Pollution discharge permission evaluation and management method based on intelligent analysis

Abstract

The invention provides a pollution discharge permission evaluation and management method based on intelligent analysis, and relates to the technical field of pollution discharge management, and the method comprises the steps: obtaining first pollution discharge permission information of a first enterprise; generating first period enterprise pollution discharge data and first period enterprise energy consumption data; carrying out pollution discharge standard exceeding judgment to generate a first period judgment result; when the judgment result of the first period is that the standard does not exceed the standard, pollution discharge standard exceeding risk prediction and energy consumption prediction in a second period are carried out based on the enterprise pollution discharge data of the first period, the enterprise energy consumption data of the first period, the pollution discharge limit value information of the second period and the energy consumption limit value information of the second period, and a standard exceeding risk index is generated; and according to the standard-exceeding risk index, carrying out pollution discharge standard-exceeding reminding on the first enterprise. According to the method and the device, the problem that an early warning mechanism for future pollution discharge risks is lacked in the prior art can be solved, and the technical effects of timely supervision and emission standard exceeding reminding are achieved.

Description

Technical Field

[0001] This application relates to the technical field of sewage discharge management, and particularly to a sewage discharge permit evaluation and management method based on intelligent analysis. Background Art

[0002] With the acceleration of the industrialization and urbanization processes and the continuous improvement of environmental protection management requirements, the sewage discharge management problem of industrial enterprises has become one of the core issues in enterprise management. In order to ensure that the sewage discharge behavior of enterprises complies with environmental protection standards, a strict sewage discharge permit system has been implemented for enterprises, stipulating the types and limits of pollutants that enterprises are allowed to discharge within a certain period. Enterprises implement the sewage discharge permit system and obtain sewage discharge data through automatic, manual and other monitoring methods for supervision by relevant departments.

[0003] The existing sewage discharge monitoring system lacks a warning mechanism for future sewage discharge risks. Usually, an enterprise will only be discovered and punished after the sewage discharge exceeds the standard, but this ex-post supervision mode cannot prevent the occurrence of excessive discharge in time and may cause irreversible damage to the environment. Without prediction means based on historical data and future discharge trends, enterprises cannot take corresponding measures in advance to prevent the occurrence of excessive discharge. Summary of the Invention

[0004] The purpose of this application is to provide a sewage discharge permit evaluation and management method based on intelligent analysis to solve the technical problem in the prior art that the sewage discharge permit management effect is not good due to the lack of a warning mechanism for future sewage discharge risks.

[0005] In view of the above problems, this application provides a sewage discharge permit evaluation and management method based on intelligent analysis, including: obtaining the first sewage discharge permit information of the first enterprise, where the first sewage discharge permit information includes a first sewage discharge type list, first-period sewage discharge limit information, second-period sewage discharge limit information, a first energy consumption list, first-period energy consumption limit information, and second-period energy consumption limit information; establishing a communication connection with the first automatic monitoring device of the first enterprise, receiving and analyzing the automatic monitoring information in the first period in real time, and generating first-period enterprise sewage discharge data and first-period enterprise energy consumption data; combining the first sewage discharge type list, the first-period sewage discharge limit information, the first energy consumption list, the first-period energy consumption limit information, the first-period enterprise sewage discharge data, and the first-period enterprise energy consumption data to judge whether the sewage discharge exceeds the standard, and generating a first-period judgment result; when the first-period judgment result is that the standard is not exceeded, predicting the pollution sewage discharge exceeding the standard risk and the energy consumption in the second period based on the first-period enterprise sewage discharge data, the first-period enterprise energy consumption data, the second-period sewage discharge limit information, and the second-period energy consumption limit information, and generating an exceeding the standard risk index; and giving a sewage discharge exceeding the standard reminder to the first enterprise according to the exceeding the standard risk index.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Obtain the first pollution discharge permit information of the first enterprise, where the first pollution discharge permit information includes a first list of pollution discharge types, first-period pollution discharge limit information, second-period pollution discharge limit information, a first energy consumption list, first-period energy consumption limit information, and second-period energy consumption limit information; establish a communication connection with the first automatic monitoring device of the first enterprise, receive and analyze the automatic monitoring information in the first period in real time, and generate first-period enterprise pollution discharge data and first-period enterprise energy consumption data; combine the first list of pollution discharge types, the first-period pollution discharge limit information, the first energy consumption list, the first-period energy consumption limit information, the first-period enterprise pollution discharge data, and the first-period enterprise energy consumption data to judge whether there is an excessive pollution discharge, and generate a first-period judgment result; when the first-period judgment result is that there is no excessive discharge, based on the first-period enterprise pollution discharge data, the first-period enterprise energy consumption data, the second-period pollution discharge limit information, and the second-period energy consumption limit information, predict the risk of excessive pollution discharge and the energy consumption in the second period, and generate an excessive discharge risk index; give a pollution discharge excessive reminder to the first enterprise according to the excessive discharge risk index. By monitoring and analyzing the enterprise's pollution discharge data in real time and combining the pollution discharge permit information, it can intelligently judge the situation of excessive pollution discharge, predict the excessive discharge risk in the next period, generate an excessive discharge risk index, and give a pollution discharge excessive reminder, helping the enterprise take measures in advance to prevent future excessive pollution discharge, achieving the technical effect of timely supervision and giving an excessive discharge reminder.

