Pollution traceability analysis system and method based on sewage pipe network

Abstract

The invention relates to the technical field of sewage pipe networks, in particular to a pollution traceability analysis system and method based on a sewage pipe network, and the method comprises the following steps: S1, data collection: collecting the pollutant concentration in real time; s2, data preprocessing: preprocessing the collected pollutant concentration; s3, pollution source spatio-temporal change analysis: identifying a distribution mode and a change trend of pollutants, and determining an initial position and a diffusion direction of the pollution source; s4, identifying and tracking the pollution source: dynamically identifying and tracking the position of the pollution source and the diffusion path of the pollution source in the pipe network through a multi-dimensional spatial-temporal change analysis model based on the determined initial position and diffusion direction of the pollution source in combination with the real-time pollutant concentration, and updating the diffusion state and flow path of the pollution source in real time; according to the invention, the pollution problem of the sewage pipe network in a complex environment can be effectively solved, and an efficient pollution control and treatment strategy is provided in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage pipe networks, and particularly to a pollution source tracing analysis system and method based on sewage pipe networks. Background Art

[0002] With the rapid development of industrialization and urbanization, the construction scale of sewage pipe networks is expanding day by day, and the types and quantities of pollutants discharged are becoming increasingly complex. As an important infrastructure for urban pollution control, sewage pipe networks not only need to undertake the functions of drainage and pollutant transportation, but also need to effectively monitor the location of pollution sources and their diffusion paths to ensure the safety of the water environment. However, due to the characteristics of pollution sources such as dynamics, multi-sources, and concealment, the diffusion of pollutants in sewage pipe networks is often complex and difficult to predict. Traditional static monitoring and single-source tracing technologies have been difficult to meet the needs of modern environmental governance. Therefore, constructing a pollution source tracing method based on real-time data and dynamic analysis to improve the ability of pollution source location and diffusion prediction has become an important research direction in the current environmental monitoring field.

[0003] Currently, traditional pollution source tracing technologies mostly rely on single-point monitoring or manual sampling and analysis methods. This way is difficult to comprehensively reflect the spatio-temporal variation characteristics of pollutants in complex sewage pipe networks. In addition, many methods lack scientificity and systematicness in dealing with data noise and missing values, resulting in low-quality pollutant concentration data, thus affecting the accuracy and reliability of analysis. In terms of dynamic identification of pollution sources, existing technologies often only consider the static distribution of pollutant concentrations, fail to conduct dynamic analysis by combining the flow data and topological structure of sewage pipe networks, and lack the ability to track the diffusion path and trend of pollutants in real time. Especially in the scenario of multi-source pollution, traditional methods are difficult to cope with the dynamic changes of pollution sources and cannot accurately predict the future diffusion direction of pollution sources, affecting the timeliness and efficiency of pollution control.

[0004] In view of the problems existing in the prior art in pollution source tracing, such as incomplete monitoring, low data quality, and insufficient dynamic tracking ability, the present invention provides a pollution source tracing analysis system and method based on sewage pipe networks, which can effectively improve the accuracy and timeliness of pollution source tracing and provide scientific and reliable technical support for pollution control and environmental governance of sewage pipe networks. Summary of the Invention

[0005] The present invention provides a pollution source tracing analysis system and method based on sewage pipe networks.

[0006] A pollution source tracing analysis method based on sewage pipe networks includes the following steps: S1, data collection: Sensors are arranged at multiple nodes of the sewage pipe network to collect pollutant concentrations in real time, and the time stamps of the pollutant concentrations and the corresponding spatial positions are recorded; S2, Data preprocessing: Preprocess the collected pollutant concentrations, including denoising and missing value handling; S3, Spatiotemporal variation analysis of pollution sources: Based on the preprocessed pollutant concentrations, use a spatiotemporal analysis model to analyze the spatiotemporal variations of pollutant concentrations, identify the distribution patterns and change trends of pollutants, and determine the preliminary locations and diffusion directions of pollution sources; S4, Identification and tracking of pollution sources: Based on the determined preliminary locations and diffusion directions of pollution sources, combined with real-time pollutant concentrations, through a multi-dimensional spatiotemporal variation analysis model, dynamically identify and track the locations of pollution sources and their diffusion paths in the pipe network, and update the diffusion states and flow paths of pollution sources in real time.

