Intelligent Runoff Pollution Monitoring and Response Method and System

Abstract

The present invention provides an intelligent runoff pollution monitoring and response method and system. By arranging multiple monitoring points in the runoff area, sensors are used to collect water quality, hydrological and meteorological data in real time, and the data is transmitted to the data processing center through a wireless network for preprocessing, storage and analysis. The comprehensive pollution index of each monitoring point is calculated and compared with the set index threshold. When the comprehensive pollution index exceeds the threshold, the system will identify and evaluate key water quality parameters to determine reasonable parameter thresholds; once the data at the monitoring point exceeds the preset pollution threshold, the alarm mechanism will be triggered. Subsequently, in combination with the pipe network water flow model and the geographic information system, the pollution path is traced back in reverse to accurately locate the pollution source, providing a basis for pollution control. This process includes screening suspected pollution source nodes, calculating the probability of the propagation path, preferentially checking high-probability paths until the pollution source is traced or the path probability is lower than the preset value.

Description

Technical Field

[0001] The present invention relates to the technical field of runoff pollution monitoring, and particularly to an intelligent runoff pollution monitoring and response method. Background Art

[0002] With the acceleration of the urbanization process, runoff pollution has become an important issue affecting water quality and the ecological environment. Traditional water quality monitoring methods often rely on manual sampling and laboratory analysis, which are not only time-consuming and laborious, but also difficult to achieve real-time monitoring and rapid response to pollution events.

[0003] Although existing intelligent monitoring technologies have improved the monitoring efficiency to a certain extent, there are still some problems. For example, the layout of monitoring points is unreasonable, resulting in the monitoring data being unable to comprehensively reflect the pollution status of the runoff area; the data processing and analysis capabilities are insufficient, making it difficult to accurately evaluate the pollution degree and mine key water quality parameters; the alarm mechanism is insensitive, unable to detect and warn of pollution anomalies in a timely manner; the pollution source tracing technology is backward, making it difficult to quickly locate the pollution source area. In view of these problems, the present application proposes an intelligent runoff pollution monitoring and response method and system, aiming to improve the monitoring efficiency, accurately evaluate the pollution degree, timely detect and warn of pollution anomalies, and quickly locate the pollution source area. Summary of the Invention

[0004] In view of the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide an intelligent runoff pollution monitoring and response method and system, which are used to solve the problem in the prior art that it is difficult to perform real-time monitoring and rapid response to runoff pollution events.

[0005] To achieve the above purpose and other related purposes, the present invention provides the following technical solutions:

[0006] An intelligent runoff pollution monitoring and response method, comprising the following steps:

[0007] S1. Arrange a plurality of monitoring points in the runoff area, use sensors to collect water quality parameters, hydrological parameters, and meteorological data of the runoff in real time, and transmit the collected data to the data processing center by using a wireless sensor network;

[0008] S2. The data processing center analyzes and processes the collected data, evaluates the pollution index for each monitoring point according to the processing results, analyzes the key water quality parameters highly related to runoff pollution for the monitoring points with a pollution index exceeding the index threshold, and performs parameter-level evaluation on these key water quality parameters;

[0009] S3. Set parameter thresholds according to the parameter-level evaluation. Both the parameter threshold and the index threshold are regarded as pollution thresholds. Once the runoff exceeds the preset pollution threshold, it is regarded as an abnormal situation, and the alarm mechanism is triggered;

[0010] S4. Once the alarm mechanism is triggered, the pollution source is traced back by combining the pipe network water flow model and the geographic information system. By analyzing the flow rate and water quality changes at each monitoring point, the pollution source area is located.

[0011] To implement the above technical solution, multiple monitoring points are scientifically arranged in the runoff area, and each monitoring point is equipped with advanced sensors for real-time collection of water quality parameters (such as dissolved oxygen, pH value, heavy metal content, etc.), hydrological parameters (such as flow rate, flow velocity, etc.), and meteorological data (such as rainfall, wind speed, etc.). These data are efficiently and reliably transmitted to the data processing center through the wireless sensor network to ensure the timeliness and accuracy of information. After receiving the data from each monitoring point, the data processing center cleans, integrates, and analyzes the data. By calculating the pollution index, the pollution status of each monitoring point is quantitatively evaluated. For the monitoring points where the pollution index exceeds the index threshold, the key water quality parameters related to runoff pollution are further analyzed and a parameter-level evaluation is carried out to provide a basis for setting reasonable parameter thresholds. According to the evaluation results of the pollution index and the key water quality parameters, pollution thresholds (including index thresholds and parameter thresholds) are set. Once the data of a certain monitoring point exceeds these thresholds, it is regarded as an abnormal situation, and the alarm mechanism is immediately triggered to send an alarm message to the management personnel to remind them to take countermeasures. After the alarm is triggered, the pipe network water flow model and geographic information system (GIS) technology are used, combined with the flow rate and water quality change data of each monitoring point, to trace back the transmission path of pollutants and accurately locate the pollution source area. This step helps to quickly identify the pollution source and provides key information for subsequent pollution control and treatment.

[0012] In an embodiment of the present invention, the S1 includes:

[0013] S11. Determine the monitoring point locations according to the terrain, landform, water flow characteristics, land use type, and potential pollution sources in the runoff area;

[0014] S12. Install water quality sensors, hydrological sensors, and meteorological data sensors at each monitoring point and automatically collect data at preset time intervals to ensure that the data collection timestamps of each monitoring point are consistent;

[0015] S13. The data processing center establishes an efficient data receiving interface for simultaneously processing a large amount of raw runoff data from multiple monitoring points. After preprocessing the raw runoff data, the preprocessed runoff data is stored in a distributed database.

[0016] To implement the above technical solution, based on the terrain, landform, water flow characteristics, land use types, and potential pollution sources in the runoff area, the selection of these locations aims to comprehensively cover the runoff area while focusing on potential pollution sources and areas vulnerable to pollution to ensure the effectiveness and accuracy of monitoring. Install water quality sensors, hydrological sensors, and meteorological data sensors at each determined monitoring point. The sensors automatically collect data at preset time intervals and transmit it to the data processing center through a wireless sensor network. To ensure the accuracy and consistency of the data, the data collection timestamps of each monitoring point are uniformly set for subsequent data analysis and processing. The data processing center establishes an efficient data receiving interface for simultaneously processing a large volume of raw runoff data from multiple monitoring points. These interfaces have high concurrent processing capabilities and a data integrity verification mechanism to ensure the accurate reception and transmission of data. The received raw runoff data undergoes preprocessing operations such as data cleaning, format conversion, and outlier handling to improve the quality and usability of the data. The preprocessed runoff data is stored in a distributed database for subsequent data analysis and application.

