

Abstract

The invention provides a monitoring and early warning method for rapid and accurate traceability, and relates to the technical field of deep traceability of environmental pollution problems. The method comprises the following steps: acquiring enterprise condition monitoring data through edge layer monitoring equipment, and acquiring regional environment condition monitoring data and enterprise attribute information through cloud equipment; obtaining alarm information; screening associated enterprises, and determining traceability range influence values and wind field influence values of the associated enterprises; obtaining a risk database score of the associated enterprise; determining the influence value of the in-production enterprise of the associated enterprise; determining the multi-link verification credibility in the enterprise; obtaining a comprehensive influence value of the in-production enterprise; and determining the risk level of the associated enterprise. According to the invention, a multi-source data fusion and cloud edge cooperative driving cross-scale multi-stage traceability system can be constructed, accurate positioning and rapid response of pollution sources from areas to enterprises and workshops are realized, environmental deterioration reasons and responsibility sources are determined in time, and scientific support is provided for emergency disposal of atmospheric events and improvement of air quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of deep source tracing of environmental pollution problems, and particularly relates to a monitoring and early warning method for rapid and accurate source tracing. BACKGROUND

[0002] Currently mainstream atmospheric pollution source tracking technologies mainly include: diffusion model method (for example, CALPUFF, AERMOD, etc.), which can simulate pollutant transport and diffusion based on meteorological data and pollution source emission inventory through Gaussian diffusion or Lagrangian particle model, and deduce the potential source area inversely. It highly depends on the accuracy of input parameters (for example, source strength, meteorological field, etc.), and has large error in complex terrain or real-time changing scene, and is time-consuming in calculation, which is difficult to meet the real-time source tracking demand of minutes level; receptor model method (for example, positive matrix factorization PMF, chemical mass balance CMB, etc.), which matches the chemical component spectrum of particulate matter collected at environmental receptor points with the known pollution source component spectrum (source spectrum library) to calculate the contribution rate of each source. This method relies on a large number of offline sampling and laboratory analysis, and has long cycle and high cost, and the localization degree of source spectrum library is insufficient, which will seriously affect the accuracy, and cannot realize rapid response and workshop level positioning; fingerprint library source tracking technology, which establishes a unique "fingerprint" characteristic database of pollution source emissions (for example, VOCs component ratio, isotope characteristics, etc.), and identifies the pollution source by matching the spectrum / mass spectrum characteristics of the environmental sample collected when the pollution occurs. Although this method has been applied in the fields of VOCs and soil pollution source tracking, it has obvious limitations: first, it highly depends on the pre-established complete fingerprint database, which has high cost and large workload in database construction and maintenance, and is difficult to cover all potential pollution sources and process changes; second, the pollutants in the environment will undergo chemical transformation and mixing dilution during the transmission process, resulting in deviation between the measured spectrum and the standard fingerprint of the source spectrum library, and reducing the matching accuracy; third, it usually needs offline sampling and laboratory analysis, which is time-consuming and complicated, and cannot meet the real-time and rapid response requirements of source tracking; traditional monitoring and manual patrol: the commonly used method, which relies on limited online monitoring sites to alarm, and then environmental protection personnel carry out on-site investigation with portable equipment. This method has slow response speed, high labor cost, and is highly dependent on personal experience, which is difficult to effectively locate hidden and intermittent emission sources in complex industrial areas. In related technologies, model calculation or manual investigation is usually at the level of hours or even days, which cannot capture short-term and sudden emission events such as instantaneous stealing and abnormal start-stop of pollution control facilities, and relies too much on environmental concentration data or limited source inventory, without deep fusion with dynamic data such as production conditions of enterprises, real-time running state of pollution control facilities (for example, current, voltage, valve opening, etc.), energy consumption, etc., and lacks monitoring of pollution generation process. In complex scenarios such as multiple sources crossing and sudden changes in meteorological conditions, the error of contribution rate calculation of traditional methods can exceed 30%, which can only be traced to the park or enterprise level, and cannot accurately locate to the specific workshop, production line or production equipment. Therefore, there are problems such as single data dimension, low spatio-temporal resolution and insufficient source tracking accuracy, which are difficult to deeply integrate multi-source data and accurately trace in real time, resulting in low accuracy and efficiency of source tracking.

[0003] The information disclosed in the background section of the present application is only intended to deepen the understanding of the general background of the present application and should not be regarded as acknowledging or implying in any form that the information constitutes prior art known to those skilled in the art. SUMMARY

[0004] The present application provides a monitoring and early warning method for rapid and accurate traceability, which can solve the technical problems that related technologies are difficult to deeply integrate multi-source data and are difficult to realize real-time and accurate traceability.

[0005] According to a first aspect of the present application, a monitoring and early warning method for rapid and accurate traceability is provided, comprising: obtaining enterprise condition monitoring data through an edge layer monitoring device, and obtaining regional environment condition monitoring data and enterprise attribute information through a cloud device; analyzing the enterprise condition monitoring data and the regional environment condition monitoring data through the edge layer monitoring device and the cloud device to obtain alarm information; screening associated enterprises according to the alarm information and the regional environment condition monitoring data, and determining a traceability range influence value and a wind field influence value of the associated enterprises; obtaining a risk database score of the associated enterprises according to the enterprise condition monitoring data and the enterprise attribute information; determining an influence value of an in-production enterprise of the associated enterprises according to the traceability range influence value and the wind field influence value of the associated enterprises, and the risk database score; determining an enterprise internal multi-link verification credibility according to the enterprise condition monitoring data of the associated enterprises; obtaining an in-production enterprise comprehensive influence value according to the influence value of the in-production enterprise and the enterprise internal multi-link verification credibility; determining a risk level of the associated enterprises according to the in-production enterprise comprehensive influence value.

[0006] According to the present application, the associated enterprises are screened, and the traceability range influence value and the wind field influence value of the associated enterprises are determined, comprising: determining abnormal point position information according to the alarm information; screening pending associated enterprises according to the abnormal point position information, and determining a traceability range influence value of the pending associated enterprises; screening the associated enterprises from the pending associated enterprises according to the regional environment condition monitoring data, and determining a wind field influence value of the associated enterprises.

[0007] According to the present application, the pending associated enterprises are screened, and the traceability range influence value of the pending associated enterprises is determined, comprising: setting an abnormal screening range with the abnormal point position information as the center; determining the enterprises within the abnormal screening range as the pending associated enterprises; Obtain the distance between the to-be-determined associated enterprise and the abnormal point position information; According to the formula Determine the traceability range influence value of the to-be-determined associated enterprise Wherein, A is the influence coefficient of the traceability range constraint factor, and X is the distance between the to-be-determined associated enterprise and the abnormal point position information.