[0008] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specific embodiments of this application are specifically given. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understandable through the following description of the specification. Brief Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0010] Figure 1 It is a schematic flowchart of the pollution discharge permit evaluation and management method based on intelligent analysis of this application;

[0011] Figure 2 This is a schematic flowchart of generating an over-standard risk index in the sewage discharge permit evaluation and management method based on intelligent analysis of this application. Specific implementation manners

[0012] By providing a sewage discharge permit evaluation and management method based on intelligent analysis, this application solves the technical problem in the prior art that due to the lack of an early warning mechanism for future sewage discharge risks, the management effect of sewage discharge permits is poor. Through real-time monitoring and analysis of the enterprise's sewage discharge data, combined with the sewage discharge permit information, it intelligently judges the sewage discharge over-standard situation, predicts the over-standard risk in the next cycle, generates over-standard risk indicators, and gives sewage discharge over-standard reminders, helping enterprises take measures in advance to prevent future sewage discharge over-standard, achieving the technical effects of timely supervision and over-standard discharge reminder.

[0013] Next, the technical solutions in this application will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited by the example embodiments described here. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application. Additionally, it should be noted that for the sake of description, only parts related to this application are shown in the accompanying drawings rather than all of them.

[0014] Please refer to the attached Figure 1 , this application provides a sewage discharge permit evaluation and management method based on intelligent analysis, which specifically includes the following steps:

[0015] Step 1: Obtain the first sewage discharge permit information of the first enterprise, where the first sewage discharge permit information includes a first sewage discharge type list, first-period sewage discharge limit information, second-period sewage discharge limit information, a first energy consumption list, first-period energy consumption limit information, and second-period energy consumption limit information.

[0016] Specifically, the first enterprise generally refers to any enterprise that needs to be subject to pollutant discharge permit management. The first pollutant discharge permit information refers to the content and structure covered by the pollutant discharge permit of the first enterprise, mainly including the first pollutant discharge type list, the pollutant discharge limit information for the first cycle, and the pollutant discharge limit information for the second cycle. The first pollutant discharge type list clearly lists the different types of pollutant discharge permit types involved by the first enterprise, which may include waste gas, wastewater, solid waste, noise, etc. For example, the pollutant discharge type list of a chemical enterprise includes sulfur dioxide and nitrogen oxides in waste gas, as well as chemical oxygen demand and ammonia nitrogen in wastewater. The pollutant discharge limit information for the first cycle refers to the specific limits of pollutants that the first enterprise is allowed to discharge within a certain cycle (such as one day), usually expressed in specific numerical forms. For example, in the pollutant discharge limit information of a certain enterprise in the first cycle, the emission limit of sulfur dioxide is 50mg / m 3 , and the concentration limit of chemical oxygen demand in wastewater is 300mg / L. The pollutant discharge limit information for the second cycle refers to the specific limits of pollutants that are allowed to be discharged in the second cycle which is greater than the first cycle. For example, if the first cycle is daily, the second cycle is monthly, and the second cycle must be greater than the first cycle.

[0017] The first energy consumption list refers to the list of energy consumption types that need to be supervised, such as electric energy. The energy consumption limit information for the first cycle refers to the limits of different types of energy consumption within the first cycle, and the energy consumption limit information for the second cycle refers to the limits of different types of energy consumption within the second cycle.

[0018] Step 2: Establish a communication connection with the first automatic monitoring device of the first enterprise, receive and analyze the automatic monitoring information in real time in the first cycle, and generate the enterprise pollutant discharge data and enterprise energy consumption data for the first cycle.

[0019] Specifically, after establishing a communication connection with the first automatic monitoring device of the first enterprise, start receiving various pollutant discharge information in real time in the first cycle, and analyze these data into the pollutant discharge data for the first cycle. This data is collected and transmitted by the first automatic monitoring device. The first automatic monitoring device includes an exhaust gas monitoring module, a wastewater monitoring module, a noise monitoring module, a solid waste monitoring module, and an energy consumption monitoring device. These modules respectively conduct real-time monitoring and data collection for different types of pollution sources.

[0020] The exhaust gas monitoring module is responsible for monitoring the exhaust gas emission situation of the first enterprise. It is usually equipped with a variety of sensors for detecting substances such as sulfur dioxide, nitrogen oxides, and particulate matter. For example, a steel plant needs to monitor the sulfur dioxide concentration emitted by its blast furnace in real time. The wastewater monitoring module is used to monitor the pollutant concentration in wastewater, such as chemical oxygen demand (COD), ammonia nitrogen (NH 3-N), and heavy metal ions, etc. The noise monitoring module is responsible for collecting the noise values of the enterprise during the working hours. The solid waste monitoring module is used to monitor the generation amount, treatment method, and final disposal path of solid waste to ensure the compliant treatment of waste. For example, a chemical enterprise may need to monitor the generation amount and disposal method of its hazardous waste to ensure that it is not discarded randomly or directly discharged without treatment. The energy consumption monitoring equipment is used to monitor the energy consumption amount.