[0017] In an embodiment of the present invention, S2 includes:

[0018] S21, the data processing center obtains the preprocessed runoff data of each detection point from the distributed database and generates a comprehensive pollution index for each monitoring point;

[0019] S22, compare the comprehensive pollution index with the set index threshold. Once the comprehensive pollution index is greater than the index threshold, key water quality parameters highly correlated with runoff pollution are selected through correlation analysis and principal component analysis, and the concentration change amount and concentration change rate of these key water quality parameters at the set time step are evaluated.

[0020] To implement the above technical solution, the data processing center obtains the preprocessed runoff data of each monitoring point from the distributed database and generates a comprehensive pollution index for each monitoring point. This comprehensive index is a comprehensive evaluation indicator that can reflect the overall water quality pollution situation of the monitoring point; the data processing center compares the generated comprehensive pollution index with the set index threshold. Once the comprehensive pollution index is greater than the index threshold, it indicates that water quality pollution has occurred, and the data processing center will further conduct correlation analysis and principal component analysis. Correlation analysis aims to identify key water quality parameters highly correlated with the comprehensive pollution index, which have the greatest impact on water quality pollution and are the focus of subsequent evaluation and response; principal component analysis is used to further simplify the data and extract the main components or factors affecting water quality pollution; after identifying the key water quality parameters, the data processing center evaluates the concentration change amount and concentration change rate of these key water quality parameters at the set time step to predict the future development trend of the key water quality parameters.

[0021] In an embodiment of the present invention, S21 includes:

[0022] S211, determining relevant water quality parameters of runoff pollution and setting weights for each relevant water quality parameter according to historical data, water quality standards and expert opinions;

[0023] S212, performing standardization processing on each relevant water quality parameter, and the standardization processing method is as follows:

[0024]

[0025] Wherein, is the original value of the th relevant water quality parameter, is the minimum value of the th relevant water quality parameter, is the maximum value of the th relevant water quality parameter, is the value after standardization of the th relevant water quality parameter;

[0026] S213, calculating the comprehensive pollution index of each monitoring point by using the weighted average method, and the method for obtaining the comprehensive pollution index is as follows:

[0027]

[0028] Wherein, is the comprehensive pollution index, is the weight of the th relevant water quality parameter, is the value after standardization of the th relevant water quality parameter, is the number of relevant water quality parameters.

[0029] By implementing the above technical solution, water quality parameters closely related to pollution are identified according to the characteristics of runoff pollution. Based on water quality standards, historical data and expert opinions, reasonable weights are set for these relevant water quality parameters. The setting of weights takes into account the magnitude of the contribution of each relevant parameter to water quality pollution, toxicity and impact on the ecosystem. In order to eliminate the influence of the dimensions and value ranges of different water quality parameters, it is necessary to perform standardization processing on each parameter. The standardization processing method uses linear transformation to convert the original value of each parameter into a standardized value between 0 and 1. After the standardization processing of the water quality parameters is completed, the weighted average method is used to calculate the comprehensive pollution index of each monitoring point, so as to comprehensively reflect the water quality pollution status of each monitoring point and provide a basis for subsequent analysis and response.

[0030] In an embodiment of the present invention, S22 includes:

[0031] If the comprehensive pollution index is greater than the index threshold, key water quality parameters highly correlated with runoff pollution are selected through correlation analysis and principal component analysis, and the first-order difference of the key water quality parameter is calculated to measure the concentration change of the key water quality parameter. The calculation method of the first-order difference is as follows:

[0032]

[0033] Wherein, is the first-order difference of the key water quality parameter, is the time point concentration of the key water quality parameter, is the time point concentration of the key water quality parameter;

[0034] According to the first-order difference, the second-order difference of the key water quality parameter is calculated to measure the concentration change rate of the key water quality parameter. The calculation method of the second-order difference is as follows:

[0035]

[0036] Wherein, is the second-order difference of the key water quality parameter, is the time point concentration of the key water quality parameter.

[0037] To implement the above technical solution, first, the correlation analysis and principal component analysis methods are used to screen out the key water quality parameters highly correlated with runoff pollution from many relevant water quality parameters. These key water quality parameters are usually indicators that have an important impact on the water quality pollution status and change significantly; for the selected key water quality parameters, their first-order differences are calculated to measure the concentration change within a set time step, and then based on the calculated first-order differences, the second-order differences are further calculated to measure the concentration change rate, which helps to predict the future development trend of water quality pollution.

[0038] In an embodiment of the present invention, the S22 further includes:

[0039] Using the first-order difference and the second-order difference as independent variables, a concentration prediction model is constructed to predict the concentration of the key water quality parameter at the time point The concentration prediction model is as follows:

[0040]

[0041] Wherein, is the predicted concentration of the key water quality parameter at the time point ; is the intercept term, indicating the baseline concentration level of the key water quality parameter; is the regression coefficient of the first-order difference, is the regression coefficient of the second-order difference, is the error term.

[0042] By introducing the first-order difference and the second-order difference as independent variables, the concentration prediction model can more accurately capture the changing trends and patterns of key water quality parameters, thereby improving the accuracy of prediction; the concentration prediction model has important application value in the intelligent runoff pollution monitoring and response method, which can improve prediction accuracy, support early warning, optimize resource allocation, and promote technological innovation.

[0043] In an embodiment of the present invention, the S3 includes:

[0044] Set the upper threshold of the first-order difference , if , it is identified as a first-level alarm;

[0045] Set the upper threshold of the second-order difference , if , it is identified as a second-level alarm;

[0046] Set the upper threshold of the concentration of the key water quality parameter If , if , it is identified as a third-level alarm;

[0047] Set the upper threshold of the comprehensive pollution index If , if , it is identified as a fourth-level alarm.

