Sewage tracing method and device, electronic equipment and storage medium

Abstract

The invention provides a sewage traceability method and device, electronic equipment and a storage medium, and relates to the technical field of sewage traceability, and the method comprises the steps: obtaining an abnormal water sample of a target monitoring point and a three-dimensional fluorescence spectrum of the abnormal water sample, and obtaining flow time sequence data of an enterprise discharge port in an associated region; analyzing the three-dimensional fluorescence spectrum of the abnormal water sample, and identifying the pollution type; performing space-time analysis based on the municipal pipe network topological structure and the flow time sequence data, and determining contribution degree weights of the discharge ports of the enterprises in the abnormal time period of the abnormal water samples; and determining the responsibility score of each enterprise by using a decision model in combination with the pollution type and the contribution degree weight, and generating a traceability result according to the responsibility score. In the mode, accurate and rapid source tracing and responsibility quantification of the pollution source are realized, the supervision efficiency is remarkably improved, and the system layout cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of wastewater source tracing technology, and in particular to a wastewater source tracing method, apparatus, electronic device, and storage medium. Background Technology

[0002] The core of water environment pollution supervision lies in the effective monitoring and pollution source tracing of discharge outlets into rivers (seas), which mainly relies on online water quality sensors for routine indicator monitoring.

[0003] In related technologies, monitoring only water quality is typically used, which can only detect anomalies but cannot pinpoint the source of pollution. Even when source tracing is possible, it is difficult to accurately locate the polluting company, and source tracing requires deploying expensive equipment at all potential discharge points, making it uneconomical. These shortcomings lead to low regulatory efficiency and make it difficult to meet the needs of precise enforcement and efficient governance. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a wastewater source tracing method, device, electronic device and storage medium, which realizes accurate and rapid source tracing and responsibility quantification of pollution sources, significantly improves regulatory efficiency and reduces system deployment costs.

[0005] In a first aspect, embodiments of the present invention provide a wastewater source tracing method, the method comprising: acquiring abnormal water samples and their three-dimensional fluorescence spectra at a target monitoring point, and acquiring flow time-series data of enterprise discharge outlets within the associated area; analyzing the three-dimensional fluorescence spectra of the abnormal water samples to identify pollution types; performing spatiotemporal analysis based on the municipal pipeline network topology and flow time-series data to determine the contribution weight of each enterprise discharge outlet during the abnormal period of the abnormal water samples; combining the pollution type and contribution weight, using a decision model to determine the responsibility score of each enterprise, and generating source tracing results based on the responsibility scores.

[0006] In a preferred embodiment of the present invention, the above-mentioned analysis of the three-dimensional fluorescence spectrum of abnormal water samples to identify the pollution type includes: preprocessing the three-dimensional fluorescence spectrum; the preprocessing includes: normalization and elimination of scattering interference; parallel factor analysis of the preprocessed three-dimensional fluorescence spectrum to extract feature vectors; inputting the feature vectors into a pre-trained support vector machine classification model to output the pollution type and confidence level.

[0007] In a preferred embodiment of the present invention, the above-mentioned support vector machine classification model is pre-trained in the following manner: a three-dimensional fluorescence spectral water quality fingerprint database containing multiple pollution sources is constructed; the spectral data in the three-dimensional fluorescence spectral water quality fingerprint database is preprocessed and subjected to parallel factor analysis to extract feature vectors; and the support vector machine model is trained using the feature vectors and the corresponding pollution type labels.

[0008] In a preferred embodiment of the present invention, the above-mentioned spatiotemporal analysis based on the municipal pipeline network topology and flow time series data to determine the contribution weight of each enterprise's discharge outlet during the abnormal period of the abnormal water sample includes: determining the sewage propagation path from each enterprise's discharge outlet to the target monitoring point based on the municipal pipeline network topology, and determining the theoretical propagation time along the sewage propagation path; extracting the actual abnormal occurrence time corresponding to the flow abnormality of each enterprise's discharge outlet before the abnormal time of the abnormal water sample from the flow time series data; determining the time matching degree between the actual abnormal occurrence time of the enterprise's discharge outlet and the expected discharge time for each enterprise's discharge outlet; and determining the flow abnormality weight of each enterprise's discharge outlet based on the time matching degree; wherein, the contribution weight is at least composed of the flow abnormality weight.

[0009] In a preferred embodiment of the present invention, the above-mentioned combination of pollution type and contribution weight to determine the responsibility score of each enterprise using a decision model includes: matching the registered pollution type of each enterprise in the database with the identified pollution type; and determining the responsibility score through a gradient boosting tree model based on the contribution weight, combined with the pollution type matching degree and historical emission behavior characteristics.

[0010] In a preferred embodiment of the present invention, enterprises within the aforementioned associated region are pre-classified into key management enterprises and general management enterprises. The pre-classification method is as follows: a comprehensive evaluation system including on-site indicators and operation and maintenance indicators is constructed using the analytic hierarchy process; the comprehensive score of each enterprise is determined based on the comprehensive evaluation system; and the enterprises are classified into key management enterprises and general management enterprises based on the comprehensive score and a pre-set ranking threshold.

[0011] In a preferred embodiment of the present invention, generating a tracing result based on the responsibility score includes: sorting the results in descending order of the responsibility score to generate a tracing ranking list as the tracing result.