[0021] In actual operation, each module continuously collects and transmits real-time data. For example, the exhaust gas monitoring module uploads the sulfur dioxide concentration data at regular intervals through the sensors installed on the exhaust pipe; similarly, the wastewater monitoring module may also upload the COD data in the wastewater every hour. Parse and store various types of pollution discharge data received. Thus, according to the data collected by each module, extract the pollution discharge data belonging to the first period as the enterprise pollution discharge data in the first period, including the real-time discharge amounts of various pollutants, and the enterprise energy consumption data in the first period. The enterprise energy consumption data in the first period includes the total energy consumption of the enterprise for production tasks in the first period.

[0022] Step three: Combine the first pollution discharge type list, the first-period pollution discharge limit information, the first energy consumption list, the first-period energy consumption limit information, the first-period enterprise pollution discharge data, and the first-period enterprise energy consumption data to judge whether there is an excessive pollution discharge, and generate a judgment result for the first period.

[0023] Specifically, the first-period enterprise pollution discharge data is the actual discharge data collected by the first automatic monitoring equipment, including the discharge amount of each pollutant and the operation status of the pollution control facilities. Combine the first pollution discharge type list and the first-period pollution discharge limit information, extract the actual discharge amount of any type of pollutant from the first-period enterprise pollution discharge data, and compare it with the specified discharge amount corresponding to the first-period pollution discharge limit information. If the actual discharge amount exceeds the permitted discharge amount, it means that the discharge of this type of pollutant exceeds the standard in the first period, otherwise it does not exceed the standard. Similarly, extract any type of energy consumption amount from the first-period enterprise energy consumption data, and compare it with the specified energy consumption amount corresponding to the first-period energy consumption limit information. If the actual energy consumption amount exceeds the permitted energy consumption amount, it means that this type of energy consumption amount exceeds the standard in the first period, otherwise it does not exceed the standard. Generate a judgment result for the first period according to the excessive pollution discharge judgment result of the pollutant discharge amount and the excessive pollution discharge judgment result of the energy consumption.

[0024] Step four: When the judgment result for the first period is that there is no excessive discharge, based on the first-period enterprise pollution discharge data, the first-period enterprise energy consumption data, the second-period pollution discharge limit information, and the second-period energy consumption limit information, predict the risk of excessive pollution discharge and the energy consumption amount in the second period, and generate an excessive pollution discharge risk index.

[0025] Specifically, in the case where the judgment result of the first cycle is not exceeding the standard, further based on the enterprise pollutant discharge data of the first cycle and the pollutant discharge limit information of the second cycle, as well as the enterprise energy consumption data of the first cycle and the energy consumption limit information of the second cycle, the risk of exceeding the standard for pollutant discharge and energy consumption in the second cycle will be predicted to generate an exceeding-standard risk indicator, that is, to predict whether there is a risk of exceeding the pollutant discharge standard and energy consumption standard for the first enterprise in the second cycle. For example, if it is determined that the pollutant discharge of the first enterprise within a week does not exceed the standard, the pollutant discharge behavior within a month will continue to be predicted to judge the exceeding-standard risk within a month. The enterprise pollutant discharge data of the first cycle is the actual pollutant discharge situation of the first enterprise in the first cycle, covering the total amount of all pollutants discharged and the specific discharge trend. For example, within a month, the daily sulfur dioxide discharge amount of the first enterprise, the chemical oxygen demand (COD) concentration in the wastewater, etc. are all recorded as the basis for prediction in the next cycle. The pollutant discharge limit information of the second cycle is the discharge limit set by the relevant department for the first enterprise in the second cycle (such as the whole quarter). The exceeding-standard risk indicator is a risk coefficient predicted based on historical discharge data and future discharge limits, indicating whether there is a possibility of exceeding the standard for the discharge of a certain or multiple pollutants by the first enterprise in the second cycle. For example, an exceeding-standard risk indicator of 0.8 (i.e., 80% risk) means that the enterprise has a relatively high possibility of exceeding the standard in the second cycle. For example, a chemical enterprise has an annual sulfur dioxide permit discharge amount of 2.56 t / a, and the actual discharge amount in the first quarter reaches 1.52 t. During prediction, based on the discharge trend of the first cycle, it is predicted that the discharge amount in the second quarter may exceed 2.56 t, and the generated pollutant exceeding-standard risk indicator is 1. And so on, combining the enterprise energy consumption data of the first cycle and the energy consumption limit information of the second cycle, the risk of exceeding the standard for energy consumption in the second cycle will be predicted. It should be noted that the exceeding-standard risk indicator includes the exceeding-standard risk indicators corresponding to each type of pollutant and each type of energy consumption. Based on this, it is prompted that the first enterprise has a relatively high risk of exceeding the standard, and it is recommended to take emission control optimization measures in advance to help the enterprise identify potential environmental protection problems early and ensure that future pollutant discharge behaviors meet environmental protection requirements.