[0007] Optionally, the data collection in S1 includes: S11, Select sensor deployment nodes: Conduct on-site surveys at multiple nodes of the sewage pipe network, select key monitoring areas to deploy sensors, and the key monitoring areas include the inlet, outlet of the pipe network, and intermediate nodes with pollutant emissions; S12, Sensor installation: Install pollutant concentration sensors at the selected nodes; S13, Real-time data collection: After the sensors are installed, monitor the pollutant concentrations in real time. When collecting pollutant concentrations, automatically add timestamps to each group of pollutant concentrations and bind them to the corresponding spatial locations (pipe network node numbers or GPS coordinates).

[0008] Optionally, the data preprocessing in S2 includes: S21, Denoising processing: Use wavelet transform to denoise the collected pollutant concentrations; S22, Missing value handling: For missing values, use linear interpolation to fill them.

[0009] Optionally, the spatiotemporal variation analysis of pollution sources in S3 includes: S31, Spatiotemporal pattern recognition: Based on the preprocessed pollutant concentrations, use a spatiotemporal clustering algorithm to cluster the pollutant concentrations, identify the distribution patterns of pollutants at different time periods and spatial locations, and analyze the change trends of pollutant concentrations through time series analysis methods to identify the change trends of pollutant concentrations; S32, Preliminary pollution source location and diffusion direction determination: Based on the identified pollutant distribution patterns and change trends, combined with the topological structure and flow data of the sewage pipe network, determine the preliminary locations and diffusion directions of pollution sources.

[0010] Optionally, the spatiotemporal pattern recognition in S31 includes: S311, Spatiotemporal clustering analysis: Use the spatiotemporal K-means clustering algorithm to perform clustering analysis on the preprocessed pollutant concentrations to identify the aggregation intervals of pollutants in space and time; S312, Time series analysis: Based on the results of spatiotemporal clustering, use the moving average method to analyze the changing trend of pollutant concentrations.

[0011] Optionally, the preliminary pollution source location and diffusion direction determination in S32 include: S321, Calculate the pollutant concentration gradient: Use the identified pollutant concentration distribution pattern to calculate the gradient of pollutant concentration in space ; S322, Location in combination with the pipe network topology: According to the topology of the sewage pipe network, that is, the pipe network nodes and their connection relationships, by calculating the relationship between the pollutant concentration gradient and the pipe network flow, determine the location of the pollution source; S323, Diffusion direction analysis: According to the preliminary location of the pollution source and the concentration gradient, combined with the flow data of the pipe network, calculate the diffusion direction intensity of the pollutant , and determine the diffusion direction of the pollution source.

[0012] Optionally, the pollution source identification and tracking in S4 include: S41, Dynamic identification and location of the pollution source: Based on the preliminary location and diffusion direction of the pollution source, combined with the real-time collected pollutant concentrations, use a multi-dimensional spatiotemporal analysis model to dynamically identify and locate the pollution source; S42, Tracking and updating of the pollution source diffusion path: Based on the real-time data of real-time pollutant concentrations, dynamically track the diffusion path of the pollution source, and combined with the topology and flow data of the sewage pipe network, predict the diffusion trend and path of the pollutant, and adjust the diffusion direction and path of the pollution source in real time by gradually updating the diffusion state of the pollution source.

[0013] Optionally, the multi-dimensional spatiotemporal analysis model in S41 uses a grid-based diffusion model, and the grid-based diffusion model includes: S411, Grid-based area division: Divide the sewage pipe network into multiple small areas (grids), and each grid represents a node or area in the pipe network; S412, Application of the pollution source location and diffusion direction: Based on the determined preliminary location and diffusion direction of the pollution source, calculate the initial pollutant concentration for each grid, that is, the initial pollutant concentration is the diffusion direction intensity of the pollutant at this location ; S413, Pollutant Diffusion Simulation: Use the diffusion equation to simulate the diffusion of pollutants between each grid cell. By calculating the updated value of the pollutant concentration in each grid cell, simulate the spatial diffusion process of pollutants, and dynamically identify and locate the pollution source.

[0014] Optionally, the pollution source diffusion path tracking and updating in S42 includes: S421, Dynamic Diffusion Path Tracking: Use real-time pollutant concentration data and pipe network flow data to dynamically calculate the diffusion direction intensity of pollutants from the current grid position ; ; S422, Diffusion Trend and Path Prediction: Use the diffusion direction intensity obtained by dynamic tracking to predict the diffusion trend and path of pollutants at future times; S423, Real-time Adjustment of Diffusion Direction and Path: By continuously updating the concentration state of pollutants, and the diffusion direction intensity , gradually optimize the diffusion direction and future path of pollutants.