[0012] Secondly, embodiments of the present invention also provide a wastewater source tracing device, comprising: a data acquisition module, used to acquire abnormal water samples and their three-dimensional fluorescence spectra at target monitoring points, and to acquire flow time-series data of enterprise discharge outlets within the associated area; a pollution type identification module, used to analyze the three-dimensional fluorescence spectra of abnormal water samples to identify pollution types; a spatiotemporal analysis module, used to perform spatiotemporal analysis based on the municipal pipeline network topology and flow time-series data to determine the contribution weight of each enterprise discharge outlet during the abnormal period of the abnormal water samples; and a source tracing result generation module, used to combine pollution types and contribution weights, use a decision model to determine the responsibility score of each enterprise, and generate source tracing results based on the responsibility scores.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the wastewater source tracing method of the first aspect described above.

[0014] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are invoked and executed by a processor, the computer-executable instructions cause the processor to implement the wastewater source tracing method of the first aspect described above.

[0015] The embodiments of the present invention bring the following beneficial effects: This invention provides a wastewater source tracing method, apparatus, electronic device, and storage medium. It acquires abnormal water samples and their three-dimensional fluorescence spectra from target monitoring points, and obtains flow time-series data of enterprise discharge outlets within the associated area. The three-dimensional fluorescence spectra of the abnormal water samples are analyzed to identify pollution types. Spatiotemporal analysis is performed based on the municipal pipeline network topology and flow time-series data to determine the contribution weight of each enterprise discharge outlet during the abnormal period of the abnormal water samples. Combining the pollution type and contribution weight, a decision model is used to determine the responsibility score of each enterprise, and source tracing results are generated based on the responsibility scores. This method achieves accurate and rapid source tracing and responsibility quantification, significantly improving regulatory efficiency and reducing system deployment costs.

[0016] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0017] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 A flowchart of a wastewater source tracing method provided in an embodiment of the present invention; Figure 2 A flowchart of another wastewater source tracing method provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a wastewater source tracing device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] The core of water environment pollution supervision lies in the effective monitoring and pollution source tracing of discharge outlets into rivers (seas), which mainly relies on online water quality sensors for routine indicator monitoring.

[0022] In related technologies, monitoring only water quality is typically used, which can only detect anomalies but cannot pinpoint the source of pollution. Even when source tracing is possible, it is difficult to accurately locate the polluting company, and source tracing requires deploying expensive equipment at all potential discharge points, making it uneconomical. These shortcomings lead to low regulatory efficiency and make it difficult to meet the needs of precise enforcement and efficient governance.

[0023] Based on this, the wastewater source tracing method, device, electronic equipment, and storage medium provided in this embodiment of the invention can acquire abnormal water samples and their three-dimensional fluorescence spectra from target monitoring points, and obtain flow time-series data of enterprise discharge outlets within the associated area. By analyzing the three-dimensional fluorescence spectra of the abnormal water samples, pollution types can be identified. Spatiotemporal analysis based on the municipal pipeline network topology and flow time-series data is performed to determine the contribution weight of each enterprise discharge outlet during the abnormal period of the abnormal water samples. Combining the pollution type and contribution weight, a decision model is used to determine the responsibility score of each enterprise, and source tracing results are generated based on the responsibility score. This method achieves accurate and rapid source tracing and responsibility quantification of pollution sources, significantly improving regulatory efficiency and reducing system deployment costs.

[0024] To facilitate understanding of this embodiment, a wastewater source tracing method disclosed in this embodiment of the invention will first be described in detail.

[0025] Example 1 This invention provides a wastewater source tracing method. Figure 1 This is a flowchart illustrating a wastewater source tracing method provided in an embodiment of the present invention. Figure 1 As shown, this wastewater source tracing method may include the following steps: Step S101: Obtain abnormal water samples and their three-dimensional fluorescence spectra at the target monitoring point, and obtain the flow time series data of enterprise discharge outlets in the associated area.

[0026] When the "Comprehensive Water Quality Monitoring Unit" deployed at the main discharge outlet of the river detects excessive levels of conventional indicators such as COD and ammonia nitrogen, the system determines it as "abnormal" and triggers two actions: First, it controls the "Automatic Abnormal Water Sample Preservation and Locking Unit" inside the unit to collect and retain the water sample at that moment. At the same time, its built-in "3D Fluorescent Water Quality Fingerprint Collector" scans the water sample to generate a 3D spectral map (EEMs) characterizing the types and concentrations of dissolved organic matter (DOM) in the water. Second, the system retrieves historical readings of "Ultrasonic Flow Meters" installed at the discharge outlets of all enterprises within the "related area" (usually referring to the drainage area that may flow into the upstream) in the pipeline network connected to the discharge outlet for a period of time before and after the incident (such as 6 hours before the incident) through the Internet of Things platform, forming "flow time series data". For example, if the target monitoring point alarms at 14:00, the system obtains the minute-by-minute flow data of upstream enterprises A, B, and C between 13:00 and 14:00.

[0027] Step S102: Analyze the three-dimensional fluorescence spectrum of the abnormal water sample to identify the type of pollution.