[0026] Step Five: Give a reminder to the first enterprise about exceeding the pollutant discharge standard according to the exceeding-standard risk indicator.

[0027] Specifically, the exceeding-standard risk indicator generally ranges from 0 to 1. The closer the value is to 1, the higher the possibility that the first enterprise will exceed the pollutant discharge standard in the second cycle. For example, when the exceeding-standard risk indicator is 0.9, it means that the enterprise has a 90% possibility of exceeding the standard in the next cycle. Further, a staff member can set a risk threshold, such as setting it to 0.8. If the exceeding-standard risk indicator is greater than the risk threshold, at this time, a reminder about exceeding the pollutant discharge standard needs to be given to the first enterprise, so that the enterprise can fully understand its pollutant discharge risk and take preventive measures to avoid exceeding the discharge standard. This proactive reminder mechanism can not only improve the environmental protection compliance of the enterprise but also reduce the environmental protection risk of exceeding the discharge standard.

[0028] Furthermore, as shown in the appendix Figure 2 , step four of this application includes:

[0029] Based on the first sewage discharge type list, connect to the data sharing platform, and collect the historical sewage discharge execution time series and historical energy consumption monitoring time series of the first enterprise; based on the long short-term memory network, train the large time zone continuous sewage discharge prediction branch with the historical sewage discharge execution time series, and train the large time zone energy consumption prediction branch with the historical energy consumption monitoring time series, integrate and connect the large time zone continuous sewage discharge prediction branch and the large time zone energy consumption prediction branch to generate a prediction model; input the first cycle enterprise sewage discharge data, the first cycle enterprise energy consumption data and the second cycle into the prediction model to generate the second cycle sewage discharge prediction information and the second cycle energy consumption prediction information; compare the second cycle sewage discharge prediction information with the second cycle sewage discharge limit information, and the second cycle energy consumption limit information with the second cycle energy consumption prediction information to generate the exceed-standard risk index.

[0030] Specifically, the data sharing platform is a platform that contains the historical sewage discharge data of enterprises. Enterprises can upload their emission records to this platform for easy calling and analysis. Specifically, it includes the total amount of pollutants discharged, the total energy consumption and their change trends every day, week, and month, providing rich historical data support. The historical sewage discharge execution time series refers to the time series data of the past emission behavior of the first enterprise, showing the amount of pollutants discharged in different time periods. For example, the emission time series of sulfur dioxide of a certain chemical enterprise in the past year may be: 300 kg in January, 320 kg in February, and 350 kg in March. Among them, January can be further divided into the emissions of each day. Through these historical data, the sewage discharge trend and periodicity of the enterprise can be analyzed. The historical energy consumption monitoring time series refers to the time series data of the past energy consumption of the first enterprise, showing the energy consumption in different time periods. The long short-term memory network (LSTM) is a deep learning model used to process time series data, especially good at analyzing long-term and short-term dependencies. Through the long short-term memory network, the long-term trends (such as seasonal emission fluctuations) and short-term fluctuations (such as monthly or weekly changes) in the sewage discharge behavior of the first enterprise can be identified.

[0031] The large and small time zone continuous sewage discharge prediction branch is a sewage discharge prediction model trained based on the LSTM model. It can predict future sewage discharge amounts according to different time scales (such as days, weeks, months), flexibly cope with the periodic and sudden changes in the enterprise's emission behavior, and provide more accurate prediction results. Similarly, the large and small time zone energy consumption prediction branch is a sewage discharge prediction model trained based on the LSTM model. It can predict future energy consumption amounts according to different time scales (such as days, weeks, months), flexibly cope with the periodic and sudden changes in the enterprise's energy consumption, and provide more accurate prediction results. Finally, the large and small time zone continuous sewage discharge prediction branch and the large and small time zone energy consumption prediction branch are integrally connected to generate a prediction model. The first-cycle enterprise sewage discharge data, the first-cycle enterprise energy consumption data, and the second cycle are input into the prediction model to generate second-cycle sewage discharge prediction information and second-cycle energy consumption prediction information. For example, the large and small time zone continuous sewage discharge prediction branch can predict the overall sewage discharge amount in January based on the sewage discharge quantity in the first week of January, and use this as the second-cycle sewage discharge prediction information. Compare the second-cycle sewage discharge prediction information with the second-cycle sewage discharge limit information. If the prediction result exceeds the sewage discharge limit, the over-standard risk index is directly configured as 1. If it does not exceed, the over-standard risk index is generated according to the difference. Specifically, the difference between the prediction result and the sewage discharge limit can be calculated, then the ratio of the difference to the sewage discharge limit is calculated, and 1 minus this ratio is used. The resulting value is the over-standard risk index corresponding to the pollutant. The closer the prediction result is to the sewage discharge limit, the closer the over-standard risk index is to 1, indicating that the enterprise has a high over-standard risk, providing a warning for the enterprise and prompting it to take corresponding environmental protection measures in advance to reduce the possibility of over-standard in the next cycle.