[0015] A sewage pipe network pollution source tracing analysis system for implementing the above-mentioned sewage pipe network pollution source tracing analysis method, including the following modules: Data Acquisition Module: Install sensors at multiple nodes of the sewage pipe network to collect pollutant concentration data in real time, and record the time stamps of pollutant concentrations and their corresponding spatial positions; Data Preprocessing Module: Preprocess the collected pollutant concentration data, including denoising and missing value processing; Pollution Source Spatiotemporal Variation Analysis Module: Based on the preprocessed pollutant concentration data, use a spatiotemporal analysis model to analyze the spatiotemporal variation of pollutant concentrations, identify the distribution pattern and variation trend of pollutants, and determine the preliminary location and diffusion direction of the pollution source; Pollution Source Identification and Tracking Module: Based on the preliminary location and diffusion direction of the pollution source, combined with the real-time collected pollutant concentration data, through a multi-dimensional spatiotemporal variation analysis model, dynamically identify and track the location of the pollution source and its diffusion path in the sewage pipe network, and update the diffusion state and flow path of the pollution source in real time.

[0016] Advantages of the present invention: In the present invention, by constructing a complete method chain from data collection, data preprocessing to the spatio-temporal variation analysis, dynamic identification and tracking of pollution sources, the accurate tracing and real-time dynamic monitoring of pollution sources in sewage pipe networks are realized. In data collection, by deploying sensors to monitor pollutant concentrations and combining timestamp and spatial location information, the accuracy and real-time nature of the data are ensured. In data preprocessing, wavelet transform is used for denoising and linear interpolation is used to fill in missing values, improving the quality and continuity of the data, providing a reliable basis for subsequent analysis, ensuring the comprehensiveness of pollution source tracing and the accuracy of data processing, and avoiding errors caused by data missing or noise interference in traditional methods.

[0017] In the present invention, through the spatio-temporal variation analysis and identification and tracking of pollution sources, the dynamic identification and real-time update of pollution sources are realized. Based on the spatio-temporal clustering analysis of pollutant concentrations, the spatial distribution patterns and changing trends of pollutants can be accurately captured, and combined with the topological structure and flow data of the pipe network, the preliminary location and diffusion direction of pollution sources can be dynamically inferred. In addition, through the multi-dimensional spatio-temporal analysis model and the grid-based diffusion model, the diffusion paths of pollution sources are tracked in real time, and the concentration distribution status of pollutants is updated, effectively coping with the dynamic changes of pollutant diffusion in complex sewage pipe networks, significantly improving the timeliness of pollution source location and the dynamic tracking ability, and providing a scientific basis for the dynamic monitoring of pollutant diffusion.

[0018] In the present invention, through the dynamic diffusion path tracking and prediction, combined with pollutant concentration gradients and pipe network flow data, not only can the location and diffusion status of current pollution sources be accurately identified, but also the future diffusion trends of pollutants can be predicted. By adjusting the diffusion path and direction in real time, the inference accuracy of pollutant propagation trends is optimized, significantly improving the efficiency and accuracy of pollution source tracing. Combining the grid-based diffusion model and path prediction method, pollution problems in complex sewage pipe network environments can be effectively handled, and efficient pollution control and treatment strategies can be provided in real time. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a schematic flow diagram of the analysis method according to an embodiment of the present invention; Figure 2 It is a schematic diagram of the system function modules according to an embodiment of the present invention. Detailed Embodiments

[0021] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the accompanying drawings are only for more specifically describing the embodiments, and are not intended to specifically limit the present invention.

[0022] It should be noted that in the specification, the mention of "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicates that the described embodiments may include specific features, structures or characteristics, but not necessarily every embodiment includes such specific features, structures or characteristics. Additionally, when combining embodiments to describe specific features, structures or characteristics, implementing such features, structures or characteristics in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0023] Generally, terms can be understood at least in part from their use in the context. For example, at least in part depending on the context, the term "one or more" as used herein can be used to describe any feature, structure or characteristic in a singular sense, or can be used to describe a combination of features, structures or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily aiming to convey a set of exclusive factors, but rather, at least in part depending on the context, allowing for the existence of other factors that may not be explicitly described.