[0028] Specifically, analyzing the three-dimensional fluorescence spectra of abnormal water samples to identify pollution types can include: preprocessing the three-dimensional fluorescence spectra; preprocessing includes: normalization and elimination of scattering interference; parallel factor analysis of the preprocessed three-dimensional fluorescence spectra to extract feature vectors; and inputting the feature vectors into a pre-trained support vector machine classification model to output the pollution type and confidence level.

[0029] The raw EEMs data contain interference from instrument noise and scattered light caused by water sample turbidity, and therefore need to be cleaned.

[0030] "Normalization" typically refers to unifying the fluorescence intensity of the entire spectrum to a standard scale (such as standardizing based on the DOC concentration or Raman scattering peak area of ​​the water sample) to make the spectra of water samples with different concentrations comparable.

[0031] "Scattering interference cancellation" primarily addresses Rayleigh and Raman scattering bands, which can mask the true fluorescence peaks of organic compounds. Common methods include delonizing the data in the scattering region or using interpolation to replace the data. For example, blank subtraction can be used to correct for internal filtering effects, and a threshold can be set to identify the scattering region, which can then be filled in by interpolation with surrounding effective fluorescence data.

[0032] The preprocessed EEMs are still high-dimensional data (hundreds of excitation × emission wavelengths). Parallel factor analysis (PARAFAC) is a multidimensional decomposition model that can decompose complex EEMs into several independent mathematical factors representing different fluorescent components (such as humic acid-like, protein-like, etc.). "Extracting feature vectors" refers to extracting the relative intensity values ​​of these fluorescent components to form a low-dimensional vector (such as a 1×5-dimensional vector). For example, if a water sample's EEMs are decomposed into 5 components by PARAFAC with intensities of [120, 85, 40, 200, 15], this vector is the core "fingerprint" representing the fluorescence characteristics of the water sample.

[0033] The extracted feature vectors (e.g., [120, 85, 40, 200, 15]) are input into a pre-trained SVM model. This model has already learned tens of thousands of feature vectors and labels for various types of polluted water during training. The model calculates the probability that the vector belongs to each category. The output includes the main "pollution type" (e.g., "pharmaceutical wastewater") and a "confidence level" (e.g., 92.5%), indicating the model's level of certainty regarding this judgment.

[0034] The support vector machine classification model is pre-trained in the following way: a three-dimensional fluorescence spectral water quality fingerprint database containing multiple pollution sources is constructed; the spectral data in the three-dimensional fluorescence spectral water quality fingerprint database is preprocessed and parallel factor analysis is performed to extract feature vectors; the support vector model is trained using the feature vectors and the corresponding pollution type labels.

[0035] The database requires the systematic collection and labeling of a large number of real water sample EEMs data. "Multiple pollution sources" should cover all typical industries within the target regulatory area, such as papermaking, chemical, pharmaceutical, food, printing and dyeing, and domestic sewage, as well as possible mixed types. For example, the team has accumulated more than 26,000 spectral data sets, each clearly labeled with its collection source (e.g., "drainage outlet of XX pharmaceutical factory").

[0036] This involves repeatedly performing preprocessing and parallel factor analysis on all historical spectra in the database to generate a standardized feature vector for each sample. This is an offline, batch data preparation process to ensure consistent training data quality.

[0037] In this process, feature vectors (data) are paired with their pollution source labels (such as "food wastewater") and input into an SVM algorithm for learning. The model uses an optimization algorithm (such as Sequential Minimum Optimization, SMO) to find an optimal hyperplane that maximizes the separation of feature vectors from different categories in the feature space. After training, the model is able to predict the pollution type of a new water sample based on its feature vectors.

[0038] Step S103: Based on the municipal pipeline network topology and flow time series data, perform spatiotemporal analysis to determine the contribution weight of each enterprise's discharge outlet during the abnormal period of the abnormal water sample.

[0039] The "municipal pipeline network topology" refers to a GIS map that includes pipe connections, pipe diameters, slopes, and lengths. The system uses this structure to calculate the theoretical time (propagation time) required for wastewater to flow from each enterprise to the monitoring point. Combined with "flow time series data," the system checks whether any abnormal drainage behavior (such as a sudden increase in flow) occurred near the theoretical propagation time point calculated from the abnormal time point at the monitoring point.

[0040] For example, it theoretically takes 30 minutes for emissions from company A to travel to the monitoring point. If the monitoring point shows an anomaly at 14:00, then company A's "suspected emission time window" is approximately 13:30. If its flow data peaks at 13:28, its "contribution weight" will be very high; if the flow is stable during that period, the weight will be low.

[0041] Specifically, spatiotemporal analysis based on municipal pipeline network topology and flow time series data is used to determine the contribution weight of each enterprise's discharge outlet during the abnormal period of the abnormal water sample. This can include: determining the sewage propagation path from each enterprise's discharge outlet to the target monitoring point based on the municipal pipeline network topology, and determining the theoretical propagation time along the sewage propagation path; extracting the actual abnormal occurrence time corresponding to the flow abnormality at each enterprise's discharge outlet before the abnormal time of the abnormal water sample from the flow time series data; determining the time matching degree between the actual abnormal occurrence time and the expected discharge time for each enterprise's discharge outlet; and determining the flow abnormality weight of each enterprise's discharge outlet based on the time matching degree; wherein the contribution weight consists of at least the flow abnormality weight.