[0048] Implementing the above technical solution, a first-level alarm indicates that the concentration of the key water quality parameter has changed significantly in a short period of time; a second-level alarm indicates that the rate of change of the concentration of the key water quality parameter is abnormal; a third-level alarm indicates that the concentration of the key water quality parameter may exceed the safety threshold at the future time point ; a fourth-level alarm indicates that the overall water quality pollution situation is serious; by setting different levels of alarm thresholds, the system can monitor water quality changes in real time and quickly identify potential risks to achieve timely warning.

[0049] In an embodiment of the present invention, the S4 includes:

[0050] Based on the detailed design drawings, pipe diameter, pipe length, and slope information of the drainage pipe network, a pipe network water flow model is constructed using hydraulic principles. In the pipe network water flow model, the pipe network is divided into pipe segments for water flow transportation and nodes for water flow convergence or diversion, and at the same time, the nodes are used as monitoring points;

[0051] Fuse the topographic and geomorphic features, land use types, and geographical location data of the drainage network in the geographic information system with the pipe network water flow model. In the geographic information system, display the pipe network layout in the form of a map layer, and at the same time associate the information of each node with the surrounding geographical environment;

[0052] Among all the monitored node data, screen out the set of nodes with excessive pollution according to the set pollution threshold , and use these polluted nodes as the starting point for tracing the pollution source and trace back the pollution source in reverse.

[0053] To implement the above technical solution, the system fuses the topographic and geomorphic features, land use types, and geographical location data of the drainage network in the geographic information system with the pipe network water flow model. Through the fusion, the geographic information system can intuitively display the pipe network layout in the form of a map layer, and at the same time associate the information of each node with the surrounding geographical environment. This fusion not only improves the visualization degree of the pipe network information, but also provides rich geographical environment background information for subsequent pollution source tracing. In addition, the system screens out the set of nodes with excessive pollution through the preset pollution threshold , and uses these polluted nodes as the starting point for tracing the pollution source and trace back the pollution source in reverse.

[0054] In an embodiment of the present invention, the method for tracing back the pollution source in reverse is as follows:

[0055] B1. For each polluted node , trace back to its upstream adjacent node , and calculate the flow difference and the change rate of the concentration of the water quality parameter between the node and . If and , it indicates that the key water quality parameter is transmitted from the upstream node to the node . At the same time, mark the node as a suspected pollution source transmission node and add it to the set of suspected nodes , where is the flow of the polluted node , is the flow of the adjacent node to the , represents the concentration of the th key water quality parameter in the polluted node , represents the concentration of the th key water quality parameter in the node ;

[0056] B2. According to the suspected node and the polluted node The length of the pipe segment between , the water flow velocity , the attenuation coefficient of the th key water quality parameter , calculate the key water quality parameter propagating from node to node

[0057]

[0058] wherein represents the path probability from node to node , represents the weighted sum of all possible paths;

[0059] B3, sort the path probabilities from large to small, and sort the nodes in the suspected node set according to the sorting result;

[0060] B4, take the node with the highest probability in the suspected node set as the new starting point, repeat steps B1 - B3, continuously trace back the pollution path upstream, and update the suspected node set and the path probability distribution until the source of the pipe network is traced or is less than the preset value .

[0061] By scientifically and reasonably combining the flow difference and the change rate of water quality parameter concentration for the preliminary screening of suspected pollution sources, the possible pollution propagation nodes can be accurately screened out from numerous pipe network nodes quickly, avoiding the waste of time and resources caused by blind investigation; based on the dynamic analysis of real-time monitoring data, it is ensured that the locking of suspected pollution sources can timely reflect the latest changes in pollution transmission; at the same time, the path probability calculation formula is introduced to quantify the possibility of pollution propagation paths, providing a scientific decision-making basis for the investigation work; with the progress of the tracing process, the dynamic update of path probabilities and the real-time adjustment of investigation priorities enable the continuous optimization of resource allocation. At different stages, the focus is always placed on the most likely pollution source direction, avoiding the ineffective investment of resources on low-probability paths, and achieving the effective control of tracing costs and the maximization of investigation effects.

[0062] In another embodiment of the present invention, an intelligent runoff pollution monitoring and response system is provided, including:

[0063] The monitoring network module is used to arrange multiple monitoring points in the runoff area. Each monitoring point is equipped with a water quality sensor, a hydrological sensor, and a meteorological data sensor to collect the water quality parameters, hydrological parameters, and meteorological data of the runoff in real time, and transmit the collected data to the data processing center through the wireless sensor network;

[0064] The data processing and analysis module is used to receive the data from the monitoring network module, preprocess, store, analyze, and process the data to evaluate the pollution index of each monitoring point, identify the key water quality parameters, and conduct parameter-level evaluation on these key water quality parameters;

[0065] The alarm trigger module is used to set the pollution threshold. According to the pollution index and the evaluation results of the key water quality parameters provided by the data processing and analysis module, once it is found that the runoff exceeds the preset pollution threshold, the alarm mechanism is triggered;

[0066] Once the alarm trigger module issues an alarm, the pollution source tracking module combines the pipe network water flow model and the geographic information system to reverse-track the pollution source and locate the pollution source area by analyzing the flow rate and water quality changes at each monitoring point;

[0067] The user interface module is used to provide the user with a system operation interface, display the monitoring data, analysis results, alarm information, and pollution source tracking results, and allow the user to perform parameter settings and system configurations.