[0024] As Figure 1 shown, a pollution source tracing and analysis method based on a sewage pipe network includes the following steps: S1, Data collection: Sensors are deployed at multiple nodes of the sewage pipe network to collect pollutant concentrations in real time, and the time stamps of the pollutant concentrations and the corresponding spatial positions are recorded. S2, Data preprocessing: The collected pollutant concentrations are preprocessed, including denoising and missing value processing. S3, Spatiotemporal variation analysis of pollution sources: Based on the preprocessed pollutant concentrations, a spatiotemporal analysis model is used to analyze the spatiotemporal variations of the pollutant concentrations, identify the distribution patterns and variation trends of the pollutants, and determine the preliminary positions and diffusion directions of the pollution sources. S4, Pollution source identification and tracking: Based on the determined preliminary positions and diffusion directions of the pollution sources, combined with the real-time pollutant concentrations, through a multi-dimensional spatiotemporal variation analysis model, the positions of the pollution sources and their diffusion paths in the pipe network are dynamically identified and tracked, and the diffusion states and flow paths of the pollution sources are updated in real time. Through the above, a comprehensive analysis from data collection to pollution source tracking is achieved, which can monitor the changes of pollutants in the sewage network in real time, dynamically identify and track the location of pollution sources and their diffusion paths, effectively improve the accuracy and response speed of pollution source positioning, and through spatio-temporal analysis and multi-dimensional data fusion, can accurately predict the change trend of pollution sources, optimize pollution remediation strategies, and provide more efficient decision-making support.

[0025] The data collection in S1 includes: S11, select sensor layout nodes: conduct on-site surveys at multiple nodes of the sewage network, select key monitoring areas to deploy sensors, and the key monitoring areas include the inlet, outlet of the network, and intermediate nodes with pollutant emissions; S12, sensor installation: install pollutant concentration sensors at the selected nodes; S13, real-time data collection: after the sensors are installed, monitor the pollutant concentration in real time, and when collecting the pollutant concentration, automatically add a timestamp to each group of pollutant concentration and bind it to the corresponding spatial location (sewage network node number or GPS coordinates) to ensure that each piece of data can accurately correspond to the time and location of its collection; Through the above, the water quality changes in the sewage network can be comprehensively and accurately monitored. By focusing on monitoring the inlet, outlet of the network and intermediate nodes where pollution sources may exist, it is ensured that the data can truly reflect the pollution status of the entire network. Each piece of data collected has a timestamp and a spatial location label, ensuring the timeliness and spatial positioning accuracy of the data, not only improving the reliability and accuracy of the data, but also ensuring the comprehensiveness and real-time nature of pollution monitoring, providing strong support for timely discovery and repair of pollution sources.

[0026] The data preprocessing in S2 includes: S21, denoising processing: use wavelet transform to perform denoising processing on the collected pollutant concentration, which can effectively remove the high-frequency noise in the data while retaining the main features of the signal, expressed as: ; Among them, is the original pollutant concentration, represents the wavelet transform of the pollutant concentration to obtain its wavelet coefficients, represents the inverse transform of the wavelet coefficients, is the denoised pollutant concentration; S22, missing value processing: for missing values, use linear interpolation method to fill them. Suppose the pollutant concentration at a certain moment is missing, and it is estimated through the pollutant concentration at known moments, expressed as: ; Among them, is the pollutant concentration at the time point where the missing value is located, and are respectively the known pollutant concentrations at time points and ; is the time difference between the missing value position and the previous known value, is the time difference between known time points; Through the above content, the quality of pollutant concentration is improved. The denoising process effectively removes the high-frequency noise that may appear during the acquisition process, ensures the stability and accuracy of the data, avoids the analysis errors caused by noise interference, and the missing value filling restores the incomplete data through the interpolation method, avoids the analysis deviation caused by missing values, and ensures the continuity and integrity of the data.

[0027] The spatio-temporal variation analysis of pollution sources in S3 includes: S31, Spatio-temporal pattern recognition: Based on the preprocessed pollutant concentration, use the spatio-temporal clustering algorithm to cluster the pollutant concentration, identify the distribution patterns of pollutants at different time periods and spatial positions, and analyze the change trend of pollutant concentration through the time series analysis method to identify the change trend of pollutant concentration; S32, Preliminary pollution source location and diffusion direction determination: Based on the identified pollutant distribution patterns and change trends, combined with the topological structure and flow data of the sewage pipe network, determine the preliminary location and diffusion direction of the pollution source; Through the above content, it is possible to accurately capture the distribution characteristics and change laws of pollutants in different times and spaces, not only improve the accuracy and reliability of pollution source identification, but also dynamically track the diffusion path of pollutants, update the status information of pollution sources in a timely manner, combined with the topological structure and flow data of the sewage pipe network, the analysis process is more scientific and systematic, and ensures the accuracy of pollution source location.