[0042] The pipeline network is abstracted as a graph structure, with nodes representing manholes / outlets and edges representing pipes. Graph theory algorithms (such as Dijkstra's algorithm) are used to calculate the shortest hydraulic path from each enterprise node to the monitoring point. The "theoretical propagation time" is estimated based on the non-full-pipe flow formula. ;in, : Pollution transmission time; l: Path length; D: Base flow velocity; Pipe diameter influencing factor; I: Slope; : Slope influencing factors.

[0043] This involves analyzing enterprise traffic curves and defining "anomaly" rules (such as traffic exceeding three standard deviations of the baseline average). The "actual anomaly occurrence time" refers to the timestamp corresponding to the first identified abnormal traffic peak. For example, if enterprise G's traffic suddenly increases from 10 m³ / h to 50 m³ / h at 13:15 and remains so for 5 minutes, then the "actual anomaly occurrence time" is extracted as 13:15.

[0044] Wherein, "expected emission time" = monitoring point anomaly time - the enterprise's theoretical propagation time. The "time matching degree" is usually calculated using mathematical methods such as the Gaussian kernel function to assess the closeness between the "actual anomaly occurrence time" and the "expected emission time".

[0045] Among them, "traffic anomaly weight" can be directly equal to time matching degree, or converted based on it. In more complex systems, contribution weight can be a weighted combination of traffic anomaly weight and other factors (such as enterprise size coefficient, distance decay coefficient).

[0046] Specifically, the traffic anomaly weight can be obtained using the following formula: ;in, Traffic anomaly weight; Tab: Monitoring point anomaly time; Flow meter malfunction time; The company may emit emissions at certain times. ; Standard deviation, which can be taken as 3600s.

[0047] Step S104: Combining pollution type and contribution weight, the responsibility score of each enterprise is determined using a decision model, and the source tracing results are generated based on the responsibility score.

[0048] For example, a company (D) might have a high spatiotemporal contribution weight, but if its registered industry type in the database is "mechanical processing," which doesn't match the identified "food wastewater" type, its responsibility score will be lowered. Conversely, a food company (E) might have a matching type and a high spatiotemporal weight, resulting in a high responsibility score. The decision-making model automatically learns this complex relationship and outputs a quantified ranking list of "responsibility scores." The final traceability report will list the most likely responsible company and its score, along with the basis (e.g., company E, responsibility score 95, type matching degree 98%, time matching weight 0.92).

[0049] Specifically, by combining pollution type and contribution weight, a decision model is used to determine the responsibility score of each enterprise. This may include: matching the registered pollution types of each enterprise in the database with the identified pollution types; and determining the responsibility score through a gradient boosting tree model based on contribution weight, combined with pollution type matching degree and historical emission behavior characteristics.

[0050] This includes querying a corporate information database to obtain the industry category of a company's registration or the type of wastewater it historically discharged. The data is then compared with the "pollution type" to calculate the similarity. For example, if the identified type is "dyeing and printing wastewater," and company J is registered as "textile dyeing and printing," the match is high; however, if company K is registered as "electronic components," the match is low or zero.

[0051] The "historical emission behavior characteristics" can include: the number of suspected illegal discharges recorded in the past month, previous environmental administrative penalty records, and the compliance rate of self-monitoring data. The Gradient Boosting Tree (GBDT) model uses contribution weights, type matching degree, and historical behavior characteristics as input features (X), and is trained using known truly responsible companies from a large number of historical pollution events as labels (y). When a new event occurs, the model integrates all these features and outputs a "responsibility score" of 0-100. For example, a company with a slightly lower spatiotemporal weight (0.7) but a perfect match in pollution type and a good historical record (no abnormal emission records) may still be given a moderately high responsibility score (e.g., 70 points) by the model; while another company with a high weight (0.9) but a completely mismatched type and frequent historical abnormal emissions may still be given a higher score (e.g., 65 points) due to the presence of repeated violation records, but lower than the former.

[0052] Specifically, generating tracing results based on responsibility scores can include: sorting the results in descending order of responsibility scores to generate a tracing ranking list as the tracing results.

[0053] The source tracing results are typically a ranking list with responsibility scores, ordered based on the companies' responsibility scores. Based on this list, the system can automatically classify primary and secondary suspects. Finally, all analysis processes, data, and conclusions are compiled into a structured electronic document, namely the source tracing report.

[0054] The wastewater source tracing method provided in this invention can acquire abnormal water samples and their three-dimensional fluorescence spectra from target monitoring points, and obtain flow time-series data of enterprise discharge outlets within the associated area. Analyzing the three-dimensional fluorescence spectra of the abnormal water samples identifies the pollution type. Based on the municipal pipeline network topology and flow time-series data, spatiotemporal analysis is performed to determine the contribution weight of each enterprise discharge outlet during the abnormal period of the abnormal water sample. Combining the pollution type and contribution weight, a decision model is used to determine the responsibility score of each enterprise, and source tracing results are generated based on the responsibility score. This method achieves accurate and rapid source tracing and responsibility quantification, significantly improving regulatory efficiency and reducing system deployment costs.

[0055] Example 2 This invention also provides another wastewater source tracing method; this method is implemented based on the method in the above embodiments; this method focuses on describing the specific implementation of pre-dividing key controlled enterprises and general controlled enterprises.