[0032] Furthermore, the present application further includes the following steps:

[0033] Perform random segmentation of the historical sewage discharge execution time series into large and small continuous time zones to generate multiple time zone segmentation results; based on the long short-term memory network, train the large and small time zone continuous sewage discharge prediction branch with the multiple time zone segmentation results.

[0034] Specifically, the historical pollution discharge execution time series refers to the pollution discharge data of the first enterprise in the past period of time. These data are usually recorded at time granularities such as days, weeks, and months. The historical pollution discharge execution time series is divided into multiple time segments by randomly dividing the historical pollution discharge data into two consecutive different time lengths. Among them, the segmentation result of any time zone includes two time segments of different lengths, and the two time segments are connected. For example, one time segment is the pollution discharge volume in the first week of August, and the other time segment is the pollution discharge volume for the entire month of August. The changes in pollution discharge behavior under long-term cycles can be better captured through short-term data. The long short-term temporal memory network (LSTM) is a deep learning model used to process time series data. It is particularly good at analyzing data with long-term and short-term dependencies. Through the LSTM model, the long-term trend of an enterprise's pollution discharge behavior can be learned from the segmented data. Simply put, a time zone segmentation result is used as a set of data, in which the pollution discharge data corresponding to the short-term time segments are the training input, and the pollution discharge data corresponding to the long-term time segments are the output supervision values. Based on this, multiple iterative training is performed until the test accuracy of the long short-term temporal memory network meets the preset accuracy requirements, such as 90%, and a continuous pollution discharge prediction branch for large and small time zones is obtained, providing model support for pollution discharge risk prediction, thereby effectively predicting future pollution discharge conditions and providing enterprises with accurate risk warnings.

[0035] Similarly, the same method can be used to construct the large and small time zone energy consumption prediction branch, which will not be described in detail here.

[0036] Furthermore, step five of this application includes:

[0037] If the risk index of exceeding the standard is greater than the preset risk index, the pollutants exceeding the standard are located according to the pollution discharge forecast information of the second period and the pollution discharge limit information of the second period, and the types of energy consumption exceeding the standard are located according to the energy consumption forecast information of the second period and the energy consumption limit information of the second period; a first mapping relationship table of the production equipment, pollution treatment equipment and pollutants discharged by the first enterprise and a second mapping relationship table corresponding to the energy consumption type are established; the pollutants exceeding the standard are input into the first mapping relationship table, the types of energy consumption exceeding the standard are input into the second mapping relationship table, and the associated equipment group is located; the pollution discharge forecast information of the second period, the energy consumption forecast information of the second period and the associated equipment group are sent to the first enterprise for early warning.

[0038] Specifically, when the risk index of exceeding the standard is greater than the preset risk index, the pollutants exceeding the standard will be located according to the sewage discharge prediction information in the second cycle and the sewage discharge limit information in the second cycle. At the same time, the energy consumption type exceeding the standard will be located according to the energy consumption prediction information in the second cycle and the energy consumption limit information in the second cycle. Furthermore, a first mapping relationship table of the production equipment, sewage treatment equipment and pollutants discharged by the first enterprise, and a second mapping relationship table corresponding to the energy consumption type are established. The equipment groups that may cause exceeding the standard are associated through the first mapping relationship table and the second mapping relationship table, and a warning message is sent to the enterprise. The first mapping relationship table and the second mapping relationship table are a database that records the relationships among the production equipment, sewage treatment equipment, pollutants discharged and energy consumption of the first enterprise. Through this table, it is possible to trace which equipment or processes are associated with the emissions of specific pollutants or energy consumption. The mapping relationship table is constructed by professional technical personnel in the field based on the historical production data and sewage discharge data of the first enterprise. The production equipment and pollution treatment equipment associated with the pollutants exceeding the standard are identified through the mapping relationship table, and these are used as the associated equipment groups, and a warning message is sent to the first enterprise to prompt the equipment and processes that need to be adjusted.

[0039] Exemplarily, the sewage discharge prediction information in the second cycle of a chemical enterprise shows that the emission amount of sulfur dioxide reaches 850 kg, while the limit in the sewage discharge limit information in the second cycle is 800 kg. The calculated risk index of exceeding the standard for sulfur dioxide is 1, exceeding the preset risk index. At this time, it is determined that there is a risk of exceeding the standard for sulfur dioxide, and the production and sewage treatment equipment that may cause exceeding the standard are continuously located. In the mapping relationship table, the sulfur dioxide emission is associated with the following equipment: Production equipment group A: High-temperature reaction furnace, which generates a large amount of sulfur dioxide during the main production process. Sewage treatment equipment group B: Exhaust gas treatment tower, which is responsible for purifying the sulfur dioxide discharged from the reaction furnace. By matching these equipment groups and sending them to the first enterprise, it is recommended to focus on checking the working status of the high-temperature reaction furnace and the operating efficiency of the exhaust gas treatment tower to avoid exceeding the standard.