[0028] The spatio-temporal pattern recognition in S31 includes: S311, Spatio-temporal clustering analysis: Use the spatio-temporal K-means clustering algorithm to perform clustering analysis on the preprocessed pollutant concentration to identify the aggregation intervals of pollutants in space and time; The spatio-temporal K-means clustering algorithm specifically includes: S3111, Select spatio-temporal data set: Select the pollutant concentrations at each node of the sewage pipe network collected to form a spatio-temporal data set Among them, is the spatial coordinate (sewage pipe network node position) of the th data point, is the time stamp of this data point, is the pollutant concentration of this data point; S3112, Select the initial cluster centers ( clusters): Randomly select data points as the center points of the initial clusters, denoted as (cluster centers); S3113, Calculate the spatio-temporal distance: Calculate the spatio-temporal distance between data points to measure the similarity of data points. Given two points and , calculate their spatio-temporal distance , expressed as: ; where, and are spatial coordinates, and are timestamps, and are the corresponding pollutant concentrations respectively, is the time normalization coefficient; S3114, Assign data points to the nearest cluster center: According to the calculated spatio-temporal distance, assign each data point to the cluster where its nearest cluster center is located. That is, for each data point , find the cluster center that makes the smallest, and then assign it to this cluster, expressed as: ; where, is the cluster to which the data point is assigned, is the cluster center; S3115, Update the cluster center: After each assignment of data points, update the cluster center. The new cluster center is the weighted average of all points in the cluster, expressed as: ; where, is the number of samples in the cluster , is the data point assigned to the cluster ; S3116, Judge convergence and stop: Repeat steps S3113, S3114, and S3115 until the cluster centers no longer change significantly or reach the preset maximum number of iterations. At this time, the clustering process ends, and the finally obtained cluster centers are the spatio-temporal distribution patterns of pollutants; S312, Time series analysis: Based on the results of spatio-temporal clustering, use the moving average method to analyze the change trend of pollutant concentration, expressed as: ; Among them, represents the predicted concentration at time , represents the actual pollutant concentration at time , is the window size; Through the above content, the spatio-temporal distribution pattern of pollutants in the sewage pipe network can be accurately identified. It not only considers the change trend of pollutants in different time periods but also can identify the aggregation intervals of pollution sources in space, thus better reflecting the diffusion law of pollution sources. Through spatio-temporal clustering analysis, the dynamic evolution of pollutants and the potential locations of pollution sources can be effectively revealed, providing a more scientific and accurate basis for pollution source tracing in the sewage pipe network, improving the timeliness and accuracy of pollution source identification, being able to track the changes of pollution sources in real time, and providing effective data support for environmental monitoring and governance.

[0029] The preliminary pollution source location and diffusion direction determination in S32 include: S321, calculating the pollutant concentration gradient: Using the identified pollutant concentration distribution pattern, calculate the gradient of the pollutant concentration in space . Let the pollutant concentration at a certain sewage pipe network node be , and the pollutant concentration at its adjacent node be . The spatial distance between the nodes is . Then the pollutant concentration gradient is expressed as: ; S322, positioning in combination with the pipe network topology: According to the topology of the sewage pipe network, that is, the pipe network nodes and their connection relationships, by calculating the relationship between the pollutant concentration gradient and the pipe network flow, judge the location of the pollution source. Let the flow at a certain node in the pipe network be , and the flow flowing to the adjacent node be . Then the preliminary location of the pollution source is expressed as: ; Among them, represents the possibility value of node as the pollution source. Through the combined analysis of flow and concentration gradient, the pollution source potential scores of each node are obtained, and the node with the maximum potential is the preliminary location of the pollution source; S323, diffusion direction analysis: According to the preliminary location of the pollution source and the concentration gradient, combined with the flow data of the pipe network, calculate the diffusion direction intensity of the pollutants and determine the diffusion direction of the pollution source, which is expressed as: ; Wherein, represents the diffusion direction intensity of pollutants from node to node . The diffusion direction of pollutants extends along the path with the largest flow rate and significant concentration change. is the flow rate between node and node in the sewage pipe network. Through the above content, combined with the spatio-temporal distribution pattern of pollutants, the pipe network topology structure, and the flow rate data, the preliminary location of the pollution source in the sewage pipe network and its diffusion path can be accurately identified. It not only considers the spatial variation of pollutant concentration but also incorporates the flow rate information into the analysis, making the location of the pollution source more accurate and dynamic. By combining the flow rate and concentration gradient, the diffusion direction of the pollution source can be tracked in real time, and the propagation trend of pollutants in the pipe network can be detected in a timely manner, thus providing a more scientific basis for pollution control and pipe network management, significantly improving the accuracy and efficiency of pollution source tracing, and effectively assisting the pollution control and environmental protection work of the sewage pipe network.