[0056] Figure 2 A flowchart of another wastewater source tracing method provided in an embodiment of the present invention is shown below. Figure 2As shown, enterprises within the associated region are pre-classified into key-controlled enterprises and general-controlled enterprises. The pre-classification method includes the following steps: Step S201: Use the analytic hierarchy process (AHP) to construct a comprehensive evaluation system that includes on-site indicators and operation and maintenance indicators.

[0057] Key controlled enterprises are those polluting entities within the regulatory area that are deemed to have high water environment risk according to the comprehensive evaluation system and require key monitoring. General controlled enterprises are those polluting entities within the regulatory area that are deemed to have relatively low water environment risk according to the comprehensive evaluation system and only require routine monitoring.

[0058] The process of obtaining the pre-defined key and general management enterprises may include: constructing a comprehensive evaluation system that includes on-site indicators and operation and maintenance indicators using the analytic hierarchy process; determining the comprehensive score of each enterprise based on the comprehensive evaluation system; and classifying enterprises into key and general management enterprises based on the comprehensive scores and pre-set ranking thresholds.

[0059] Among them, the Analytic Hierarchy Process (AHP) is a multi-criteria decision-making method that combines qualitative and quantitative approaches; on-site indicators may include: basic data, emergency management, initial rainwater interception facilities, full sewage collection, and full pipe network coverage; operation and maintenance indicators may include: sewage pipeline repair, full separation of rainwater and sewage, and water environment impact.

[0060] Specifically, the Analytic Hierarchy Process (AHP) is used to construct a comprehensive evaluation system that includes on-site indicators and operation and maintenance indicators, which can be described as follows: Determining the weights of the target layer: Determining the weights of each dimension and indicator requires calculating the maximum eigenvalue and eigenvector of the constructed judgment matrix A. Specifically, the "sum-product method" is used to calculate the maximum eigenvalue and eigenvector. The specific steps are as follows: Compare each determined indicator at the same level pairwise to obtain the relative weight between each individual evaluation indicator, and then construct the judgment matrix A: Where A is an n×n order positively reciprocal matrix, Elements at all levels and The importance levels are compared and scaled accordingly. Then, using Thomas Seti's "1-9 scale method," values ​​are assigned to each pair of different indicators. After weighting the indicators, a hierarchical structure table of the regional water environment assessment system for each unit is generated. See Table 1 below for details: Table 1:

[0061] Perform a consistency check: Normalize the judgment matrix A by dividing each factor of the matrix by the sum of its corresponding columns. Further calculation yields the normalized matrix A2: Then, the row summation of each row in the normalized matrix A2 is performed to obtain the eigenvector T, which is then normalized to obtain the normalized eigenvector. This leads to the normalized vector of the largest eigenvalue. : Since the judgment matrix needs to satisfy consistency, a consistency check is then performed on the judgment matrix A to obtain the largest eigenvalue of the judgment matrix. : The quantitative indicator CI, defined to measure inconsistency, is as follows: The smaller the CI value, the higher the consistency of the judgment matrix A, and the better it passes the test. The larger the CI value, the more inconsistent the judgment matrix A is. Specifically, for a judgment matrix A with perfect consistency, CI = 0. Next, the CR is calculated. The quantitative indicator CR, defined as a measure of inconsistency, is: The RI value is obtained by looking up a table. Find the corresponding matrix order for the appropriate consistency index RI. When CR = 0, it indicates that the matrix is ​​completely consistent, with extremely high consistency, and passes the consistency test. When CR < 0.1, it indicates that the matrix consistency is slightly poor but acceptable, and the consistency test is passed. When CR ≥ 0.1, it indicates that the matrix is ​​very inconsistent, with very poor consistency, and the consistency test is failed. Timely modifications should be made until CR < 0.1.

[0062] Following the steps outlined above, starting from the criteria level, the importance of each indicator within the same dimension is compared pairwise using scores from experts in the relevant field. A judgment matrix is ​​constructed, and the largest eigenvalue and corresponding standardized eigenvector of the judgment matrix are calculated using the "sum-product method." This determines the different weight proportions of indicators at each level within that dimension. A consistency check is then used to verify the validity of the results. Passing the consistency check indicates that the results meet the requirements; otherwise, they do not, and the scoring process needs to be repeated until the check is passed. After all indicator weights across all dimensions have passed the consistency check, a comprehensive evaluation system is further constructed by combining the indicator weights.

[0063] Step S202: Determine the overall score of each enterprise based on the comprehensive evaluation system.

[0064] The comprehensive evaluation system determines the overall score for each enterprise. Specifically, it involves using Thomas Seti's 1-9 scale to select 10 experts in relevant fields to assess the importance of each pair of different indicator factors. Multiple rounds of assessment are conducted through field research and questionnaires to reach a consensus on the importance percentages of different indicators across each dimension. Based on the assessment results, a criterion-level judgment matrix A is formed, and the weight percentage of each indicator is calculated. After obtaining the judgment matrix, the "sum-product method" is used to divide each factor in the matrix by the sum of its corresponding columns, resulting in a column normalized matrix A2. Row summation is then performed on each row of the normalized judgment matrix A2 to obtain the eigenvector T, which is then normalized to obtain the normalized vector of the largest eigenvalue. Next, a consistency check is performed, and the largest eigenvalue is calculated. Furthermore, by looking up the table to obtain RI, when CR=0, it indicates that the matrix is ​​completely consistent, and the consistency is extremely high, which can be verified through consistency testing to obtain the weights of each indicator in the criterion layer. The criterion layer may include: on-site indicators, operation and maintenance indicators, etc.