[0008] According to the present application, the associated enterprise is screened from the to-be-determined associated enterprise, and the wind field influence value of the associated enterprise is determined, comprising: Obtain the pollutant transmission path through the Lagrange reverse trajectory model and the abnormal point position information; According to the pollutant transmission path, set the fan-shaped screening range; Determine the associated enterprise in the fan-shaped screening range as the associated enterprise; Obtain the center line of the fan, and the included angle between the connecting line of the associated enterprise and the abnormal point position information and the center line; According to the formula Determine the wind field influence value of the associated enterprise Wherein, B is the wind field trajectory constraint influence coefficient, The included angle between the connecting line of the associated enterprise and the abnormal point position information and the center line.

[0009] According to the present application, the risk database score of the associated enterprise is obtained, comprising: According to the enterprise condition monitoring data and the scores of multiple alarm events, determine the alarm index score of the associated enterprise; According to the enterprise condition monitoring data and the scores of multiple enterprise investigation conditions, determine the investigation hidden danger index score of the associated enterprise; According to the enterprise condition monitoring data and the scores of multiple enterprise sudden environmental event risks, determine the enterprise sudden environmental event risk grading index score of the associated enterprise; According to the alarm index score, the investigation hidden danger index score, the enterprise sudden environmental event risk grading index score and the first preset weight, determine the risk database score of the associated enterprise.

[0010] According to the present application, the enterprise sudden environmental event risk grading index score of the associated enterprise is determined, comprising: According to the risk substance data of the associated enterprise, the production process and the atmospheric environmental risk control level, and the atmospheric environmental risk receptor sensitivity, determine multiple enterprise sudden environmental event risk scores.

[0011] According to the present application, the influence value of the in-production enterprise of the associated enterprise is determined according to the traceability range influence value and the wind field influence value of the associated enterprise, and the risk database score, and comprises the following steps: According to the enterprise condition monitoring data of the associated enterprise, the alarm influence value of the associated enterprise is determined. According to the alarm influence value, the traceability range influence value, the wind field influence value and the risk database score, the influence value of the in-production enterprise of the associated enterprise is determined.

[0012] According to the present application, the multi-link verification credibility in the enterprise is determined, comprising the following steps: According to the enterprise condition monitoring data of the associated enterprise, the abnormal highest frequency coefficient of each link of the associated enterprise is determined. According to the formula The verification coefficient of the i-th link of the j-th associated enterprise is determined , wherein is the abnormal intensity coefficient of the i-th link of the j-th enterprise, is the weight coefficient of the i-th link of the j-th enterprise, is the abnormal highest frequency coefficient of the i-th link of the j-th enterprise; According to the formula The multi-link comprehensive verification coefficient of the j-th associated enterprise is obtained , wherein G is a cross-environment consistency coefficient, is the number of links of the j-th associated enterprise; According to the formula The multi-link verification credibility in the enterprise of the j-th associated enterprise is determined , wherein is the multi-link comprehensive verification coefficient of the first associated enterprise, is the multi-link comprehensive verification coefficient of the second associated enterprise, is the multi-link comprehensive verification coefficient of the n-th associated enterprise.

[0013] According to the present application, the comprehensive influence value of the in-production enterprise is obtained, comprising the following steps: According to the formula The comprehensive influence value EE of the in-production enterprise of the associated enterprise is obtained, wherein DE is the influence value of the in-production enterprise of the associated enterprise, and S is the multi-link verification credibility in the enterprise of the associated enterprise.

[0014] According to the second aspect of the present application, a monitoring and early warning system for rapid and accurate traceability is provided, comprising: an acquisition module, which acquires enterprise condition monitoring data through an edge layer monitoring device and acquires regional environment condition monitoring data and enterprise attribute information through a cloud device; an alarm information module, which analyzes the enterprise condition monitoring data and the regional environment condition monitoring data through the edge layer monitoring device and the cloud device to obtain alarm information; a screening and influence value module, which screens associated enterprises according to the alarm information and the regional environment condition monitoring data and determines a traceability range influence value and a wind field influence value of the associated enterprises; a risk database score module, which acquires a risk database score of the associated enterprises according to the enterprise condition monitoring data and the enterprise attribute information; an in-production enterprise influence value module, which determines an influence value of an in-production enterprise of the associated enterprises according to the traceability range influence value and the wind field influence value of the associated enterprises and the risk database score; a credibility module, which determines a multi-link verification credibility in an enterprise according to the enterprise condition monitoring data of the associated enterprises; a comprehensive influence value module, which obtains a comprehensive influence value of the in-production enterprise according to the influence value of the in-production enterprise and the multi-link verification credibility in the enterprise; a risk level module, which determines a risk level of the associated enterprises according to the comprehensive influence value of the in-production enterprise.

[0015] By adopting the above technical solutions, the present application can achieve the following technical effects: According to the application, enterprise condition monitoring data can be obtained through edge layer monitoring equipment, regional environment condition monitoring data and enterprise attribute information can be obtained through cloud equipment, alarm information can be obtained through analysis, and then associated enterprises can be screened, and the traceability range influence value and the wind field influence value of the associated enterprises can be determined. According to the enterprise condition monitoring data and the enterprise attribute information, the risk database score of the associated enterprises can be obtained, and then the influence value of the in-production enterprises of the associated enterprises can be determined, and according to the enterprise condition monitoring data of the associated enterprises, the multi-link verification credibility in the enterprise can be determined, and then the comprehensive influence value of the in-production enterprises can be obtained, so as to determine the risk level of the associated enterprises. A multi-source data fusion and cloud-edge collaborative driving cross-scale multi-level traceability system can be constructed, the production enterprise external environmental pollution problem can be quickly, accurately and automatically traced, the pollution source can be accurately positioned and quickly responded from the region to the enterprise workshop, the environmental deterioration reason and the responsibility source can be determined in time, and scientific support can be provided for the emergency disposal of air events and the improvement of air quality. And the enterprise condition monitoring data can be obtained through the edge layer monitoring equipment, the regional environment condition monitoring data and the enterprise attribute information can be obtained through the cloud equipment, and the alarm information can be obtained after analysis, which breaks through the limitation of traditional methods that can only trace to the enterprise, and can comprehensively consider the enterprise DCS, power consumption and other data for traceability. And the cloud-edge collaborative architecture can reasonably distribute the computing load, the edge is responsible for real-time early warning, the cloud is responsible for in-depth analysis, and the real-time performance of mass data processing is improved. When determining the comprehensive influence value of the in-production enterprise, the comprehensive influence value of the in-production enterprise can be obtained based on the influence value of the in-production enterprise and the multi-link verification credibility in the enterprise, a decision model based on dynamic weight and credibility evaluation is designed, the credibility of different data sources is automatically evaluated and the weight of the data sources in the traceability decision is dynamically adjusted, the anti-interference ability and the reliability of the results of the system are improved, and a peripheral and internal two-level linkage traceability mechanism is created, the range is first macroscopically circled through a physical model, and then accurately positioned through a data model, so that the system can still maintain stable traceability performance and robustness under complex interference. Further, a multi-source data cross-validation and physical mechanism-data driven fusion model can be created, the deep correlation between environmental data, working condition data, energy data and video data is mined through feature engineering and machine learning algorithms, multi-source data is deeply fused and intelligently associated, the traceability efficiency and accuracy are improved, and the pollution causes are quickly locked to guide the supervision department to immediately carry out risk control and source treatment. The pre-prevention and rapid disposal capability of pollution events can be significantly improved, the continuous accumulation and diffusion of pollutants in the atmosphere can be reduced, the regional air quality can be improved, and the public health risk can be reduced.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory, but not limiting the application. Other features and aspects of the application will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other embodiments can also be obtained from these drawings without creative labor. Figure 1 An exemplary flowchart of a monitoring and early warning method for rapid and accurate traceability according to an embodiment of the present application is shown. Figure 2 An exemplary flowchart of screening associated enterprises and determining the traceability range influence value and wind field influence value of the associated enterprises according to an embodiment of the present application is shown. Figure 3 An exemplary block diagram of a monitoring and early warning system for rapid and accurate traceability according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will describe the technical solutions in the embodiments of the present application clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, but not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] The technical solutions of the present application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and some embodiments may not be described again for the same or similar concepts or processes.