[0030] The pollution source identification and tracking in S4 include: S41, Dynamic identification and location of the pollution source: Based on the preliminary location and diffusion direction of the pollution source, combined with the pollutant concentration collected in real time, a multi-dimensional spatio-temporal analysis model is used to dynamically identify and locate the pollution source. S42, Tracking and updating of the pollution source diffusion path: Based on the real-time data of the real-time pollutant concentration, the diffusion path of the pollution source is dynamically tracked, and combined with the topology structure and flow rate data of the sewage pipe network, the diffusion trend and path of pollutants are predicted. By gradually updating the diffusion state of the pollution source, the diffusion direction and path of the pollution source are adjusted in real time. Through the above content, the dynamic identification and tracking of the pollution source location, characteristics, and diffusion path are realized. The diffusion state and flow path of the pollution source can be updated in real time, effectively coping with the dynamic changes during the diffusion process of the pollution source. By continuously monitoring the spatio-temporal changes of pollutants, the precise location of the pollution source can be accurately identified, and its diffusion trend can be detected in a timely manner, providing strong support for the pollution source control and treatment of the sewage pipe network, enhancing the real-time and accuracy of pollution source tracing, providing a scientific basis for environmental protection and pollution prevention, and ensuring the high efficiency and reliability of sewage pipe network management.

[0031] The multi-dimensional spatio-temporal analysis model in S41 adopts a grid-based diffusion model, and the grid-based diffusion model includes: S411, Grid-based area division: The sewage pipe network is divided into multiple small areas (grids), and each grid represents a node or area in the pipe network. S412, Application of Pollutant Source Location and Diffusion Direction: Based on the determined preliminary location and diffusion direction of the pollutant source, calculate the initial pollutant concentration for each grid, i.e., the initial pollutant concentration is the diffusion direction intensity of the pollutant at this location , expressed as: ; S413, Pollutant Diffusion Simulation: Use the diffusion equation to simulate the diffusion of pollutants between each grid cell. By calculating the updated value of the pollutant concentration in each grid cell, simulate the spatial diffusion process of pollutants, and perform dynamic identification and positioning of the pollutant source, expressed as: ; Among them, is the grid location at time of the pollutant concentration, is the grid location at time of the pollutant concentration, is the diffusion coefficient, is the neighboring grid at time of the pollutant concentration, is the pollutant source term, depending on the intensity and location of the pollutant source, is the influence coefficient of the pollutant source on the pollutant concentration of the surrounding grids; Through the above content, the diffusion process of pollutants in the sewage pipe network can be described in detail. Using the concentration update value and diffusion path prediction, the high-value areas and abnormal change trends of pollutants can be identified in real time, so as to dynamically locate the pollutant source. The grid-based diffusion model can combine the diffusion characteristics of pollutants with the actual situation of the pipe network flow to achieve accurate tracing and real-time tracking of the pollutant source in a complex environment, significantly improving the efficiency and accuracy of pollutant source identification, and providing scientific and reliable decision-making support for the pollution control and treatment of the sewage pipe network.

[0032] The pollutant source diffusion path tracking and update in S42 include: S421, Dynamic Diffusion Path Tracking: Use real-time pollutant concentration data and pipe network flow data to dynamically calculate the diffusion direction intensity of pollutants from the current grid location , expressed as: , expressed as: ; Among them, represents the diffusion direction intensity of the grid location at time , is the grid The pollutant concentration gradient is the grid position of the flow rate and are the weights of diffusion and flow rate for path tracing respectively; S422, Diffusion trend and path prediction: Using the diffusion direction intensity obtained by dynamic tracing , predict the diffusion trend and path of pollutants at future times, expressed as: ; wherein, is the predicted pollutant concentration at grid at future time , is the current diffusion direction intensity, is the influence coefficient of the diffusion path; S423, Real-time adjustment of diffusion direction and path: By continuously updating the concentration state of pollutants and the diffusion direction intensity , gradually optimize the diffusion direction and future path of pollutants, expressed as: ; wherein, is the updated diffusion direction intensity at time , is the change in real-time pollutant concentration, is the change in real-time flow rate, are the weight coefficients of concentration change and flow rate change respectively; Through the above content, dynamically trace the diffusion path of pollutants and predict their future diffusion trends, which can update the diffusion state and direction of pollutants in real time, timely reflect the changes of pollution sources and the propagation dynamics of pollutants in the pipe network. By comprehensively considering the pollutant concentration gradient and water flow direction, the accuracy and timeliness of pollution source location and path tracing are improved. In addition, it can also predict the future pollution diffusion trend, providing scientific decision-making support for pollution control and emergency management.