[0065] Similarly, the importance values ​​of each indicator in the indicator layer are assigned by 10 experts in related fields who score different indicator factors in pairs, resulting in two judgment matrices with different dimensions. The weight ratio of each dimension's detailed standard is calculated, and the results are obtained through consistency checks.

[0066] The identification of surface water environmental impact factors should be carried out in accordance with the requirements of the "Technical Guidelines for Environmental Impact Assessment: Surface Water Environment (HJ2.3-2018, replacing HJ / T2.3-93)" and should analyze the impact of each stage of the project on surface water environmental quality, including the construction phase, production and operation phase, and after the service period (which can be selected according to the project situation, the same below).

[0067] 1. The selection of evaluation factors for water pollution impact construction projects should meet the following requirements: a) In accordance with the technical guidelines for pollution source intensity accounting, identify pollution sources and water pollution factors of construction projects, and in combination with the current status of water environment quality in the water environment control unit or region where the construction project is located, screen factors for water environment status investigation and evaluation and impact prediction evaluation. b) Water pollutants involved in industry pollutant emission standards should be included as evaluation factors; c) Category I pollutants emitted from the workshop or workshop treatment facility outlets should be considered as evaluation factors; d) Water temperature should be considered as an evaluation factor; e) The main pollutants contained in non-point source pollution should be included as evaluation factors; f) Water quality exceeding standards or potential pollution factors (referring to water quality factors whose concentration values ​​have shown an upward trend in the past 3 years) discharged by the construction project should be included as evaluation factors. g) If the project may lead to eutrophication of the receiving water body, the evaluation factors should also include factors related to eutrophication (such as total phosphorus, total nitrogen, chlorophyll a, permanganate index, and transparency, etc. Among them, chlorophyll a is a factor that must be evaluated).

[0068] 2. Determination of evaluation level: The environmental impact assessment level for surface water of construction projects is determined comprehensively based on factors such as the type of impact, discharge method, discharge volume or impact status, current environmental quality of the receiving water body, and water environment protection objectives. For water pollution impact projects, the assessment level is mainly determined according to the wastewater discharge method and discharge volume, as shown in Table 2 below. Direct discharge projects are classified into Level I, Level II, and Level IIIA, determined based on the wastewater discharge volume and the pollution equivalent of water pollutants. Indirect discharge projects are classified as Level IIIB.

[0069] Table 2:

[0070] Note 1: The equivalent number of a water pollutant is equal to the annual discharge of the pollutant divided by the pollution equivalent value of the pollutant. To calculate the equivalent number of discharged pollutants, it is necessary to distinguish between Class I water pollutants and other classes of water pollutants. The total equivalent number of Class I pollutants should be calculated, and then the equivalent numbers of other classes of pollutants should be sorted from largest to smallest. The largest equivalent number should be used as the basis for determining the evaluation level of the construction project.

[0071] Note 2: Wastewater discharge volume is statistically calculated according to the wastewater types specified in the industry emission standards. For those without relevant industry emission standards, the volume should be reasonably determined through engineering analysis. The discharge volume of cooling water with high heat content should be included, while the discharge volume of indirect cooling water, circulating water and other clean wastewater with very little pollutant content may be excluded.

[0072] Note 3: If there are stockpiles (raw materials, fuels, waste residue, etc., and garbage dumps in the open) or dust pollution in the factory area, the initial rainwater and sewage should be included in the wastewater discharge volume, and the corresponding major pollutants should be included in the water pollution equivalent calculation.

[0073] Note 4: If a construction project directly discharges Class I pollutants, its evaluation level is Level I; if the pollutants directly discharged by a construction project are factors exceeding the standards of the receiving water body, the evaluation level shall not be lower than Level II.

[0074] Note 5: When the direct discharge of wastewater into the receiving water body affects protected areas such as drinking water source protection zones, drinking water intakes, habitats of key and rare aquatic organisms, and natural spawning grounds of important aquatic organisms, the evaluation level shall not be lower than Level II. If the discharge of warm wastewater into rivers, lakes, or reservoirs by the construction project causes changes in the water temperature of the receiving water body exceeding the requirements of the water environmental quality standards, and the evaluation area contains temperature-sensitive targets.

[0075] Note 6: When a construction project discharges warm wastewater into rivers or lakes, causing temperature changes in the receiving water body that exceed the requirements of the water environment quality standards, and the evaluation scope includes temperature-sensitive targets, the evaluation level is Level 1. Note 7: If a construction project uses seawater as a temperature-regulating medium and the discharge volume is >5 million m³ / d, the evaluation level is Level 1; if the discharge volume is <5 million m³ / d, the evaluation level is Level 2. For projects involving only clean wastewater discharge, if the discharged water quality meets the requirements of the receiving water body's water environment quality standards, the evaluation level is Level 3A.