[0020] Figure 1 An exemplary flowchart of a monitoring and early warning method for rapid and accurate traceability according to an embodiment of the present application is shown. The method comprises: Step S1, obtaining enterprise condition monitoring data through an edge layer monitoring device, and obtaining regional environment condition monitoring data and enterprise attribute information through a cloud device; Step S2, analyzing the enterprise condition monitoring data and the regional environment condition monitoring data through the edge layer monitoring device and the cloud device to obtain alarm information; Step S3, screening associated enterprises according to the alarm information and the regional environment condition monitoring data, and determining the traceability range influence value and the wind field influence value of the associated enterprises; Step S4, obtaining the risk database score of the associated enterprises according to the enterprise condition monitoring data and the enterprise attribute information; Step S5, determining the influence value of the in-production enterprise of the associated enterprise according to the traceability range influence value and the wind field influence value of the associated enterprise and the risk database score; Step S6, determining the multi-link verification credibility in the enterprise according to the enterprise condition monitoring data of the associated enterprise; Step S7, obtaining the comprehensive influence value of the in-production enterprise according to the influence value of the in-production enterprise and the multi-link verification credibility in the enterprise; Step S8, determining the risk level of the associated enterprise according to the comprehensive influence value of the in-production enterprise.

[0021] The monitoring and early warning method for rapid and accurate traceability according to the embodiments of the present application can obtain enterprise condition monitoring data through edge layer monitoring equipment, obtain regional environment condition monitoring data and enterprise attribute information through cloud equipment, and analyze and obtain alarm information, and then screen associated enterprises and determine the traceability range influence value and the wind field influence value of the associated enterprises. According to the enterprise condition monitoring data and the enterprise attribute information, the risk database score of the associated enterprise is obtained, and then the influence value of the in-production enterprise of the associated enterprise is determined, and the multi-link verification credibility in the enterprise is determined according to the enterprise condition monitoring data of the associated enterprise, and then the comprehensive influence value of the in-production enterprise is obtained, so as to determine the risk level of the associated enterprise. A multi-source data fusion and cloud-edge collaborative driving cross-scale multi-level traceability system can be constructed to quickly, accurately and automatically trace the environmental pollution problems of production enterprises, realize accurate positioning and rapid response of pollution sources from the region to the enterprise and the workshop, timely determine the cause and responsibility source of environmental deterioration, and provide scientific support for emergency disposal of air events and improvement of air quality.

[0022] Embodiment one: According to an embodiment of the present application, in step S1, the enterprise condition monitoring data is acquired by the edge layer monitoring device, and the regional environment condition monitoring data and enterprise attribute information are acquired by the cloud device. The enterprise production conditions (for example, the start-stop state of the key production equipment, the production load, the material addition amount) and the treatment facility parameters (for example, the fan frequency, the air volume, the reagent addition, the temperature, the pressure, etc.) accessed by the edge layer monitoring device (for example, the environmental quality monitoring device, the pollution control facility operation monitoring device, etc.), the production conditions and the treatment facility electricity (for example, the production line electric meter, the treatment facility special electric meter, etc.), the real-time online monitoring data of the pollution source emission (for example, the concentration and flow of VOCs, SO2, NOx, etc. at the organized waste gas emission port), the rainwater discharge online monitoring data, the video monitoring, the access control data, etc. are the enterprise condition monitoring data. The enterprise boundary accessed by the cloud device (for example, the enterprise boundary VOCs / odor online monitoring data, etc.), the park public area online monitoring data (that is, the park public environmental air quality monitoring station data), the sensitive point online monitoring data (for example, the air quality of the park surrounding sensitive point and the complaint record, etc.), the enterprise environmental impact assessment, the enterprise public opinion, the enterprise space distribution (that is, the enterprise space coordinates), the meteorology (for example, the wind speed, the wind direction, the boundary layer height, etc.), the underway (for example, the TVOC concentration, the path trajectory, etc. underway vehicle monitoring data), the manual investigation, etc. are the regional environment condition monitoring data and enterprise attribute information. Further, the above various data can be preprocessed, for example, format conversion, unit unification, quality check, and abnormal value elimination, so that the data from different sources are standardized and have a unified scale.

[0023] Embodiment two: According to an embodiment of the present application, in step S2, the enterprise condition monitoring data and the regional environment condition monitoring data are analyzed by the edge layer monitoring device and the cloud device to obtain the alarm information. The edge layer monitoring device can store the collected enterprise condition monitoring data and regional environment condition monitoring data on the edge side and perform lightweight abnormality research and judgment (for example, the feature vectors of various data are subjected to abnormality research and judgment), and the cloud device is subjected to series data analysis on the key feature quantities (for example, abnormality marks, statistical values, etc.) subjected to edge research and judgment, and the suspected objects and suspected links obtained by the research and judgment are transmitted to the closed-loop management module, so as to generate the alarm information (for example, the public environmental air quality monitoring station generates the TVOC high value alarm at 10:00). A collaborative system of edge rapid response and cloud deep analysis and closed-loop management is formed, the cloud computing power and storage pressure are reduced by analyzing the enterprise condition monitoring data and the regional environment condition monitoring data without reducing the analysis accuracy, the overall traceability response speed is improved, and the traceability and disposal efficiency are overall accelerated.

[0024] In an example, the server of the edge layer monitoring device is responsible for storing real-time raw data of the enterprise, and deploying a lightweight abnormality identification algorithm to quickly screen enterprise condition monitoring data such as production conditions, treatment facility operation, online monitoring data of emissions, and regional environmental condition monitoring data, and identify significant abnormalities such as concentration mutation, production-treatment asynchronization, and abnormal electricity use, to form alarm information and local alarm records. The platform of the cloud device only receives key feature quantities reported by the edge, while maintaining an enterprise historical risk database, a long-term emission feature library, and a meteorological database for deep traceability analysis.