[0040] Furthermore, the present application further includes the following steps:

[0041] When the judgment result in the first cycle is exceeding the standard, a sewage discharge execution report of the first enterprise is generated in combination with the sewage discharge data of the first enterprise in the first cycle. Among them, the sewage discharge execution report of the first enterprise includes the statistical result of sewage discharge exceeding the standard and the reasons for exceeding the standard; the sewage discharge execution report of the first enterprise is pushed to the sewage discharge supervision associated terminal.

[0042] Specifically, the first-cycle judgment result is obtained by analyzing the pollution discharge data of the first enterprise in the first cycle, indicating whether the enterprise has exceeded the emission standard. When the result is exceeding the standard, a detailed implementation report is further generated, which summarizes the pollution discharge over-standard statistical results and over-standard reasons of the enterprise in the first cycle. Among them, the pollution discharge over-standard statistical results can include the total discharge amount and over-standard pollutants, and the over-standard reasons can be located according to the first mapping table and the second mapping table, that is, the associated equipment group causing the over-standard is located. The pollution discharge supervision associated terminal is a monitoring system managed by relevant supervision departments or relevant institutions, which receives the pollution discharge data and reports from the enterprise, and will push the pollution discharge implementation report of the first enterprise to this terminal for supervisors to analyze and process. Taking a chemical enterprise as an example, the sulfur dioxide emission limit of this enterprise is 4t / a. After the end of the first cycle, it is analyzed that the cumulative sulfur dioxide emission of this enterprise is 1050kg, exceeding the emission limit, and the first-cycle judgment result is determined to be exceeding the standard, and a pollution discharge implementation report is generated in combination with the first-cycle pollution discharge data of the enterprise. Exemplarily, the pollution discharge implementation report of the first enterprise includes: pollutant type: sulfur dioxide; actual emission amount: 1050kg; emission limit: 1000kg; over-standard situation: exceeding the standard by 50kg. Supervisors can view the detailed data through the terminal and issue corresponding emission reduction early warnings to the first enterprise to assist the enterprise in avoiding the penalty risk of exceeding the permitted emission amount in the actual emission amount of the cycle year.

[0043] Furthermore, the present application further includes the following steps:

[0044] Call the trust monitoring module to perform a trust judgment on the first enterprise to generate a trust judgment result; verify the validity of the first-cycle enterprise pollution discharge data according to the trust judgment result; generate a pollution discharge monitoring anomaly reminder message according to the validity verification result and send it to the pollution discharge supervision associated terminal.

[0045] Specifically, the trust monitoring module is a tool for monitoring and evaluating the authenticity and consistency of an enterprise's pollutant discharge data. By analyzing the deviation between historical pollutant discharge data and current data, it determines whether the enterprise's pollutant discharge data is trustworthy. The trust judgment result is the result of the trust monitoring module's evaluation of the credibility of the first enterprise's pollutant discharge data. If the deviation of the data is large or there are anomalies, the trust judgment result will show as failed, indicating that there may be problems with the data. The validity verification is based on the trust judgment result and further analyzes the pollutant discharge data monitored by the first enterprise during the first period to verify whether it conforms to logic and the actual discharge situation, ensuring the accuracy of the data. Once the validity verification fails, a pollutant discharge monitoring anomaly reminder message is generated and sent to the pollutant discharge supervision associated terminal. Supervisors can view the pollutant discharge monitoring anomaly reminder message through the terminal and then decide whether to conduct an on-site inspection of the first enterprise or re-verify the data to ensure the authenticity of the enterprise's pollutant discharge data and prevent environmental protection compliance risks caused by data tampering or equipment failures.

[0046] Furthermore, the present application further includes the following steps:

[0047] The trust monitoring module includes a trust monitoring database. Among them, the trust monitoring database includes deviation characteristic values of self-pollutant discharge data and measured pollutant discharge data at multiple progressive time nodes, and the trust monitoring database is connected to the pollutant discharge supervision associated terminal and is updated according to a preset cycle; traverse the trust monitoring database to obtain the trust anomaly node closest to the first period, where the trust anomaly node refers to a node whose deviation characteristic value is not within the preset deviation range; identify the number of trust nodes between the trust anomaly node and the first period. When the number of trust nodes is greater than the preset number, the trust judgment result is passed; otherwise, it is not passed.