[0076] Note 8: For projects that rely on existing emission outlets and do not involve new direct emissions of pollutants into the external environment, the evaluation level is determined as Level 3B, based on indirect emissions.

[0077] Note 9: For direct emission construction projects that rely on existing emission outlets and do not generate new pollutants in the external environment, the evaluation level is the same as that for indirect emission projects, and is classified as Level 3B.

[0078] The environmental impact assessment standards for surface water of enterprises discharging water outlets should be determined based on the requirements for water environment quality management within the assessment scope and the relevant pollutant discharge standards, specifying the applicable water environment quality standards and corresponding pollutant discharge standards for each assessment factor.

[0079] 3. Environmental Status Assessment: a) Based on the characteristics of the water environment impact of the construction project and the requirements for water environment quality management, select all or some of the following contents for evaluation: b) Water quality compliance status of water environment functional zones or water function zones and nearshore marine environment functional zones; c) Water quality compliance status at the discharge outlet section; d) Sediment contamination assessment; e) Evaluation of stable and compliant discharge based on wastewater treatment facilities.

[0080] Step S203: Based on the comprehensive score and the pre-set ranking threshold, enterprises are divided into key management enterprises and general management enterprises.

[0081] Among them, enterprises are divided into key management enterprises and general management enterprises based on comprehensive scores and pre-set ranking thresholds. Specifically, the ranking threshold can be set to 33%, and enterprises with comprehensive scores in the top 33% are key management enterprises, while those below 33% are general management enterprises.

[0082] Example 3 Corresponding to the above method embodiments, this invention provides a wastewater source tracing device. Figure 3 This is a schematic diagram of a wastewater source tracing device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the wastewater source tracing device may include: The data acquisition module 301 is used to acquire abnormal water samples and their three-dimensional fluorescence spectra at the target monitoring point, and to acquire the flow time series data of enterprise discharge outlets in the associated area.

[0083] The pollution type identification module 302 is used to analyze the three-dimensional fluorescence spectrum of abnormal water samples to identify the pollution type.

[0084] The spatiotemporal analysis module 303 is used to perform spatiotemporal analysis based on the municipal pipeline network topology and flow time series data to determine the contribution weight of each enterprise's discharge outlet during the abnormal period of abnormal water samples.

[0085] The source tracing result generation module 304 is used to combine pollution type and contribution weight, use a decision model to determine the responsibility score of each enterprise, and generate source tracing results based on the responsibility score.

[0086] The wastewater source tracing device provided in this invention can acquire abnormal water samples and their three-dimensional fluorescence spectra from target monitoring points, as well as the flow time-series data of enterprise discharge outlets within the associated area. Analyzing the three-dimensional fluorescence spectra of the abnormal water samples identifies the pollution type. Based on the municipal pipeline network topology and flow time-series data, spatiotemporal analysis is performed to determine the contribution weight of each enterprise discharge outlet during the abnormal period of the abnormal water sample. Combining the pollution type and contribution weight, a decision model is used to determine the responsibility score of each enterprise, and source tracing results are generated based on the responsibility score. This method achieves accurate and rapid source tracing and responsibility quantification of pollution sources, significantly improving regulatory efficiency and reducing system deployment costs.

[0087] In some embodiments, the pollution type identification module is further used to preprocess the three-dimensional fluorescence spectrum; the preprocessing includes: normalization and scattering interference elimination; parallel factor analysis of the preprocessed three-dimensional fluorescence spectrum to extract feature vectors; inputting the feature vectors into a pre-trained support vector machine classification model to output the pollution type and confidence level.

[0088] In some embodiments, the pollution type identification module is further configured to construct a three-dimensional fluorescence spectral water quality fingerprint database containing multiple pollution sources; preprocess the spectral data in the three-dimensional fluorescence spectral water quality fingerprint database and perform parallel factor analysis to extract feature vectors; and use the feature vectors and corresponding pollution type labels to train the support vector machine model.

[0089] In some embodiments, the spatiotemporal analysis module is further configured to determine the sewage propagation path from each enterprise outlet to the target monitoring point based on the municipal pipeline network topology, and determine the theoretical propagation time along the sewage propagation path; extract the actual anomaly occurrence time corresponding to the flow anomaly occurring at each enterprise outlet before the anomaly time of the abnormal water sample from the flow time series data; determine the time matching degree between the actual anomaly occurrence time and the expected discharge time of each enterprise outlet for each enterprise outlet; and determine the flow anomaly weight of each enterprise outlet based on the time matching degree; wherein the contribution weight is at least composed of the flow anomaly weight.

[0090] In some embodiments, the source tracing result generation module is also used to match the registered pollution types of each enterprise in the database with the identified pollution types; based on the contribution weight, combined with the pollution type matching degree and historical emission behavior characteristics, the responsibility score is determined through a gradient boosting tree model.

[0091] In some embodiments, the data acquisition module is further configured to construct a comprehensive evaluation system including on-site indicators and operation and maintenance indicators using the analytic hierarchy process; determine the comprehensive score of each enterprise based on the comprehensive evaluation system; and classify enterprises into key management enterprises and general management enterprises based on the comprehensive score and a pre-set ranking threshold.

[0092] In some embodiments, the tracing result generation module is further configured to sort the results in descending order of responsibility score and generate a tracing sort list as the tracing result.