[0025] In this way, enterprise condition monitoring data can be obtained through the edge layer monitoring device, regional environmental condition monitoring data and enterprise attribute information can be obtained through the cloud device, and alarm information can be obtained after analysis, breaking through the limitation of traditional methods that can only trace back to the enterprise, and enabling comprehensive consideration of enterprise internal DCS, electricity use, and other data for traceability. Moreover, the cloud-edge collaborative architecture can reasonably distribute the computing load, with the edge being responsible for real-time early warning and the cloud being responsible for deep analysis, thereby improving the real-time performance of massive data processing.

[0026] Embodiment Three Figure 2 An example flowchart for screening associated enterprises and determining the traceability range influence value and wind field influence value of the associated enterprises according to an embodiment of the present application is shown.

[0027] According to an embodiment of the present application, in step S3, associated enterprises are screened and the traceability range influence value and wind field influence value of the associated enterprises are determined according to the alarm information and the regional environmental condition monitoring data, including: step S31, determining abnormal point position information according to the alarm information; step S32, screening pending associated enterprises according to the abnormal point position information, and determining the traceability range influence value of the pending associated enterprises; and step S33, screening associated enterprises from the pending associated enterprises according to the regional environmental condition monitoring data, and determining the wind field influence value of the associated enterprises.

[0028] According to an embodiment of the present application, in step S31, abnormal point position information is determined according to the alarm information. The location (e.g., coordinates) of problem points in the alarm information, such as high-value alarm of public regional environmental air quality station data, complaint of abnormal odor at sensitive points, and abnormal high value of road walk-through in the park, can be taken as the abnormal point position information. For example, the alarm information is a high-value alarm of TVOC generated by a public environmental air quality monitoring station at 10:00, and the location of the public environmental air quality monitoring station is the abnormal point position information.

[0029] Embodiment Four According to the embodiment of the present application, in step S32, according to the abnormal point position information, the pending associated enterprise is screened, and the traceability range influence value of the pending associated enterprise is determined, including: setting an abnormal screening range with the abnormal point position information as the center; determining the enterprises in the abnormal screening range as the pending associated enterprises; obtaining the distance between the pending associated enterprise and the abnormal point position information; determining the traceability range influence value of the pending associated enterprise according to formula (1) , (1) Wherein, A is the influence coefficient of the traceability range constraint factor, and X is the distance between the pending associated enterprise and the abnormal point position information.

[0030] According to the embodiment of the present application, the abnormal screening range is set with the abnormal point position information as the center. For example, a circular range with the abnormal point position information as the center and a radius of 5km is set as the abnormal screening range. Further, the enterprises in the abnormal screening range can be determined as the pending associated enterprises. The enterprises outside the abnormal screening range are directly excluded from the traceability range this time, so as to eliminate the low probability objects with no spatial association with the abnormal point.

[0031] According to the embodiment of the present application, in formula (1), A is the influence coefficient of the traceability range constraint factor, for example, A is 100. Further, the ratio of the influence coefficient of the traceability range constraint factor and the distance between the pending associated enterprise and the abnormal point position information can be taken as the traceability range influence value of the pending associated enterprise . For example, the distance between a certain pending associated enterprise and the abnormal point position information is 1.2km, and the influence coefficient of the traceability range constraint factor is 100, so the traceability range influence value of the pending associated enterprise is 100 / 1.2=83.3 Embodiment five: According to the embodiment of the present application, in step S33, according to the regional environmental condition monitoring data, the associated enterprise is screened from the pending associated enterprise, and the wind field influence value of the associated enterprise is determined, including: obtaining the pollutant transmission path through the Lagrange reverse trajectory model and the abnormal point position information; setting a fan-shaped screening range according to the pollutant transmission path; determining the pending associated enterprise in the fan-shaped screening range as the associated enterprise; obtaining the center line of the fan, and the included angle between the line connecting the associated enterprise and the abnormal point position information and the center line; determining the wind field influence value of the associated enterprise according to formula (2) , (2) Wherein, B is the wind field trajectory constraint influence coefficient, is the included angle between the line connecting the associated enterprise and the abnormal point position information and the center line.

[0032] According to an embodiment of the present application, based on real-time wind speed, wind direction, boundary layer height and other meteorological data, the transmission path of the pollutant before the abnormal point information appears is simulated by a Lagrangian reverse trajectory model, that is, the pollutant transmission path. The angle bisector of the above pollutant transmission path is taken as the center line of the sector, and a sector range of ±45° (i.e. a sector range of 90°) is determined, which is the sector screening range. Further, the pending associated enterprises in the sector screening range are determined as the associated enterprises, and the pending associated enterprises exceeding the sector screening range can be eliminated under the constraint of the wind field, thereby further reducing the high-suspicion enterprise set. The angle bisector of the pollutant transmission path is the center line of the sector, and the angle between the line connecting the associated enterprise and the abnormal point information and the center line can be determined.

[0033] According to an embodiment of the present application, in formula (2), B is the wind field trajectory constraint influence coefficient, for example, B is 100. Further, the ratio of the wind field trajectory constraint influence coefficient and the angle between the line connecting the associated enterprise and the abnormal point information and the center line can be taken as the wind field influence value of the associated enterprise . For example, the angle between the line connecting a certain associated enterprise and the abnormal point information and the center line is 10°, and the wind field trajectory constraint influence coefficient is 100, so the wind field influence value of the associated enterprise is 100 / 10=10.

[0034] Embodiment six: According to an embodiment of the present application, in step S4, the risk database score of the associated enterprise is obtained according to the enterprise status monitoring data and the enterprise attribute information, including: determining the alarm index score of the associated enterprise according to the enterprise status monitoring data and the scores of multiple alarm events; determining the hidden danger index score of the associated enterprise according to the enterprise status monitoring data and the scores of multiple enterprise investigation statuses; determining the enterprise sudden environmental event risk grading index score of the associated enterprise according to the enterprise status monitoring data and the risk scores of multiple enterprise sudden environmental events; and determining the risk database score of the associated enterprise according to the alarm index score, the hidden danger index score, the enterprise sudden environmental event risk grading index score and the first preset weight.

[0035] According to the embodiment of the present application, the alarm index score of the associated enterprise is determined according to the enterprise condition monitoring data and the scores of various alarm events. The number of each alarm event of each associated enterprise is determined according to the enterprise condition monitoring data, for example, the number of automatic monitoring fraud alarm in the past years, the number of pollution source abnormal data alarm, the number of treatment facility abnormal alarm, the number of electricity abnormal alarm, the number of water-gas balance abnormal alarm, etc. And the preset alarm index score of each alarm event can be set artificially, for example, the preset alarm index score of each alarm event is 2. Further, the product of the total number of various alarm events of the associated enterprise and the preset alarm index score is taken as the alarm index score of the associated enterprise, for example, the preset alarm index score of each alarm event is 2, the number of automatic monitoring fraud alarm of a certain associated enterprise in the past years is 5, the number of pollution source abnormal data alarm is 3, and there is no other alarm event, and the alarm index score of the associated enterprise is (3+5) x 2 = 16.