[0033] As Figure 2 shown, a sewage pipe network pollution source tracing analysis system for implementing the above-mentioned sewage pipe network pollution source tracing analysis method includes the following modules: Data acquisition module: Install sensors at multiple nodes of the sewage pipe network to collect pollutant concentration data in real time, and record the time stamps of pollutant concentrations and their corresponding spatial positions; Data preprocessing module: Preprocess the collected pollutant concentration data, including denoising and missing value processing; Pollution source spatio-temporal variation analysis module: Based on the preprocessed pollutant concentration data, use a spatio-temporal analysis model to analyze the spatio-temporal variation of pollutant concentration, identify the distribution pattern and variation trend of pollutants, and determine the preliminary location and diffusion direction of the pollution source; Pollution source identification and tracking module: Based on the preliminary location and diffusion direction of the pollution source, combined with the real-time collected pollutant concentration data, through a multi-dimensional spatio-temporal variation analysis model, dynamically identify and track the location of the pollution source and its diffusion path in the sewage pipe network, and update the diffusion state and flow path of the pollution source in real time.

[0034] This invention covers any alternatives, modifications, equivalent methods, and solutions made within the essence and scope of this invention. To enable the public to have a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments of this invention. However, those skilled in the art can fully understand this invention without the description of these details. Additionally, well-known methods, processes, procedures, components, and circuits are not described in detail to avoid unnecessary confusion to the essence of this invention.

[0035] The above are only the preferred embodiments of this invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of this invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this invention.

Claims

1. A method for tracing the source of pollution based on a sewage network, characterized in that: The following steps are involved: S1, data collection: sensors are deployed at multiple nodes of the sewage network to collect pollutant concentrations in real time and record the timestamps of pollutant concentrations and corresponding spatial locations; S2, data preprocessing: preprocessing the collected pollutant concentrations, including denoising and missing value processing; S3, analysis of spatiotemporal changes of pollution sources: Based on the pre-treated pollutant concentrations, the spatiotemporal changes of pollutant concentrations are analyzed using a spatiotemporal analysis model to identify the distribution pattern and change trend of pollutants and determine the preliminary location and diffusion direction of pollution sources; S4, pollution source identification and tracking: Based on the initial location and diffusion direction of the determined pollution source, combined with the real-time pollutant concentration, through a multi-dimensional spatiotemporal change analysis model, the location of the pollution source and its diffusion path in the pipeline network are dynamically identified and tracked, and the diffusion status and flow path of the pollution source are updated in real time.

2. A method for tracing the source of pollution based on a sewage pipe network according to claim 1, characterized in that: The data collection in S1 includes: S11, select sensor deployment nodes: conduct on-site surveys at multiple nodes of the sewage pipe network, and select key monitoring areas to deploy sensors. The key monitoring areas include the water inlet, water outlet, and intermediate nodes where pollutants are discharged; S12, sensor installation: installing pollutant concentration sensors on selected nodes; S13, real-time data collection: After the sensor is installed, the pollutant concentration is monitored in real time. When the pollutant concentration is collected, a timestamp is automatically added to each group of pollutant concentrations and bound to the corresponding spatial location.

3. The method for tracing the source of pollution based on sewage pipe network according to claim 1 is characterized in that: The data preprocessing in S2 includes: S21, denoising: using wavelet transform to denoise the collected pollutant concentration; S22, missing value processing: For missing values, linear interpolation is used to fill them.

4. The method for tracing the source of pollution based on sewage pipe network according to claim 1 is characterized in that: The analysis of the spatiotemporal variation of pollution sources in S3 includes: S31, spatiotemporal pattern recognition: Based on the pre-processed pollutant concentration, the spatiotemporal clustering algorithm is used to cluster the pollutant concentration, identify the distribution pattern of pollutants in different time periods and spatial locations, and analyze the change trend of pollutant concentration through time series analysis method to identify the change trend of pollutant concentration; S32, preliminary location of pollution sources and determination of diffusion direction: Based on the identified pollutant distribution patterns and changing trends, combined with the topological structure and flow data of the sewage network, the preliminary location and diffusion direction of the pollution sources are determined.

