Method for detecting water pollution in concealed conduit drainage well and water pollution monitor

Abstract

The invention provides a method for detecting water pollution in a concealed conduit drainage well and a water pollution monitor. The water pollution concentration of each detection node in the concealed conduit drainage well is detected through an intelligent water quality sensor; determining the mutual support degree of the water pollution detection results among the intelligent water quality sensors according to the cross correlation coefficient of the water pollution concentrations among the different detection nodes and the spatial topological structure of the intelligent water quality sensors; performing fuzzy evaluation on the layered interference effect intensity of water pollution detection at different depths through the vertical concentration gradient of water pollution in the concealed conduit drainage well and the local flow velocity of water at different depths to obtain interference evaluation indexes of water pollution detection at different depths; and performing cost fusion on the water pollution concentration of each detection node based on all the mutual support degrees and the interference evaluation indexes of the water pollution detection at different depths to obtain the fused pollution degree of the water pollution. By adopting the scheme of the invention, the cost fusion of multi-source information in the concealed conduit drainage well water pollution detection process can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of water pollution detection. More specifically, the present application relates to a method for detecting water pollution in a concealed pipe drainage well and a water pollution monitor. Background Art

[0002] Water pollution detection is an important link in ensuring the quality of water environment and the safety of public health. Especially in the urban drainage system, pollutants are discharged into the drainage well through underground concealed pipes, often causing deterioration of the local water quality and even triggering ecological disasters. In order to timely grasp the pollution diffusion situation, carrying out efficient and accurate water pollution monitoring has become a key task in the current urban water environment management. Traditional water quality detection mostly relies on fixed-point sampling or manual inspection, with low efficiency and limited coverage, and it is difficult to cope with the spatial heterogeneity and dynamic change trend of pollutant distribution in underground drainage wells. Therefore, establishing a multi-point pollution detection technology system based on intelligent perception and information fusion has become an important direction for improving the intelligent and refined level of pollution monitoring.

[0003] In the prior art, the existing water pollution detection methods generally have the problem of strong dependence on single-point detection, that is, most technologies only collect data from single or a few detection nodes, lacking comprehensive consideration of the detection relationship between sensors and spatial interference factors. When facing complex underground water flow disturbances and vertical distribution changes of pollutants, such methods are prone to large deviations in the overall detection results due to node anomalies or position offsets, and it is difficult to truly reflect the overall pollution situation of the drainage well. In addition, due to the lack of a key information interaction and fusion mechanism between detection nodes, the correlation characteristics and complementary advantages between multi-source detection data cannot be fully exploited, resulting in one-sided evaluation results of pollution concentration and being difficult to provide reliable support for the accurate identification, tracing and treatment of water pollution. Therefore, how to achieve the cost fusion of multi-source information in the process of detecting water pollution in a concealed pipe drainage well to enhance the accuracy of the overall detection result has become a difficult problem faced by the industry. Summary of the Invention

[0004] The present application provides a method for detecting water pollution in a concealed pipe drainage well and a water pollution monitor, which can achieve the cost fusion of multi-source information in the process of detecting water pollution in a concealed pipe drainage well.

[0005] In a first aspect, the present application provides a method for detecting water pollution in a concealed pipe drainage well, including the following steps: Deploy a plurality of detection nodes and intelligent water quality sensors in a target concealed pipe drainage well, detect the water pollution data of each detection node through the intelligent water quality sensors, and then extract the water pollution concentration of each detection node; Determine the cross - correlation coefficient of water pollution concentration between different detection nodes according to the water pollution data of each detection node in the historical time period, and then determine the mutual support degree of water pollution detection results between each intelligent water quality sensor through all the cross - correlation coefficients and the spatial topology structure of the intelligent water quality sensors; Extract the vertical concentration gradient of water pollution in the target hidden pipe drainage well, and conduct a fuzzy evaluation on the intensity of the layered interference effect of water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of water bodies at different depths, so as to obtain the interference evaluation index of water pollution detection at different depths; Based on all the mutual support degrees and the interference evaluation indexes of water pollution detection at different depths, conduct cost fusion on the water pollution concentration of each detection node to obtain the fusion pollution degree of water pollution, and then use the fusion pollution degree as the pollution degree of the water body in the target hidden pipe drainage well.

[0006] Preferably, the water pollution data of each detection node is detected by an intelligent water quality sensor, and then the extraction of the water pollution concentration of each detection node specifically includes: For each detection node, the intelligent water quality sensor is used to collect the water pollution data of the detection node in real time; Perform smoothing processing on the collected water pollution data, eliminate outliers and noise interference information to obtain the smoothed water pollution data; Extract the water pollution concentration of the detection node from the smoothed water pollution data through a preset pollutant concentration calculation model, and then obtain the water pollution concentration of each detection node.

[0007] Preferably, determining the cross - correlation coefficient of water pollution concentration between different detection nodes according to the water pollution data of each detection node in the historical time period specifically includes: For every two detection nodes, perform time alignment processing on the water pollution data of the two detection nodes in the historical time period to obtain a time - aligned water pollution data group; Based on the time - aligned water pollution data group, conduct cross - correlation analysis on the water pollution concentration between the two detection nodes to obtain the cross - correlation coefficient of water pollution concentration between the two detection nodes, and then obtain the cross - correlation coefficient of water pollution concentration between every two detection nodes.

[0008] Preferably, determining the mutual support degree of water pollution detection results between each intelligent water quality sensor through all the cross - correlation coefficients and the spatial topology structure of the intelligent water quality sensors specifically includes: For every two intelligent water quality sensors, determine the confidence distance between the two intelligent water quality sensors according to the spatial topology structure of the intelligent water quality sensors; Associate and support the evaluation of the consistency of water pollution detection results between two intelligent water quality sensors through all cross - correlation coefficients and the confidence distance, obtain the mutual support degree of water pollution detection results between the two intelligent water quality sensors, and further obtain the mutual support degree of water pollution detection results between every two intelligent water quality sensors.