[0036] According to the embodiment of the present application, the investigation hidden danger index score of the associated enterprise is determined according to the enterprise condition monitoring data and the scores of various enterprise investigation conditions. The number of each enterprise investigation condition of each associated enterprise can be determined according to the enterprise condition monitoring data, for example, the number of historical internal hidden danger investigation found problems, the number of factory boundary temporary monitoring found problems, etc. And the preset investigation hidden danger index score of each enterprise investigation condition can be set artificially, for example, the preset investigation hidden danger index score of each enterprise investigation condition is 3. Further, similar to the determination of the alarm index score of the associated enterprise, the product of the total number of various enterprise investigation conditions of the associated enterprise and the preset investigation hidden danger index score is taken as the investigation hidden danger index score of the associated enterprise.

[0037] Embodiment seven: According to the embodiment of the present application, the enterprise emergency environmental event risk grading index score of the associated enterprise is determined according to the enterprise condition monitoring data and the scores of various enterprise emergency environmental event risks, including: determining the scores of various enterprise emergency environmental event risks according to the risk substance data of the associated enterprise, the production process and the atmospheric environmental risk control level, and the atmospheric environmental risk receptor sensitivity.

[0038] According to the embodiment of the present application, the weights of the three enterprise emergency environmental events of the risk substance data of the associated enterprise, the production process and the atmospheric environmental risk control level, and the atmospheric environmental risk receptor sensitivity can be artificially set, for example, the weights of the above three enterprise emergency environmental events are all determined as 1. The risk substance data (i.e., the number of risk substances related to the atmosphere) of each associated enterprise, the production process and the atmospheric environmental risk control level, and the atmospheric environmental risk receptor sensitivity can be determined according to the industry status monitoring data. Further, the enterprise emergency environmental event risk scores of the risk substance data, the production process and the atmospheric environmental risk control level, and the atmospheric environmental risk receptor sensitivity can be determined. When determining the enterprise emergency environmental event risk score of the risk substance data, the ratio of the risk substance data to the critical amount can be used for determination, for example, when the ratio of the risk substance data to the critical amount is <1, the enterprise emergency environmental event risk score of the corresponding risk substance data is 0; when 1≤the ratio of the risk substance data to the critical amount is <10, the enterprise emergency environmental event risk score of the corresponding risk substance data is 5; when 10≤the ratio of the risk substance data to the critical amount is <50, the enterprise emergency environmental event risk score of the corresponding risk substance data is 15; when 50≤the ratio of the risk substance data to the critical amount is <100, the enterprise emergency environmental event risk score of the corresponding risk substance data is 25; and when the ratio of the risk substance data to the critical amount is ≥100, the enterprise emergency environmental event risk score of the corresponding risk substance data is 35.

[0039] According to the embodiment of the present application, when determining the enterprise emergency environmental event risk score of the production process and the atmospheric environmental risk control level, the risk process and equipment conditions, atmospheric environmental risk prevention and control measures, and the occurrence of sudden atmospheric environmental events of the production process of the associated enterprise can be used for determination, for example, the production process and atmospheric environmental risk control level value obtained by referring to the Enterprise Emergency Environmental Event Risk Classification Method (HJ941-2018) is used as the enterprise emergency environmental event risk score of the production process and the atmospheric environmental risk control level. When determining the enterprise emergency environmental event risk score of the atmospheric environmental risk receptor sensitivity, the atmospheric environmental risk receptor sensitivity type of the associated enterprise can be used for determination, for example, the enterprise emergency environmental event risk score of the atmospheric environmental risk receptor sensitivity corresponding to type 1 is 30; the enterprise emergency environmental event risk score of the atmospheric environmental risk receptor sensitivity corresponding to type 2 is 15; and the enterprise emergency environmental event risk score of the atmospheric environmental risk receptor sensitivity corresponding to type 3 is 0.

[0040] According to an embodiment of the present application, the enterprise emergency environmental event risk grading index score of the associated enterprise is obtained by weighting and summing the risk substance data, the production process and atmospheric environmental risk control level, and the atmospheric environmental risk receptor sensitivity of the enterprise emergency environmental event of the associated enterprise according to the weight of the enterprise emergency environmental event. For example, the weights of the three enterprise emergency environmental events are all 1, the risk substance data, the production process and atmospheric environmental risk control level, and the atmospheric environmental risk receptor sensitivity of the enterprise emergency environmental event of an associated enterprise are 25, 15 and 15 respectively, and the enterprise emergency environmental event risk grading index score of the associated enterprise is 25*1+15*1+15*1=55.

[0041] According to an embodiment of the present application, the risk database score of the associated enterprise is determined according to the alarm index score, the hidden danger investigation index score, the enterprise emergency environmental event risk grading index score and the preset first weight. The preset first weight corresponding to the alarm index score, the hidden danger investigation index score and the enterprise emergency environmental event risk grading index score can be set artificially, and the risk database score is obtained by weighting and summing the alarm index score, the hidden danger investigation index score and the enterprise emergency environmental event risk grading index score through the preset first weight. For example, the preset first weight corresponding to the alarm index score is 0.5, the preset first weight corresponding to the hidden danger investigation index score is 0.2, and the preset first weight corresponding to the enterprise emergency environmental event risk grading index score is 0.1, the alarm index score, the hidden danger investigation index score and the enterprise emergency environmental event risk grading index score of an associated enterprise are 12, 9 and 55 respectively, and the risk database score of the associated enterprise is 12*0.5+9*0.2+55*0.1=13.3.

[0042] Embodiment eight According to an embodiment of the present application, in step S5, the influence value of the in-production enterprise of the associated enterprise is determined according to the traceability range influence value and the wind field influence value of the associated enterprise and the risk database score, including: determining the alarm influence value of the associated enterprise according to the enterprise condition monitoring data of the associated enterprise; and determining the influence value of the in-production enterprise of the associated enterprise according to the alarm influence value, the traceability range influence value, the wind field influence value and the risk database score.

[0043] According to an embodiment of the present application, according to the enterprise condition monitoring data of the associated enterprise, the abnormal situation of the production, treatment and discharge data of the associated enterprise is determined (for example, the time of the abnormality of the online monitoring alarm, the working condition alarm, the treatment facility alarm, the electricity abnormality, the water and gas balance abnormality and the like of the associated enterprise). Further, a time window with a time length of T (for example, 2 hours) is set based on the abnormality time, the abnormality alarm situation of the production, treatment and discharge data of the associated enterprise within T hours before the abnormality time point is retrieved, and if there is an abnormal alarm, an alarm influence value is given to the associated enterprise (for example, an alarm influence value of 20 is given). For example, the abnormality time is 10:00, the time window T is 2 hours, the treatment facility temperature abnormality, the short-time increase of the discharge concentration and the like of a certain associated enterprise occur in the time period from 09:30 to 09:50, and the alarm influence value of 20 is given to the associated enterprise within the time period from 08:00 to 10:00.