[0048] Specifically, during the execution of the trust judgment process, the trust monitoring module will verify the trust of the sewage discharge data based on the content of the trust monitoring database. The trust monitoring database records the deviation characteristic values between the self-sewage monitoring data and the actual monitoring data of the first enterprise at multiple changing time nodes. The changing time nodes refer to the self-sewage monitoring data and the actual monitoring data collected in different time periods, and these data are regularly recorded as the basis for subsequent trust verification. The deviation characteristic value is the difference value between the self-sewage monitoring data and the actual monitoring data, which is used to measure the credibility of the data. If the deviation value exceeds the preset range, the data is considered abnormal. The trust abnormal node refers to the time node when the deviation characteristic value is not within the reasonable range, and these nodes indicate that the data of the first enterprise may be abnormal or inconsistent. For example, the sulfur dioxide emission data of an enterprise is regularly recorded in the trust monitoring database. In the past year, the self-reported data and the measured data of the enterprise are collected once a month, and the deviation characteristic values are recorded. Normally, the deviation between the self-reported sulfur dioxide emission and the measured value is controlled within ±5%. The deviations in May, July, and September of a certain year are 8%, 12%, and 15% respectively, all exceeding the preset deviation range, and these nodes are marked as trust abnormal nodes

[0049] When analyzing the data of the first cycle, traverse the trust monitoring database and obtain the trust abnormal node closest to the time corresponding to the enterprise sewage discharge data of the first cycle, such as October of the past year. At this time, calculate the number of trust nodes between the trust abnormal node and the time corresponding to the enterprise sewage discharge data of the first cycle (that is, the number of nodes that do not exceed the deviation range). If the number of trust nodes is greater than the preset threshold (for example, 8), it is determined that the enterprise passes the trust verification; otherwise, if the number of trust nodes is small, it is determined that the enterprise fails the trust verification. If the number of trust nodes is insufficient, set the trust judgment result to failed, and further trigger the data verification process to generate an abnormal reminder message. Through this process, the credibility of the enterprise sewage discharge data can be accurately evaluated, the authenticity of the data can be ensured, and a reliable basis can be provided for environmental protection supervision

[0050] In summary, the sewage discharge permit evaluation and management method based on intelligent analysis provided by this application has the following technical effects:

[0051] Obtain the first enterprise's first pollutant discharge permit information, where the first pollutant discharge permit information includes a first pollutant discharge type list, first-period pollutant discharge limit information, second-period pollutant discharge limit information, a first energy consumption list, first-period energy consumption limit information, and second-period energy consumption limit information; establish a communication connection with the first enterprise's first automatic monitoring device, receive and parse the automatic monitoring information in the first period in real time, and generate first-period enterprise pollutant discharge data and first-period enterprise energy consumption data; combine the first pollutant discharge type list, the first-period pollutant discharge limit information, the first energy consumption list, the first-period energy consumption limit information, the first-period enterprise pollutant discharge data, and the first-period enterprise energy consumption data to judge whether there is an excessive pollutant discharge, and generate a first-period judgment result; when the first-period judgment result is no excessive discharge, based on the first-period enterprise pollutant discharge data, the first-period enterprise energy consumption data, the second-period pollutant discharge limit information, and the second-period energy consumption limit information, conduct a risk prediction of excessive pollution discharge and an energy consumption prediction in the second period, and generate an excessive discharge risk indicator; give a reminder of excessive pollutant discharge to the first enterprise according to the excessive discharge risk indicator. By monitoring and analyzing the enterprise's pollutant discharge data in real time, combining with the pollutant discharge permit information, intelligently judge the situation of excessive pollutant discharge, conduct a risk prediction of excessive discharge in the next period, generate an excessive discharge risk indicator, and give a reminder of excessive pollutant discharge, which helps the enterprise take measures in advance to prevent future excessive pollutant discharge, achieving the technical effect of timely supervision and reminding of excessive discharge.

[0052] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0053] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A pollutant discharge permit evaluation and management method based on intelligent analysis, characterized in that: include: Obtaining first pollutant discharge permit information of a first enterprise, wherein the first pollutant discharge permit information includes a first pollutant discharge type list, first cycle pollutant discharge limit information, second cycle pollutant discharge limit information, a first energy consumption list, first cycle energy consumption limit information, and second cycle energy consumption limit information; Establishing a communication connection with a first automatic monitoring device of a first enterprise, receiving and analyzing the automatic monitoring information in a first period in real time, and generating pollution discharge data of the enterprise in the first period and energy consumption data of the enterprise in the first period; Combine the first pollution type list, the first period pollution limit information, the first energy consumption list, the first period energy consumption limit information, the first period enterprise pollution data and the first period enterprise energy consumption data to determine if pollution discharge exceeds the standard, and generate a first period judgment result; When the judgment result of the first period is that the standard is not exceeded, based on the pollution discharge data of the enterprise in the first period, the energy consumption data of the enterprise in the first period, the pollution discharge limit information of the second period, and the energy consumption limit information of the second period, the pollution discharge risk exceeding standard and the energy consumption forecast in the second period are performed to generate a risk indicator exceeding standard; The first enterprise is reminded of excessive pollution discharge based on the excessive risk index.