[0068] To implement the above technical solution, the monitoring network module includes a monitoring point layout sub-module for determining the positions of monitoring points according to the terrain, landform, water flow characteristics, land use types, and potential pollution sources in the runoff area; a data collection and transmission sub-module for installing sensors at each monitoring point, automatically collecting data at preset time intervals, and transmitting the data to the data processing center through a wireless sensor network. The data processing and analysis module includes a data preprocessing sub-module for preprocessing the received raw data, such as data cleaning, format conversion, etc., and storing the preprocessed data in a distributed database; a pollution index evaluation sub-module for generating a comprehensive pollution index for each monitoring point and comparing it with a set index threshold to evaluate the pollution level; a key water quality parameter identification and evaluation sub-module for, when the pollution index exceeds the index threshold, selecting key water quality parameters highly correlated with the pollution index through correlation analysis and principal component analysis, and evaluating the concentration change and concentration change rate of these parameters. The alarm trigger module includes an alarm rule setting sub-module for setting the thresholds of the first-order difference, second-order difference, key water quality parameter concentration, and comprehensive pollution index; an alarm level determination sub-module for determining the alarm level based on the data provided by the data processing and analysis module and triggering the corresponding alarm mechanism. The pollution source tracking module further includes a pipe network water flow model construction sub-module for constructing a pipe network water flow model based on the design drawings, pipe diameters, pipe lengths, and slope information of the drainage pipe network using hydraulic principles; a geographic information system integration sub-module for integrating the terrain, landform, land use types, and geographical location data of the drainage pipe network in the geographic information system with the pipe network water flow model and displaying the pipe network layout in the form of a map layer; a pollution path backtracking sub-module for starting from the node with excessive pollution and backtracking the pollution source in reverse, and positioning the pollution source area by analyzing the flow rate and water quality changes at each monitoring point. The pollution path backtracking sub-module includes a suspected pollution source node screening sub-module for screening the nodes with increased flow rate and increased key water quality parameter concentration among the upstream adjacent nodes as suspected pollution source propagation nodes; a path probability calculation sub-module for calculating the path probability of the key water quality parameter propagating from the suspected node to the pollution node according to the pipe section length, water flow velocity, and attenuation coefficient of the key water quality parameter between the suspected node and the pollution node; a sorting and backtracking sub-module for sorting the suspected nodes and preferentially investigating the path and nodes with the highest probability, and continuously backtracking the pollution path upstream until the source of the pipe network or the path probability is less than the preset value.

[0069] As described above, the intelligent runoff pollution monitoring and response method and system of the present invention have the following beneficial effects:

[0070] 1. Comprehensive Coverage and Precise Monitoring: By scientifically and reasonably arranging monitoring points and equipping advanced sensors, water quality parameters, hydrological parameters, and meteorological data can be collected in real time to ensure the comprehensiveness and accuracy of the data. At the same time, a wireless sensor network is used to achieve efficient data transmission, ensuring the timeliness and reliability of information.

[0071] 2. In-depth Analysis and Scientific Evaluation: The data processing center has strong data analysis capabilities, can clean, integrate, and analyze the collected data, generate a comprehensive pollution index, and conduct parameter-level evaluations on key water quality parameters. This scientific evaluation system from macro to micro provides a full-range and high-precision basis for pollution control decision-making.

[0072] 3. Intelligent Alarm and Timely Response: Set reasonable pollution thresholds and a sensitive alarm mechanism. Once the runoff pollution exceeds the preset threshold, relevant departments and personnel can quickly receive notifications and immediately activate emergency plans. This helps to take intervention measures at the initial stage of pollution and effectively contain the further spread of pollution.

[0073] 4. Precise Source Tracing and Efficient Treatment: Combining the pipe network water flow model with Geographic Information System (GIS) technology can reverse-track the transmission path of pollutants and accurately locate the pollution source area. This step helps to quickly identify the pollution source, provides key information for subsequent pollution control and treatment, and thus greatly improves the treatment efficiency and effect.

[0074] 5. Dynamic Adjustment and Continuous Optimization: During the source tracing process, by dynamically updating the path probability and investigation priority, the resource allocation can be continuously optimized to ensure that the focus is always on the most likely pollution source direction at different stages. This avoids ineffective investment of resources on low-probability paths and realizes effective control of source tracing costs and maximization of investigation effects. Brief Description of the Drawings

[0075] Figure 1 It shows a schematic flow diagram of the method of the present invention. Detailed Embodiments

[0076] The following specific embodiments illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0077] Please refer to Figure 1, the present invention provides an intelligent runoff pollution monitoring and response method and system. The method includes the following steps: S1, arrange multiple monitoring points in the runoff area, use sensors to collect water quality parameters, hydrological parameters, and meteorological data of the runoff in real time, and transmit the collected data to the data processing center using a wireless sensor network; S2, the data processing center analyzes and processes the collected data, evaluates the pollution index for each monitoring point according to the processing results, analyzes the key water quality parameters highly related to runoff pollution for the monitoring points with pollution index exceeding the index threshold, and conducts parameter-level evaluation on these key water quality parameters; S3, set parameter thresholds according to the parameter-level evaluation. Both the parameter threshold and the index threshold are regarded as pollution thresholds. Once the runoff exceeds the preset pollution threshold, it is regarded as an abnormal situation and the alarm mechanism is triggered; S4, once the alarm mechanism is triggered, combine the pipe network water flow model and the geographic information system to trace the pollution source backward, and locate the pollution source area by analyzing the flow and water quality changes of each monitoring point.

[0078] The working principle of the above technical solution is as follows: Scientifically arrange multiple monitoring points in the runoff area. Each monitoring point is equipped with advanced sensors for real-time collection of water quality parameters (such as dissolved oxygen, pH value, heavy metal content, etc.), hydrological parameters (such as flow rate, velocity, etc.), and meteorological data (such as rainfall, wind speed, etc.). These data are efficiently and reliably transmitted to the data processing center through a wireless sensor network to ensure the real-time and accuracy of information; After receiving the data from each monitoring point, the data processing center cleans, integrates, and analyzes the data. By calculating the pollution index, the pollution status of each monitoring point is quantitatively evaluated. For the monitoring points with pollution index exceeding the index threshold, further analyze the key water quality parameters related to runoff pollution and conduct parameter-level evaluation to provide a basis for setting reasonable parameter thresholds; According to the evaluation results of the pollution index and key water quality parameters, set pollution thresholds (including index thresholds and parameter thresholds). Once the data of a certain monitoring point exceeds these thresholds, it is regarded as an abnormal situation occurring, and the alarm mechanism is immediately triggered to send an alarm message to the management personnel to remind them to take countermeasures; After the alarm is triggered, use the pipe network water flow model and geographic information system (GIS) technology, combined with the flow and water quality change data of each monitoring point, to trace the transmission path of pollutants backward and accurately locate the pollution source area. This step helps to quickly identify the pollution source and provide key information for subsequent pollution control and treatment.