[0044] According to an embodiment of the present application, according to the alarm influence value, the traceability range influence value, the wind field influence value and the risk database score, the influence value of the in-production enterprise of the associated enterprise is determined. The weights corresponding to the alarm influence value, the traceability range influence value, the wind field influence value and the risk database can be preset, and the alarm influence value, the traceability range influence value, the wind field influence value and the risk database score are processed by weighted summation, so that the influence value of the in-production enterprise of the associated enterprise is obtained. For example, the weights corresponding to the alarm influence value, the traceability range influence value, the wind field influence value and the risk database score are 0.2, 0.2, 0.2 and 0.4 respectively, the alarm influence value, the traceability range influence value, the wind field influence value and the risk database score of a certain associated enterprise are 20, 80, 10 and 15 respectively, and the influence value of the in-production enterprise of the associated enterprise is 20*0.2+80*0.2+10*0.2+15*0.4=28. The higher the influence value of the in-production enterprise indicates that the higher the relevance of the associated enterprise in the four dimensions of spatial position, wind direction, historical risk and abnormal period behavior to the pollution event.

[0045] Embodiment Nine: According to an embodiment of the present application, in step S6, according to the enterprise condition monitoring data of the associated enterprise, the multi-link verification credibility in the enterprise is determined, including: according to the enterprise condition monitoring data of the associated enterprise, the abnormality highest frequency coefficient of each link of the associated enterprise is determined. The verification coefficient of the i th link of the j th associated enterprise is determined according to formula (3) , (3) wherein, is the intensity coefficient of the abnormality of the i th link of the j th enterprise, is the weight coefficient of the i th link of the j th enterprise, The abnormal maximum frequency coefficient of the i th link of the j th enterprise; The multi-link comprehensive checking coefficient of the j th associated enterprise is obtained according to formula (4) , (4) Wherein, G is a cross-environment consistency coefficient, The number of links of the j th associated enterprise; The intra-enterprise multi-link checking credibility of the j th associated enterprise is determined according to formula (5) , (5) Wherein, The multi-link comprehensive checking coefficient of the 1 st associated enterprise, The multi-link comprehensive checking coefficient of the 2 nd associated enterprise, The multi-link comprehensive checking coefficient of the n th associated enterprise.

[0046] According to the embodiments of the present application, the abnormal maximum frequency coefficient of each link of the associated enterprise is determined according to the enterprise condition monitoring data of the associated enterprise. The frequency of historical accidents of each link of the associated enterprise is determined according to the enterprise condition monitoring data of the associated enterprise, and then different abnormal maximum frequency coefficients can be given to different frequencies, for example, the abnormal maximum frequency coefficient of the governance link of a certain associated enterprise is determined as 0.75, the abnormal maximum frequency coefficient of the pollution control link is determined as 0.5, the abnormal maximum frequency coefficient of the emission link is determined as 0.25, and the abnormal maximum frequency coefficient of the link without accidents is determined as 0.

[0047] According to the embodiments of the present application, in formula (3), The intensity coefficient of the i th link of the j th enterprise, which can be artificially set, for example, the intensity coefficient of the abnormal governance link of the corresponding enterprise is set as 0.5, the intensity coefficient of the abnormal emission link of the corresponding enterprise is set as 0.5, the intensity coefficient of the slightly abnormal emission link of the corresponding enterprise is set as 0.75, and the intensity coefficient of the abnormal pollution control link of the corresponding enterprise is set as 0.75. The weight coefficient of the i th link of the j th enterprise, which can be artificially set, for example, the weight coefficients of the pollution control link, the emission link and the governance link are set as 1, 1.5 and 1 respectively. Further, the checking coefficient of the i th link of the j th associated enterprise can be determined according to formula (3) For example, the abnormal intensity coefficient of the emission link of the jth associated enterprise is 0.5, the weight coefficient is 1.5, and the abnormal highest frequency coefficient is 0.75, respectively, and the verification coefficient of the emission link of the jth associated enterprise is 0.5*1.5*0.75=0.5625. Based on the same processing manner, the verification coefficients of the links of the jth associated enterprise can be obtained.

[0048] According to the embodiment of the present application, in formula (4), G is a cross-environment consistency coefficient, and when the relationship between two links should be positively correlated, G is 1, otherwise G is 0. For example, when the pollution generation increases, the pollution treatment load increases, and the emission decreases, that is, when it is a reverse relationship, it is homodirectional, that is, the cross-environment consistency coefficient G is 1. Further, the sum of the product of the verification coefficients of the links of the jth associated enterprise and the cross-environment consistency coefficient can be obtained. That is, the multi-link comprehensive verification coefficient of the jth associated enterprise is .

[0049] According to the embodiment of the present application, in formula (5), represents the sum of the multi-link comprehensive verification coefficients of the associated enterprises, and further the multi-link comprehensive verification coefficient of the jth associated enterprise and the ratio of the sum of the multi-link comprehensive verification coefficients of the associated enterprises That is, the intra-enterprise multi-link verification credibility of the jth associated enterprise is The higher the intra-enterprise multi-link verification credibility is, the higher the internal credibility of the jth associated enterprise as the source of the pollution event is. Based on the same processing manner, the intra-enterprise multi-link verification credibility of each associated enterprise can be obtained.

[0050] Embodiment Ten: According to the embodiment of the present application, in step S7, the in-production enterprise comprehensive influence value is obtained according to the influence value of the in-production enterprise and the intra-enterprise multi-link verification credibility, including: obtaining the in-production enterprise comprehensive influence value EE of the associated enterprise according to formula (6), (6) Wherein, DE is the influence value of the in-production enterprise of the associated enterprise, and S is the intra-enterprise multi-link verification credibility of the associated enterprise.

[0051] ​According to the embodiment of the present application, the sum of the in-production enterprise influence value of the associated enterprise and the enterprise internal multi-link verification credibility can be considered as an amplification coefficient of the in-production enterprise influence value of the associated enterprise. When S is high, the in-production enterprise influence value of the associated enterprise can be amplified, so as to obtain a higher comprehensive in-production enterprise influence value of the associated enterprise, so as to highlight the associated enterprise with external condition matching and internal evidence sufficient. On the contrary, when S is low, even if the in-production enterprise influence value of the associated enterprise is high, the comprehensive in-production enterprise influence value of the associated enterprise obtained will not be too high, so as to reduce the probability of misjudgment caused by accidental spatial coincidence. The in-production enterprise influence value of the associated enterprise (i.e., external condition) and the enterprise internal multi-link verification credibility (i.e., internal evidence) can be comprehensively considered to determine the comprehensive in-production enterprise influence value of the associated enterprise, so as to improve the accuracy and comprehensiveness of the determination of the comprehensive in-production enterprise influence value of the associated enterprise, and to be used for locking the responsibility source of the pollution event.

[0052] In this way, the comprehensive in-production enterprise influence value can be obtained based on the in-production enterprise influence value and the enterprise internal multi-link verification credibility. A decision model based on dynamic weight and credibility evaluation is designed to automatically evaluate the credibility of different data sources and dynamically adjust the weight of the data sources in the traceability decision, so as to improve the anti-interference ability of the system and the reliability of the results. Moreover, a two-level linkage traceability mechanism of periphery and interior is created to first macroscopically delimit the range through a physical model and then microscopically accurately position through a data model, so that the system can still maintain stable traceability performance and robustness under complex interference.