[0093] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0094] Example 4 This invention also provides an electronic device for running the above-described wastewater source tracing method; see [link to previous document]. Figure 4 The diagram shows the structure of an electronic device, which includes a memory 400 and a processor 401. The memory 400 stores one or more computer instructions, which are executed by the processor 401 to implement the aforementioned wastewater source tracing method.

[0095] Furthermore, Figure 4 The electronic device shown also includes a bus 402 and a communication interface 403. The processor 401, the communication interface 403 and the memory 400 are connected via the bus 402.

[0096] The memory 400 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 403 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 402 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0097] Processor 401 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 401 or by instructions in software form. Processor 401 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 400, and processor 401 reads information from memory 400 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0098] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the above-described wastewater source tracing method. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0099] The computer program product for the wastewater source tracing method provided in this embodiment of the invention includes a computer-readable storage medium storing non-volatile program code executable by a processor. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0100] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0101] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0102] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0103] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0104] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0105] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for tracing the source of wastewater, characterized in that, The method includes: Obtain abnormal water samples from the target monitoring point and their three-dimensional fluorescence spectra, and obtain time-series flow data of enterprise discharge outlets within the associated area; The three-dimensional fluorescence spectrum of the abnormal water sample was analyzed to identify the type of pollution. Spatiotemporal analysis was performed based on the municipal pipeline network topology and the flow time series data to determine the contribution weight of each enterprise's discharge outlet during the abnormal period of the abnormal water sample. By combining the pollution type with the contribution weight, a decision model is used to determine the responsibility score of each enterprise, and source tracing results are generated based on the responsibility score.

2. The method according to claim 1, characterized in that, The analysis of the three-dimensional fluorescence spectrum of the abnormal water sample to identify the type of pollution includes: The three-dimensional fluorescence spectrum is preprocessed; the preprocessing includes: normalization and scattering interference elimination; Parallel factor analysis was performed on the preprocessed three-dimensional fluorescence spectra to extract the feature vectors; The feature vector is input into a pre-trained support vector machine classification model, which outputs the pollution type and confidence level.

3. The method according to claim 2, characterized in that, The support vector machine classification model is pre-trained in the following manner: Construct a three-dimensional fluorescence spectral water quality fingerprint database containing multiple pollution sources; The spectral data in the three-dimensional fluorescence spectroscopy water quality fingerprint database are preprocessed and subjected to parallel factor analysis to extract feature vectors. The support vector machine model is trained using the feature vectors and their corresponding pollution type labels.

4. The method according to claim 2, characterized in that, The spatiotemporal analysis based on the municipal pipeline network topology and the flow time series data determines the contribution weight of each enterprise's discharge outlet during the abnormal period of the abnormal water sample, including: Based on the municipal pipeline network topology, the sewage propagation path from each enterprise's discharge outlet to the target monitoring point is determined, and the theoretical propagation time along the sewage propagation path is determined. From the flow time series data, extract the actual time of occurrence of the abnormality corresponding to the flow abnormality at each enterprise's discharge outlet before the abnormal time of the abnormal water sample; For each enterprise's discharge outlet, determine the time matching degree between the actual time of the abnormality and the expected discharge time. Based on the time matching degree, the abnormal traffic weight of each enterprise's outlet is determined; The contribution weight is composed of at least the traffic anomaly weight.

5. The method according to claim 1, characterized in that, The process of combining the pollution type and the contribution weight, and using a decision model to determine the responsibility score of each enterprise, includes: Match the registered pollution types of each enterprise in the database with the identified pollution types; Based on the aforementioned contribution weights, and combined with pollution type matching degree and historical emission behavior characteristics, the responsibility score is determined through a gradient boosting tree model.

6. The method according to claim 1, characterized in that, Enterprises within the relevant region are pre-classified into key-controlled enterprises and general-controlled enterprises, and the pre-classification method is as follows: A comprehensive evaluation system including on-site indicators and operation and maintenance indicators was constructed using the analytic hierarchy process (AHP). The overall score for each enterprise is determined based on the aforementioned comprehensive evaluation system; Based on the comprehensive score and the pre-set ranking threshold, enterprises are divided into key management enterprises and general management enterprises.

7. The method according to claim 1, characterized in that, The step of generating the source tracing result based on the responsibility score includes: Sort the results in descending order of responsibility scores to generate a source tracing sort list as the source tracing result.

8. A wastewater source tracing device, characterized in that, The device includes: The data acquisition module is used to acquire abnormal water samples from the target monitoring point and the three-dimensional fluorescence spectrum of the abnormal water samples, and to acquire the flow time series data of enterprise discharge outlets in the associated area; The pollution type identification module is used to analyze the three-dimensional fluorescence spectrum of the abnormal water sample to identify the pollution type; The spatiotemporal analysis module is used to perform spatiotemporal analysis based on the municipal pipeline network topology and the flow time series data to determine the contribution weight of each enterprise's discharge outlet during the abnormal period of the abnormal water sample. The source tracing result generation module is used to combine the pollution type and the contribution weight, use a decision model to determine the responsibility score of each enterprise, and generate source tracing results based on the responsibility score.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the wastewater source tracing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the wastewater source tracing method of any one of claims 1 to 7.

Images