[0079] The beneficial effects of the above technical solution are as follows: The in-depth analysis ability of the data processing center can not only give the comprehensive pollution index of each monitoring point, but also mine the key water quality parameters and their dynamic change characteristics for the pollution exceeding the standard situation. This scientific evaluation system from macro to micro provides a full-range and high-precision basis for pollution control decision-making. By setting reasonable pollution thresholds and supporting sensitive alarm mechanisms, the intelligent and timely discovery and early warning of pollution anomalies are realized. Once the runoff pollution exceeds the threshold, relevant departments and personnel can quickly receive notifications and immediately initiate emergency plans to take intervention measures at the initial stage of pollution, effectively curbing the further spread of pollution. By collecting water quality, hydrological and meteorological data in real time, the comprehensive impacts of natural factors (such as rainfall and temperature) and human activities (such as sewage discharge) on runoff pollution are fully considered, making the grasp of pollution dynamics more accurate. For example, after a heavy rain, it can timely monitor the large amount of surface pollutants flowing into the runoff due to rainwater scouring, so as to early warn of the possible pollution peak. Through the detailed analysis of the flow rate and water quality change data of each monitoring point during the pollution source tracing process, the propagation path and diffusion law of pollution in the pipe network can be further understood; the organic combination of the pipe network water flow model and the geographic information system provides strong technical support for pollution source tracing and can accurately locate the pollution source area.

[0080] S1 includes S11, determining the positions of monitoring points according to the topography, landform, water flow characteristics, land use type and potential pollution sources of the runoff area; S12, installing water quality sensors, hydrological sensors and meteorological data sensors at each monitoring point and automatically collecting data at preset time intervals to ensure that the data collection timestamps of each monitoring point are consistent; S13, the data processing center establishes an efficient data receiving interface for simultaneously processing a large amount of raw runoff data from multiple monitoring points, and after preprocessing the raw runoff data, storing the preprocessed runoff data in a distributed database.

[0081] Based on the topography, geomorphology, water flow characteristics, land use types, and potential pollution sources in the runoff area, the selection of these locations aims to comprehensively cover the runoff area while focusing on potential pollution sources and vulnerable areas to ensure the effectiveness and accuracy of monitoring. Water quality sensors, hydrological sensors, and meteorological data sensors are installed at each identified monitoring point. The sensors automatically collect data at preset time intervals and transmit it to the data processing center through a wireless sensor network. To ensure the accuracy and consistency of the data, the data collection timestamps at each monitoring point are uniformly set for subsequent data analysis and processing. The data processing center establishes an efficient data reception interface for simultaneously processing large volumes of raw runoff data from multiple monitoring points. These interfaces have high concurrent processing capabilities and a data integrity verification mechanism to ensure the accurate reception and transmission of data. The received raw runoff data undergoes preprocessing operations such as data cleaning, format conversion, and outlier handling to improve the quality and usability of the data. The preprocessed runoff data is stored in a distributed database for subsequent data analysis and application.

[0082] S2 includes: S21, the data processing center obtains the preprocessed runoff data of each detection point from the distributed database and generates a comprehensive pollution index for each monitoring point; S22, compares the comprehensive pollution index with the set index threshold. Once the comprehensive pollution index is greater than the index threshold, key water quality parameters highly correlated with runoff pollution are selected through correlation analysis and principal component analysis, and the concentration change amount and concentration change rate of these key water quality parameters at the set time step are evaluated.

[0083] The data processing center obtains the preprocessed runoff data of each monitoring point from the distributed database and generates a comprehensive pollution index for each monitoring point. This comprehensive index is a comprehensive evaluation indicator that can reflect the overall water quality pollution situation of the monitoring point. The data processing center compares the generated comprehensive pollution index with the set index threshold. Once the comprehensive pollution index is greater than the index threshold, it indicates that water quality pollution has occurred, and the data processing center will further conduct correlation analysis and principal component analysis. Correlation analysis aims to identify key water quality parameters highly correlated with the comprehensive pollution index, which have the greatest impact on water quality pollution and are the focus of subsequent evaluation and response. Principal component analysis is used to further simplify the data and extract the main components or factors affecting water quality pollution. After identifying the key water quality parameters, the data processing center evaluates the concentration change amount and concentration change rate of these key water quality parameters at the set time step to predict the future development trend of the key water quality parameters.

[0084] The above S21 includes: S211, determining relevant water quality parameters of runoff pollution and setting weights for each relevant water quality parameter according to historical data, water quality standards, and expert opinions; S212, performing standardization processing on each relevant water quality parameter, and the standardization processing method is as follows:

[0085]

[0086] Among them, is the original value of the th relevant water quality parameter, is the minimum value of the th relevant water quality parameter, is the maximum value of the th relevant water quality parameter, is the value after standardization of the th relevant water quality parameter;

[0087] S213, calculating the comprehensive pollution index of each monitoring point by using the weighted average method, and the method for obtaining the comprehensive pollution index is as follows:

[0088]

[0089] Among them, is the comprehensive pollution index, is the weight of the th relevant water quality parameter, is the value after standardization of the th relevant water quality parameter, is the number of relevant water quality parameters.

[0090] Identify water quality parameters closely related to pollution according to the characteristics of runoff pollution, and set reasonable weights for these relevant water quality parameters based on water quality standards, historical data, and expert opinions. The setting of weights takes into account the magnitude of the contribution of each relevant parameter to water quality pollution, toxicity, and impact on the ecosystem; in order to eliminate the influence of different water quality parameter dimensions and value ranges, it is necessary to perform standardization processing on each parameter. The standardization processing method uses linear transformation to convert the original value of each parameter into a standardized value between 0 and 1; after completing the standardization processing of water quality parameters, use the weighted average method to calculate the comprehensive pollution index of each monitoring point, so as to comprehensively reflect the water quality pollution status of each monitoring point and provide a basis for subsequent analysis and response.