[0053] Embodiment eleven: According to the embodiment of the present application, in step S8, the associated enterprise risk level is determined according to the comprehensive in-production enterprise influence value. The in-production enterprise influence values of the associated enterprises can be ranked from large to small, and divided into three risk levels of major suspicion, larger suspicion and general suspicion according to the percentage distribution, so as to determine the associated enterprises and suspicious links with major suspicion and larger suspicion. For example, the top 10% of the risk levels are major suspicion, the risk levels from 10% to 40% are larger suspicion, and the risk levels from 40% to 100% are general suspicion. In the example, the major and larger suspicion objects can be automatically pushed to a closed-loop management module to generate an on-site verification task, issue a key evidence chain report, and facilitate the on-site verification of the traceability result. Moreover, after the supervision and verification, the enterprise needs to carry out risk rectification according to the verification result and upload the rectification situation to the cloud, and after the supervision and auditing, the closed-loop management of the traceability result is realized.

[0054] In this way, a multi-source data cross-validation and physical mechanism-data driven fusion model can be created, through feature engineering and machine learning algorithms, to mine deep correlation between environmental data, working condition data, energy data, and video data, deeply fuse multi-source data and perform intelligent correlation analysis, improve the efficiency and accuracy of the traceability, and then quickly lock the pollution causes to guide the regulatory authorities to immediately carry out risk management and control and source treatment. The pollution event can be significantly improved in pre-prevention and rapid disposal capacity, the accumulation and diffusion of pollutants in the atmosphere are reduced, thereby improving the regional air quality and reducing the public health risk.

[0055] According to the monitoring and early warning method for rapid and accurate tracing of the embodiment of the application, enterprise condition monitoring data can be obtained through an edge layer monitoring device, regional environment condition monitoring data and enterprise attribute information can be obtained through a cloud device, alarm information can be obtained by analysis, and then associated enterprises are screened, and the tracing range influence value and wind field influence value of the associated enterprises are determined. According to the enterprise condition monitoring data and the enterprise attribute information, the risk database score of the associated enterprises is obtained, and then the influence value of the in-production enterprises of the associated enterprises is determined, and according to the enterprise condition monitoring data of the associated enterprises, the multi-link verification credibility in the enterprise is determined, and then the comprehensive influence value of the in-production enterprises is obtained, so as to determine the risk level of the associated enterprises. A multi-source data fusion and cloud-edge collaborative driving cross-scale multi-level tracing system can be constructed, the production enterprise external environmental pollution problem can be rapidly, accurately and automatically traced, the pollution source can be accurately positioned and rapidly responded from the region to the enterprise and the workshop, the environmental deterioration reason and the responsibility source can be determined in time, and scientific support can be provided for the emergency disposal of the atmospheric event and the improvement of the air quality. And the enterprise condition monitoring data can be obtained through the edge layer monitoring device, the regional environment condition monitoring data and the enterprise attribute information can be obtained through the cloud device, and the alarm information can be obtained by analysis, which breaks through the limitation that the traditional method can only trace to the enterprise, and can comprehensively consider the enterprise internal DCS, power consumption and other data for tracing. And the cloud-edge collaborative architecture can reasonably distribute the computing load, the edge is responsible for real-time early warning, the cloud is responsible for deep analysis, and the real-time performance of mass data processing is improved (the time from the occurrence of the pollution event to the output of the tracing result is shortened from the traditional hour level to the minute level (less than 3 minutes), and near real-time response is realized). When determining the comprehensive influence value of the in-production enterprises, the comprehensive influence value of the in-production enterprises can be obtained based on the influence value of the in-production enterprises and the multi-link verification credibility in the enterprise, a decision model based on dynamic weight and credibility evaluation is designed, the credibility of different data sources is automatically evaluated and the weight of the data sources in the tracing decision is dynamically adjusted, the anti-interference ability of the system and the reliability of the result are improved, and a two-level linkage tracing mechanism of the periphery and the interior is created, the range is first macroscopically circled through a physical model, and then accurately positioned through a data model, so that the system can still maintain stable tracing performance and robustness under complex interference. Further, a multi-source data cross-validation and physical mechanism-data driven fusion model can be created, the deep correlation between the environmental data, the working condition data, the energy data and the video data is mined through feature engineering and machine learning algorithms, the multi-source data is deeply fused and intelligently associated, the tracing efficiency and accuracy are improved (the tracing accuracy rate in a complex scene is improved from less than 60% in the traditional method to more than 90%, the false positive rate is less than 5%, and the false negative rate is less than 1%), and then the pollution causes are quickly locked to guide the regulatory authorities to immediately carry out risk control and source treatment, the enterprise internal DCS, power consumption and other data can be combined to further trace to specific production workshops, process links or even single equipment, and “targeted” accurate control is realized.The pre-prevention and rapid treatment ability of pollution events can be significantly improved, the accumulation and diffusion of pollutants in the atmosphere are reduced, the regional air quality is improved, and the public health risk is reduced.

[0056] Embodiment twelve: Figure 3 An example block diagram of a monitoring and early warning system for rapid and accurate tracing according to an embodiment of the application is shown, the system comprising: An acquisition module acquires enterprise condition monitoring data through an edge layer monitoring device and acquires regional environment condition monitoring data and enterprise attribute information through a cloud device; An alarm information module analyzes the enterprise condition monitoring data and the regional environment condition monitoring data through the edge layer monitoring device and the cloud device to obtain alarm information; A screening and influence value module screens associated enterprises according to the alarm information and the regional environment condition monitoring data, and determines a tracing range influence value and a wind field influence value of the associated enterprises; A risk database score module acquires a risk database score of the associated enterprises according to the enterprise condition monitoring data and the enterprise attribute information; An in-production enterprise influence value module determines an influence value of an in-production enterprise of the associated enterprises according to the tracing range influence value and the wind field influence value of the associated enterprises and the risk database score; A credibility module determines a multi-link verification credibility in the enterprise according to the enterprise condition monitoring data of the associated enterprises; A comprehensive influence value module obtains a comprehensive influence value of the in-production enterprise according to the influence value of the in-production enterprise and the multi-link verification credibility in the enterprise; A risk level module determines a risk level of the associated enterprises according to the comprehensive influence value of the in-production enterprise.

[0057] The present application can be a method, device, system and / or computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions loaded thereon for performing various aspects of the present application.

[0058] Those skilled in the art will understand that the embodiments of the application shown in the above description and the accompanying drawings are only examples and do not limit the application. The purpose of the application has been fully and effectively achieved. The function and structural principle of the application has been shown and explained in the embodiments, and the implementation of the application can be any modification or modification without departing from the principle.