5. A method for tracing the source of pollution based on a sewage pipe network according to claim 4, characterized in that: The spatiotemporal pattern recognition in S31 includes: S311, spatiotemporal cluster analysis: Use the spatiotemporal K-means clustering algorithm to perform cluster analysis on the pre-treated pollutant concentrations to identify the spatial and temporal clustering intervals of pollutants; S312, Time Series Analysis: Based on the results of spatiotemporal clustering, the moving average method is used to analyze the changing trend of pollutant concentrations.

6. A method for tracing the source of pollution based on a sewage pipe network according to claim 5, characterized in that: The preliminary pollution source location and diffusion direction determination in S32 include: S321, calculate the pollutant concentration gradient: use the identified pollutant concentration distribution pattern to calculate the gradient of the pollutant concentration in space ; S322, positioning in combination with the topological structure of the pipe network: according to the topological structure of the sewage pipe network, that is, the pipe network nodes and their connection relationships, the location of the pollution source is determined by calculating the relationship between the pollutant concentration gradient and the pipe network flow rate; S323, Diffusion direction analysis: Based on the preliminary location and concentration gradient of the pollution source, combined with the flow data of the pipeline network, calculate the diffusion direction intensity of the pollutants , determine the diffusion direction of the pollution source.

7. A method for tracing the source of pollution based on a sewage pipe network according to claim 6, characterized in that: The pollution source identification and tracking in S4 includes: S41, Dynamic Identification and Location of Pollution Sources: Based on the preliminary location and diffusion direction of the pollution source, combined with the real-time collected pollutant concentration, a multi-dimensional spatiotemporal analysis model is used to dynamically identify and locate the pollution source; S42, tracking and updating of pollution source diffusion paths: Based on real-time data on pollutant concentrations, dynamically track the diffusion paths of pollution sources, and combine the topological structure and flow data of the sewage network to predict the diffusion trend and path of pollutants. By gradually updating the diffusion status of pollution sources, the diffusion direction and path of pollution sources can be adjusted in real time.

8. The method for tracing the source of pollution based on sewage pipe network according to claim 7 is characterized in that: The multidimensional spatiotemporal analysis model in S41 adopts a grid diffusion model, and the grid diffusion model includes: S411, gridded area division: the sewage pipe network is divided into multiple small areas, each grid represents a node or area in the pipe network; S412, Application of pollution source location and diffusion direction: Based on the determined preliminary location and diffusion direction of the pollution source, the initial pollutant concentration is calculated for each grid, that is, the initial pollutant concentration is the diffusion intensity of the pollutant at this location ; S413, pollutant diffusion simulation: Use the diffusion equation to simulate the diffusion of pollutants between each grid cell. By calculating the updated value of the pollutant concentration of each grid cell, simulate the diffusion process of pollutants in space and dynamically identify and locate the pollution source.

9. A method for tracing the source of pollution based on a sewage pipe network according to claim 8, characterized in that: The pollution source diffusion path tracking and updating in S42 includes: S421, Dynamic Diffusion Path Tracing: Using Real-time Pollutant Concentration Data and pipe network flow data to dynamically calculate the pollutants from the current grid location Diffusion direction strength ; S422, Diffusion trend and path prediction: Diffusion direction intensity obtained by dynamic tracking , predict the diffusion trend and path of pollutants in the future; S423, real-time adjustment of diffusion direction and path: by continuously updating the concentration status of pollutants, and diffusion direction strength , and gradually optimize the diffusion direction and future path of pollutants.

10. A system for tracing the source of pollution in a sewage pipe network, used to implement a method for tracing the source of pollution in a sewage pipe network as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Data acquisition module: sensors are deployed at multiple nodes of the sewage network to collect pollutant concentration data in real time and record the timestamp of the pollutant concentration and the corresponding spatial location; Data preprocessing module: preprocess the collected pollutant concentration data, including denoising and missing value processing; Pollution source spatiotemporal change analysis module: Based on the pre-processed pollutant concentration data, the spatiotemporal analysis model is used to analyze the spatiotemporal changes of pollutant concentrations, identify the distribution pattern and change trend of pollutants, and determine the preliminary location and diffusion direction of pollution sources; Pollution source identification and tracking module: Based on the preliminary location and diffusion direction of the pollution source, combined with the real-time collected pollutant concentration data, through a multi-dimensional spatiotemporal change analysis model, the location of the pollution source and its diffusion path in the sewage network are dynamically identified and tracked, and the diffusion status and flow path of the pollution source are updated in real time.

Images