[0091] The above S22 includes: if the comprehensive pollution index is greater than the index threshold, then select key water quality parameters highly related to runoff pollution through correlation analysis and principal component analysis, and calculate the first-order difference of the key water quality parameter to measure the concentration change amount of the key water quality parameter. The first-order difference calculation method is as follows:

[0092]

[0093] Among them, is the first-order difference of the key water quality parameter, is the time point of the concentration of the key water quality parameter, is the time point of the concentration of the key water quality parameter;

[0094] According to the first-order difference, calculate the second-order difference of the key water quality parameter to measure the concentration change rate of the key water quality parameter. The calculation method of the second-order difference is as follows:

[0095]

[0096] Among them, is the second-order difference of the key water quality parameter, is the time point of the concentration of the key water quality parameter.

[0097] First, use the methods of correlation analysis and principal component analysis to screen out the key water quality parameters that are highly correlated with runoff pollution from many related water quality parameters. These key water quality parameters are usually indicators that have an important impact on the water quality pollution status and change significantly; for the screened key water quality parameters, calculate their first-order differences to measure the concentration change amount within a set time step, and then on the basis of calculating the first-order differences, further calculate the second-order differences to measure the concentration change rate, which helps to predict the future development trend of water quality pollution.

[0098] The S22 also includes: using the first-order difference and the second-order difference as independent variables to construct a concentration prediction model for predicting the concentration of the key water quality parameter at the time point The concentration prediction model is as follows:

[0099]

[0100] Among them, is the predicted concentration of the key water quality parameter at the time point ; is the intercept term, indicating the baseline concentration level of the key water quality parameter; is the regression coefficient of the first-order difference, is the regression coefficient of the second-order difference, is the error term.

[0101] By introducing the first-order difference and the second-order difference as independent variables, the concentration prediction model can more accurately capture the changing trends and patterns of key water quality parameters, thereby improving the accuracy of prediction. The concentration prediction model has important application value in the intelligent runoff pollution monitoring and response method. It can improve prediction accuracy, support early warning, optimize resource allocation, and promote technological innovation.

[0102] S3 includes: setting an upper threshold for the first-order difference , if , it is identified as a first-level alarm; setting an upper threshold for the second-order difference , if , it is identified as a second-level alarm; setting an upper threshold for the concentration of the key water quality parameter , if , it is identified as a third-level alarm; setting an upper threshold for the comprehensive pollution index , if , it is identified as a fourth-level alarm.

[0103] The first-level alarm indicates that the concentration of the key water quality parameter has changed significantly in a short period of time; the second-level alarm indicates that the rate of change of the concentration of the key water quality parameter is abnormal; the third-level alarm indicates that the concentration of the key water quality parameter may exceed the safety threshold at the future time point ; the fourth-level alarm indicates that the overall water quality pollution situation is serious. By setting different levels of alarm thresholds, the system can monitor water quality changes in real time and quickly identify potential risks to achieve timely warning.

[0104] S4 includes: Based on the detailed design drawings, pipe diameters, pipe lengths, and slope information of the drainage network, a pipe network water flow model is constructed using hydraulic principles. In the pipe network water flow model, the pipe network is divided into pipe segments for water flow transportation and nodes for water flow convergence or diversion, and at the same time, the nodes are used as monitoring points; the topographic features, land use types, and geographical location data of the drainage network in the geographic information system are integrated with the pipe network water flow model. In the geographic information system, the pipe network layout is displayed in the form of a map layer, and at the same time, the information of each node and its surrounding geographical environment is associated; among all the monitored node data, a set of nodes with excessive pollution is selected according to the set pollution threshold , and taking these polluted nodes as the starting point for tracing, the pollution source is traced back reversely.

[0105] The system integrates the topographic and geomorphic features, land use types, and geographical location data of the drainage pipe network in the geographic information system with the pipe network water flow model. Through this integration, the geographic information system can intuitively display the layout of the pipe network in the form of map layers and, at the same time, associate the geographical environment information of each node with its surroundings. This integration not only improves the visualization degree of the pipe network information but also provides rich geographical environment background information for subsequent pollution source tracing. In addition, the system screens out the set of nodes with excessive pollution through a preset pollution threshold. , and these polluted nodes are used as the starting points for tracing, and the pollution sources are traced backward.

[0106] The method for tracing the pollution source backward is as follows: B1. For each polluted node , trace back to its adjacent upstream node , and calculate the flow difference and the change rate of the water quality parameter concentration between the node and the adjacent node . If and , it indicates that the key water quality parameter is transmitted from the upstream node to the node . At the same time, mark the node as a suspected pollution source propagation node and add it to the set of suspected nodes , where is the flow of the polluted node , is the flow of the adjacent node to the , represents the concentration of the rd key water quality parameter in the polluted node , represents the concentration of the th key water quality parameter in the node ;

[0107] B2. According to the pipe segment length between the suspected node and the polluted node , the water flow velocity , and the attenuation coefficient of the th key water quality parameter, calculate the path probability of the key water quality parameter propagating from the node to the node . The path probability calculation formula is as follows:

[0108]

[0109] where represents from the node To Node The path probability, represents the weighted sum of all possible paths;

[0110] B3, sort the path probabilities from large to small, and sort the suspected node set according to the sorting results. Sort the nodes in ;

[0111] B4, the suspected node set The node with the highest probability is used as the new starting point, and steps B1-B3 are repeated to continuously trace the contaminated path upstream and update the set of suspected nodes. and path probability distribution until the source of the pipe network or Less than the preset value .

[0112] By scientifically and rationally combining the flow difference and the concentration change rate of water quality parameters to conduct preliminary screening of suspected pollution sources, it is possible to quickly and accurately screen out possible pollution transmission nodes from numerous pipe network nodes, avoiding the waste of time and resources caused by blind investigation; based on the dynamic analysis of real-time monitoring data, it ensures that the locking of suspected pollution sources can timely reflect the latest changes in pollution transmission; at the same time, the path probability calculation formula is introduced to quantify the possibility of pollution transmission paths, providing a scientific decision-making basis for investigation work; as the tracing process progresses, the dynamic update of path probabilities and the real-time adjustment of investigation priorities enable continuous optimization of resource allocation. At different stages, the focus is always placed on the most likely pollution source direction to avoid ineffective investment of resources on low-probability paths, achieving effective control of tracing costs and maximization of investigation effects.