[0059] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions recorded in the above embodiments can be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A monitoring and early warning method for rapid and accurate source tracing, characterized in that, include: Enterprise status monitoring data is obtained through edge layer monitoring devices, and regional environmental status monitoring data and enterprise attribute information are obtained through cloud devices. By analyzing enterprise status monitoring data and regional environmental status monitoring data through edge layer monitoring devices and cloud devices, alarm information can be obtained; Based on alarm information and regional environmental monitoring data, related enterprises were screened, and the source tracing impact value and wind field impact value of the related enterprises were determined. Based on enterprise status monitoring data and enterprise attribute information, obtain the risk database score of related enterprises; Based on the traceability scope impact value and wind field impact value of related enterprises, as well as the risk database score, the impact value of the related enterprises' operating enterprises is determined; Based on the enterprise status monitoring data of related enterprises, determine the credibility of multi-stage verification within the enterprise; The comprehensive impact value of the enterprise in production is obtained based on the impact value of the enterprise in production and the credibility of multi-stage verification within the enterprise. The risk level of related enterprises is determined based on the comprehensive impact value of enterprises in operation.

2. The monitoring and early warning method for rapid and accurate source tracing according to claim 1, characterized in that, Based on alarm information and regional environmental monitoring data, related enterprises were screened, and the source tracing impact value and wind field impact value of these enterprises were determined, including: Based on the alarm information, determine the abnormal location information; Based on the abnormal location information, screen the potential related enterprises and determine the traceability scope and impact value of the potential related enterprises; Based on regional environmental monitoring data, related companies were screened from the list of potential related companies, and the wind field impact values ​​of the related companies were determined.

3. The monitoring and early warning method for rapid and accurate source tracing according to claim 2, characterized in that, Based on the anomaly location information, we screen potential related enterprises and determine the impact value of the traceability scope of these enterprises, including: Set the anomaly filtering range with the anomaly location information as the center; Companies within the anomaly screening range will be identified as pending related companies. Obtain the distance between the pending related enterprises and the abnormal location information; According to the formula Determine the impact value of the traceability scope of the unidentified related enterprises Where A is the influence coefficient of the traceability range constraint factor, and X is the distance between the undetermined related enterprise and the abnormal location information.

4. The monitoring and early warning method for rapid and accurate source tracing according to claim 2, characterized in that, Based on regional environmental monitoring data, related enterprises were screened from the list of potential related enterprises, and the wind field impact values ​​of these related enterprises were determined, including: The pollutant transport path was obtained using the Lagrange inverse trajectory model and anomaly location information; Set the sector-shaped screening range according to the pollutant transport path; The undetermined related companies within the fan-shaped screening range are identified as related companies; Obtain the center line of the sector, and the angle between the line connecting the associated enterprise and the abnormal location information and the center line; According to the formula Determine the wind field impact value of related enterprises Where B is the wind field trajectory constraint influence coefficient. The angle between the line connecting the associated enterprise and the abnormal location information and the center line.

5. The monitoring and early warning method for rapid and accurate source tracing according to claim 1, characterized in that, Based on enterprise status monitoring data and enterprise attribute information, obtain the risk database score of related enterprises, including: Based on enterprise status monitoring data and the scores of various alarm events, determine the alarm indicator scores of related enterprises; Based on the enterprise status monitoring data and the scores of various enterprise investigation statuses, the scores of the investigation hazard indicators for related enterprises are determined; Based on enterprise status monitoring data and various enterprise emergency environmental incident risk scores, determine the enterprise emergency environmental incident risk classification index scores for related enterprises; The risk database score of related enterprises is determined based on the alarm indicator score, the hidden danger investigation indicator score, the enterprise sudden environmental incident risk classification indicator score, and the preset first weight.

6. The monitoring and early warning method for rapid and accurate source tracing according to claim 5, characterized in that, Based on enterprise status monitoring data and various enterprise emergency environmental incident risk scores, the enterprise emergency environmental incident risk classification index scores for related enterprises are determined, including: Based on the risk material data, production processes and atmospheric environmental risk control levels of related enterprises, and the sensitivity of atmospheric environmental risk receptors, risk scores for various types of sudden environmental events are determined.

7. The monitoring and early warning method for rapid and accurate source tracing according to claim 1, characterized in that, Based on the source tracing impact value and wind field impact value of related enterprises, as well as the risk database score, the impact value of the related enterprises' operating enterprises is determined, including: Based on the enterprise status monitoring data of related enterprises, determine the alarm impact value of related enterprises; Based on the alarm impact value, the source tracing range impact value, the wind field impact value, and the risk database score, the impact value of the related enterprises' operating enterprises is determined.

8. The monitoring and early warning method for rapid and accurate source tracing according to claim 1, characterized in that, Based on the enterprise status monitoring data of related enterprises, the reliability of multi-stage verification within the enterprise is determined, including: Based on the enterprise status monitoring data of related enterprises, determine the highest frequency coefficient of anomalies in each link of the related enterprises; According to the formula Determine the verification coefficient for the i-th step of the j-th related enterprise. ,in, Let be the intensity coefficient of the anomaly occurring in the i-th stage of the j-th enterprise. Let be the weight coefficient of the i-th stage of the j-th enterprise. Let be the highest frequency coefficient of anomalies in the ith stage of the j-th enterprise; According to the formula Obtain the multi-stage comprehensive verification coefficient of the j-th related enterprise. Where G is the cross-environment consistency coefficient. The number of links for the j-th related enterprise; According to the formula Determine the reliability of multi-stage verification within the enterprise of the j-th related enterprise. ,in, This is the comprehensive verification coefficient for the first related enterprise across multiple stages. This is the comprehensive verification coefficient for the second related enterprise across multiple stages. This is the comprehensive verification coefficient for the nth related enterprise across multiple stages.

9. The monitoring and early warning method for rapid and accurate source tracing according to claim 1, characterized in that, Based on the impact value of the producing enterprise and the reliability of multi-stage verification within the enterprise, the comprehensive impact value of the producing enterprise is obtained, including: According to the formula Obtain the comprehensive impact value EE of the related enterprise's operating enterprises, where DE is the impact value of the related enterprise's operating enterprises, and S is the credibility of the multi-stage verification within the related enterprise.

10. A monitoring and early warning system for rapid and accurate source tracing, characterized in that, include: The acquisition module acquires enterprise status monitoring data through edge layer monitoring devices and regional environmental status monitoring data and enterprise attribute information through cloud devices. The alarm information module analyzes enterprise status monitoring data and regional environmental status monitoring data through edge layer monitoring devices and cloud devices to obtain alarm information; The filtering and impact value module filters related enterprises based on alarm information and regional environmental monitoring data, and determines the source range impact value and wind field impact value of related enterprises; The risk database score module obtains the risk database score of related enterprises based on enterprise status monitoring data and enterprise attribute information; The "In-Production Enterprise Impact Value" module determines the impact value of the in-production enterprises of related enterprises based on the traceability scope impact value and wind field impact value of related enterprises, as well as the risk database score. The credibility module determines the credibility of multiple verification processes within an enterprise based on enterprise status monitoring data from related companies. The comprehensive impact value module obtains the comprehensive impact value of the enterprise in production based on the impact value of the enterprise in production and the credibility of multi-stage verification within the enterprise. The risk level module determines the risk level of related enterprises based on the comprehensive impact value of enterprises in operation.

Images