2. The method for evaluating and managing pollutant discharge permits based on intelligent analysis according to claim 1, characterized in that: Also includes: When the judgment result of the first period is that the pollution discharge exceeds the standard, a first enterprise pollution discharge implementation report is generated in combination with the pollution discharge data of the enterprise in the first period, wherein the first enterprise pollution discharge implementation report includes the statistical results of the pollution discharge exceeding the standard and the reasons for the exceeding of the standard; The pollution discharge implementation report of the first enterprise is pushed to the pollution discharge supervision associated terminal.

3. The method for evaluating and managing pollutant discharge permits based on intelligent analysis according to claim 1, characterized in that: The first automatic monitoring equipment includes an exhaust gas monitoring module, a wastewater monitoring module, a noise monitoring module, a solid waste monitoring module and an energy consumption monitoring device.

4. The method for evaluating and managing pollutant discharge permits based on intelligent analysis according to claim 3, characterized in that: Based on the pollution discharge data of the first period, the energy consumption data of the first period, the pollution discharge limit information of the second period, and the energy consumption limit information of the second period, the pollution discharge exceeding standard risk prediction and energy consumption prediction in the second period are performed to generate the exceeding standard risk index, including: Based on the first pollution type list, connect to the data sharing platform to collect the historical pollution execution time series and historical energy consumption monitoring time series of the first enterprise; Based on the long-short time series memory network, the large-time zone continuous pollution discharge prediction branch is trained with the historical pollution discharge execution time series, and the large-time zone energy consumption prediction branch is trained with the historical energy consumption monitoring time series, and the large-time zone continuous pollution discharge prediction branch and the large-time zone energy consumption prediction branch are integrated and connected to generate a prediction model; Inputting the pollution emission data of the enterprise in the first period, the energy consumption data of the enterprise in the first period and the second period into the prediction model to generate pollution emission prediction information for the second period and energy consumption prediction information for the second period; The pollution emission forecast information of the second cycle is compared with the pollution emission limit information of the second cycle, and the energy consumption limit information of the second cycle is compared with the energy consumption forecast information of the second cycle to generate the risk indicator of exceeding the standard.

5. The method for evaluating and managing pollutant discharge permits based on intelligent analysis according to claim 4, characterized in that: Based on the long-short time series memory network, the continuous pollution discharge prediction branch of the time zone is trained with the historical pollution discharge execution time series, including: Randomly dividing the historical sewage discharge execution time series into large and small continuous time zones to generate multiple time zone segmentation results; Based on the long short-term temporal memory network, the large and small time zone continuous pollution discharge prediction branch is trained with the multiple time zone segmentation results.

6. The method for evaluating and managing pollutant discharge permits based on intelligent analysis according to claim 1, characterized in that: Providing a reminder of excessive discharge of pollutants to the first enterprise according to the excessive risk indicator, including: If the risk index of exceeding the standard is greater than the preset risk index, the pollutants exceeding the standard are located according to the pollution emission prediction information of the second period and the pollution emission limit information of the second period, and the types of energy consumption exceeding the standard are located according to the energy consumption prediction information of the second period and the energy consumption limit information of the second period; Establishing a first mapping relationship table between the production equipment, sewage treatment equipment and discharged pollutants of the first enterprise, and a second mapping relationship table corresponding to energy consumption types; Input the pollutants exceeding the standard into the first mapping relationship table, input the energy consumption types exceeding the standard into the second mapping relationship table, and locate the associated equipment group; The second-cycle pollution discharge forecast information, the second-cycle energy consumption forecast information and the associated equipment group are sent to the first enterprise for early warning.

7. The method for evaluating and managing pollutant discharge permits based on intelligent analysis according to claim 1, characterized in that: Before receiving the automatic monitoring information of the first cycle in real time, it also includes: Calling a trust monitoring module to perform a trust judgment on the first enterprise and generate a trust judgment result; Verifying the validity of the pollution discharge data of the enterprise in the first period according to the trust judgment result; Generate pollution monitoring abnormality reminder information based on the effectiveness verification results and send it to the pollution monitoring associated terminal.

8. The method for evaluating and managing pollutant discharge permits based on intelligent analysis according to claim 7, characterized in that: Calling a trust monitoring module to perform a trust judgment on the first enterprise and generating a trust judgment result includes: The trust monitoring module includes a trust monitoring database, wherein the trust monitoring database includes deviation characteristic values ​​of self-discharge monitoring data and measured discharge data at multiple time nodes, and the trust monitoring database is connected to the discharge supervision associated terminal and updated according to a preset period; Traversing the trust monitoring database to obtain the trust abnormal node closest to the first cycle, wherein the trust abnormal node refers to a node whose deviation characteristic value is not within a preset deviation range; The number of trusted nodes between the trusted abnormal node and the first cycle is identified. When the number of trusted nodes is greater than a preset number, the trust judgment result is passed, otherwise, it is failed.

Images