[0113] In another embodiment of the present invention, a smart runoff pollution monitoring and response system is provided, comprising:

[0114] The monitoring network module is used to arrange multiple monitoring points in the runoff area. Each monitoring point is equipped with a water quality sensor, a hydrological sensor, and a meteorological data sensor to collect the water quality parameters, hydrological parameters, and meteorological data of the runoff in real time, and transmit the collected data to the data processing center through the wireless sensor network; the data processing and analysis module is used to receive the data from the monitoring network module, preprocess, store, analyze, and process the data to evaluate the pollution index of each monitoring point, identify the key water quality parameters, and conduct parameter-level evaluation on these key water quality parameters; the alarm trigger module is used to set the pollution threshold. According to the pollution index and the evaluation results of the key water quality parameters provided by the data processing and analysis module, once it is found that the runoff exceeds the preset pollution threshold, the alarm mechanism is triggered; the pollution source tracking module, once the alarm trigger module issues an alarm, the pollution source tracking module combines the pipe network water flow model and the geographic information system to inversely track the pollution source, and locates the pollution source area by analyzing the flow rate and water quality changes of each monitoring point; the user interface module is used to provide the user with a system operation interface, display the monitoring data, analysis results, alarm information, and pollution source tracking results, and allow the user to perform parameter settings and system configurations.

[0115] The monitoring network module includes a monitoring point layout sub-module, which is used to determine the monitoring point locations according to the terrain, landform, water flow characteristics, land use types, and potential pollution sources in the runoff area; a data collection and transmission sub-module, which is used to install sensors at each monitoring point, automatically collect data at preset time intervals, and transmit the data to the data processing center through the wireless sensor network.

[0116] The data processing and analysis module includes a data preprocessing sub-module, which is used to perform preprocessing operations on the received raw data, such as data cleaning, format conversion, etc., and store the preprocessed data in a distributed database; a pollution index evaluation sub-module, which is used to generate a comprehensive pollution index for each monitoring point and compare it with the set index threshold to evaluate the pollution degree; a key water quality parameter identification and evaluation sub-module, which is used to select the key water quality parameters highly correlated with the pollution index through correlation analysis and principal component analysis when the pollution index exceeds the index threshold, and evaluate the concentration change and concentration change rate of these parameters.

[0117] The alarm trigger module includes an alarm rule setting sub-module, which is used to set the thresholds of the first-order difference, second-order difference, key water quality parameter concentration, and comprehensive pollution index; an alarm level determination sub-module, which is used to determine the alarm level according to the data provided by the data processing and analysis module and trigger the corresponding alarm mechanism.

[0118] The pollution source tracking module further includes a pipe network water flow model construction sub-module, which is used to construct a pipe network water flow model based on the design drawings, pipe diameters, pipe lengths, and slope information of the drainage pipe network by applying hydraulic principles; a geographic information system integration sub-module, which is used to integrate the topographic features, land use types, and geographical location data of the drainage pipe network in the geographic information system with the pipe network water flow model and display the pipe network layout in the form of a map layer; and a pollution path backtracking sub-module, which is used to start from the node with excessive pollution and backtrack the pollution source in the reverse direction, and locate the pollution source area by analyzing the flow rate and water quality changes at each monitoring point.

[0119] The pollution path backtracking sub-module includes a suspected pollution source node screening sub-module, which is used to screen the nodes with increased flow rate and increased concentration of key water quality parameters among the upstream adjacent nodes as suspected pollution source propagation nodes; a path probability calculation sub-module, which is used to calculate the path probability of the key water quality parameter propagating from the suspected node to the pollution node according to the pipe section length, water flow velocity, and attenuation coefficient of the key water quality parameter between the suspected node and the pollution node; and a sorting and backtracking sub-module, which is used to sort the suspected nodes, prioritize the investigation of the path and nodes with the highest probability, and continuously backtrack the pollution path upstream until the source of the pipe network or the path probability is less than the preset value.

[0120] The above embodiments are only illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. All equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. Intelligent runoff pollution monitoring and response method, characterized in that: The following steps are involved: S1, multiple monitoring points are arranged in the runoff area, and sensors are used to collect water quality parameters, hydrological parameters and meteorological data of the runoff in real time, and the collected data are transmitted to the data processing center using a wireless sensor network; S2, the data processing center analyzes and processes the collected data, evaluates the pollution index of each monitoring point according to the processing results, analyzes the key water quality parameters that are highly correlated with runoff pollution for the monitoring points whose pollution index exceeds the index threshold, and performs parameter-level evaluation on these key water quality parameters; S3, setting a parameter threshold according to the parameter level assessment, wherein the parameter threshold and the index threshold are both regarded as pollution thresholds. Once the runoff exceeds the preset pollution threshold, it is regarded as an abnormal situation and triggers an alarm mechanism; S4, once the alarm mechanism is triggered, the water flow model of the pipe network and the geographic information system are combined to trace the source of pollution in reverse, and the pollution source area is located by analyzing the flow and water quality changes at each monitoring point; The S1 includes: S11, determine the location of monitoring points based on the topography, landforms, flow characteristics, land use type and potential pollution sources in the runoff area; S12, water quality sensors, hydrological sensors and meteorological data sensors are installed at each monitoring point, and data are automatically collected at preset time intervals to ensure that the data collection timestamps of each monitoring point are consistent; S13, the data processing center establishes an efficient data receiving interface for simultaneously processing a large amount of raw runoff data from multiple monitoring points, and after preprocessing the raw runoff data, stores the preprocessed runoff data in a distributed database; The S4 includes: Based on the detailed design drawings, pipe diameter, pipe length, and slope information of the drainage pipe network, a pipe network water flow model is constructed using hydraulic principles. In the pipe network water flow model, the pipe network is divided into pipe sections for water flow transportation and nodes for water flow convergence or diversion, and the nodes are used as monitoring points; The topography, land use type, and geographic location data of the drainage network in the geographic information system are integrated with the water flow model of the network. In the geographic information system, the network layout is displayed in the form of a map layer, and each node is associated with the surrounding geographical environment information. Among all the monitored node data, the set of nodes with excessive pollution is screened out according to the set pollution threshold P = {p1, p2, ..., p k }, using these pollution nodes as the starting point for tracing back to the source of pollution; The method for reversely tracing the pollution source is as follows: B1, for each polluted node p i ∈P, trace back to its upstream adjacent node j, and calculate node p i The flow difference between j and ij =q i -q j and water quality parameter concentration change rate If ΔQ ij >0 and This indicates that the key water quality parameters are moving from upstream node j to node p i Transmission, at the same time, mark node j as a suspected pollution source transmission node and add it to the suspected node set Z = {z1, z2, ..., z l }, where q i is the polluted node p i The flow rate, q j For the p i The traffic of neighboring node j, Represents the polluted node p i The concentration of the sth key water quality parameter in represents the concentration of the sth key water quality parameter in node j; B2, according to the suspected node z j ∈Z and polluted node p i The length of the pipe section between ij , water velocity v ij , the attenuation coefficient λ of the sth key water quality parameter s , calculate the key water quality parameters s from node z j Propagate to node p i The path probability is calculated as follows: Among them, Pr(z j →p i ) represents the slave node z j To node p i The path probability, represents the weighted sum of all possible paths; B3, sort the path probabilities from large to small, and sort the nodes in the suspected node set Z according to the sorting results; B4, take the node with the highest probability in the suspected node set Z as the new starting point, repeat steps B1-B3, continue to trace the pollution path upstream, and update the suspected node set Z and the path probability distribution until the source of the pipe network or Pr(z j →p i ) is less than the preset value Pr min .

2. The intelligent runoff pollution monitoring and response method according to claim 1 is characterized in that: The S2 includes: S21, the data processing center obtains the pre-processed runoff data of each monitoring point from the distributed database, and generates a comprehensive pollution index for each monitoring point; S22, compare the comprehensive pollution index with the set index threshold. Once the comprehensive pollution index is greater than the index threshold, the key water quality parameters that are highly correlated with runoff pollution are selected through correlation analysis and principal component analysis, and the concentration change amount and concentration change rate of these key water quality parameters in the set time step are evaluated.

3. The intelligent runoff pollution monitoring and response method according to claim 2 is characterized in that: The S21 includes: S211, determine relevant water quality parameters of runoff pollution and set weights for each relevant water quality parameter based on historical data, water quality standards and expert opinions; S212, performing standardization processing on various relevant water quality parameters, wherein the standardization processing method is as follows: Among them, X i is the original value of the i-th relevant water quality parameter, X min is the minimum value of the i-th relevant water quality parameter, X max is the maximum value of the i-th relevant water quality parameter, X′ i is the standardized value of the i-th relevant water quality parameter; S213, using a weighted average method to calculate the comprehensive pollution index of each monitoring point, the comprehensive pollution index is obtained as follows: Among them, CPI is the comprehensive pollution index, w i is the weight of the i-th relevant water quality parameter, X′ i is the standardized value of the i-th relevant water quality parameter, and n is the number of relevant water quality parameters.

4. The intelligent runoff pollution monitoring and response method according to claim 3 is characterized in that: The S22 includes: If the comprehensive pollution index is greater than the index threshold, the key water quality parameters highly correlated with runoff pollution are selected through correlation analysis and principal component analysis, and the first-order difference of the key water quality parameters is calculated to measure the concentration change of the key water quality parameters. The first-order difference calculation method is as follows: ΔX t =X t -X t-1 Where ΔX t is the first-order difference of the key water quality parameter, X t is the concentration of the key water quality parameter at time t, X t-1 is the concentration of key water quality parameters at time point t-1; According to the first-order difference, the second-order difference of the key water quality parameter is calculated to measure the concentration change rate of the key water quality parameter. The second-order difference calculation method is as follows: Δ 2 X t =ΔX t -ΔX t-1 =(X t -X t-1 )-(X t-1 -X t-2 ) Among them, Δ 2 X t is the second-order difference of key water quality parameters, X t-2 is the concentration of the key water quality parameter at time point t-2.

5. The intelligent runoff pollution monitoring and response method according to claim 4 is characterized in that: The S22 further includes: Using the first-order difference and the second-order difference as independent variables, a concentration prediction model is constructed to predict the concentration of key water quality parameters at time point t+1. The concentration prediction model is as follows: Y t+1 =β0+β1×ΔX t +β2×Δ 2 X t +∈ t Among them, Y t+1 is the predicted concentration of the key water quality parameter at time point t+1; β0 is the intercept term, which indicates the baseline concentration level of the key water quality parameter; β1 is the regression coefficient of the first-order difference, β2 is the regression coefficient of the second-order difference, ∈ t is the error term.

6. The intelligent runoff pollution monitoring and response method according to claim 5 is characterized in that: The S3 includes: Set the upper threshold of the first-order difference ΔX max , if ΔX t ≥ΔX max , it is identified as a level 1 alarm; Set the upper threshold of the second-order difference Δ 2 X max , if Δ 2 X t ≥Δ 2 X max , it is identified as a level 2 alarm; Set the concentration of key water quality parameter Y t+1 The upper threshold value Y max , if Y t+1 ≥Y max , it is identified as a level 3 alarm; Set the upper threshold of the comprehensive pollution index CPI max , if CPI ≥ CPI max , it is identified as a level 4 alarm.

7. A system for implementing the method according to any one of claims 1 to 6, characterized in that: include: The monitoring network module is used to arrange multiple monitoring points in the runoff area. Each monitoring point is equipped with a water quality sensor, a hydrological sensor and a meteorological data sensor to collect the water quality parameters, hydrological parameters and meteorological data of the runoff in real time, and transmit the collected data to the data processing center through a wireless sensor network; A data processing and analysis module is used to receive data from the monitoring network module, pre-process, store, analyze and process the data to evaluate the pollution index of each monitoring point, identify key water quality parameters, and perform parameter-level evaluation on these key water quality parameters; The alarm trigger module is used to set the pollution threshold. According to the pollution index and key water quality parameter evaluation results provided by the data processing and analysis module, once the runoff exceeds the preset pollution threshold, the alarm mechanism is triggered; Pollution source tracking module: Once the alarm trigger module issues an alarm, the pollution source tracking module combines the pipe network water flow model with the geographic information system to reversely track the source of pollution and locate the pollution source area by analyzing the flow and water quality changes at each monitoring point; The user interface module is used to provide users with a system operation interface, display monitoring data, analysis results, alarm information and pollution source tracking results, and allow users to set parameters and configure the system.

Images