[0009] Preferably, extracting the vertical concentration gradient of water pollution in the target concealed pipe drainage well specifically includes: Divide the detection nodes into at least three detection layers in the vertical direction and obtain the pollutant concentrations of each layer; Perform cubic spline interpolation on the water pollution concentration in the vertical direction based on the concentration differences between adjacent detection layers to generate a continuous vertical concentration distribution curve; Determine the first - order derivative of the vertical concentration distribution curve within a preset depth interval, and extract the maximum gradient value as the vertical concentration gradient of water pollution in the target concealed pipe drainage well.

[0010] Preferably, performing a fuzzy evaluation on the stratification interference effect intensity of water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of water at different depths, and obtaining the interference evaluation index of water pollution detection at different depths specifically includes: Initialize the initial membership degrees of the interference effects of detection layers at different depths; Construct an interference effect intensity matrix between each detection layer based on the vertical concentration gradient and the local flow velocity of water at different depths; Map the values in the interference effect intensity matrix to a fuzzy set through a fuzzy membership function; Construct a fuzzy interference evaluation matrix based on all the initial membership degrees and the fuzzy set; Perform a fuzzy evaluation on the interference effect intensity of each detection layer based on the fuzzy interference evaluation matrix to obtain the interference evaluation index of water pollution detection corresponding to each detection layer.

[0011] Preferably, the intelligent water quality sensor refers to an integrated sensing device with multi - parameter water quality perception ability, data pre - processing function, and communication module.

[0012] In a second aspect, the present application provides a water pollution monitor, which includes a water pollution detection unit, and the water pollution detection unit includes: A detection module, which is used to detect the water pollution data of each detection node through an intelligent water quality sensor, and further extract the water pollution concentration of each detection node; A processing module, which is used to determine the cross - correlation coefficient of the water pollution concentration between different detection nodes according to the water pollution data of each detection node in a historical time period, and further determine the mutual support degree of water pollution detection results between each intelligent water quality sensor through all the cross - correlation coefficients and the spatial topology structure of the intelligent water quality sensors; The processing module is further configured to extract the vertical concentration gradient of water pollution in the target buried pipe drainage well, and perform a fuzzy evaluation on the intensity of the layered interference effect of water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of water bodies at different depths, so as to obtain the interference evaluation index of water pollution detection at different depths; The execution module is configured to perform cost fusion on the water pollution concentrations of each detection node based on all the mutual support degrees and the interference evaluation indexes of water pollution detection at different depths, so as to obtain the fused pollution degree of water pollution, and further use the fused pollution degree as the pollution degree of the water body in the target buried pipe drainage well.

[0013] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned method for detecting water pollution in a buried pipe drainage well.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned method for detecting water pollution in a buried pipe drainage well is implemented.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In the embodiments of the present application, a plurality of detection nodes and intelligent water quality sensors are arranged in the target buried pipe drainage well. The water pollution data of each detection node is detected by the intelligent water quality sensors, and then the water pollution concentration of each detection node is extracted; the cross-correlation coefficient between the water pollution concentrations of different detection nodes is determined according to the water pollution data of each detection node in the historical time period, and then the mutual support degree of the water pollution detection results between each intelligent water quality sensor is determined through all the cross-correlation coefficients and the spatial topology structure of the intelligent water quality sensors; the vertical concentration gradient of water pollution in the target buried pipe drainage well is extracted, and a fuzzy evaluation is performed on the intensity of the layered interference effect of water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of water bodies at different depths, so as to obtain the interference evaluation index of water pollution detection at different depths; cost fusion is performed on the water pollution concentrations of each detection node based on all the mutual support degrees and the interference evaluation indexes of water pollution detection at different depths, so as to obtain the fused pollution degree of water pollution, and further use the fused pollution degree as the pollution degree of the water body in the target buried pipe drainage well.

[0016] It can be seen that this application performs cost fusion on the water pollution concentrations of each detection node based on all mutual support degrees and interference evaluation indices for water pollution detection at different depths, obtaining the fused pollution degree of water pollution. First, by deploying multiple intelligent water quality sensor nodes in the drainage well, the problem of strong dependence on single-point detection in traditional methods is overcome, ensuring wide coverage of water quality information at different spatial positions and providing a basic guarantee for subsequent multi-source data fusion. Second, by introducing historical data to calculate the cross-correlation coefficient between each detection node and combining the spatial topology structure of the sensors, an evaluation system for the mutual support degree of water quality detection results between nodes is further established, effectively revealing the correlation and consistency relationship between the detection results of nodes and enabling quantitative evaluation of the credibility of the detection data. Then, by extracting the vertical concentration gradient and local water body flow velocity information, constructing an interference effect intensity matrix, and using the fuzzy evaluation method to calculate the interference evaluation index, quantitative discrimination of the reliability of pollution data under vertical disturbance conditions of the water body is realized, enhancing the response ability of the model to the characteristics of water body stratified pollution. Finally, all mutual support degrees and interference evaluation indices for water pollution detection at different depths are introduced into the fusion cost function, with the fusion weight of the water pollution concentration at the detection node as the optimization variable, and the fusion cost function is iteratively solved through the genetic algorithm to achieve cost fusion between detection data, not only solving the redundancy and conflict problems existing in multi-source data, but also fully retaining the effective information provided by sensors at different depths and positions, thereby obtaining a pollution concentration expression result that more conforms to the actual situation. In summary, the solution of this application can achieve cost fusion of multi-source information in the process of water pollution detection in the concealed pipe drainage well, thereby improving the detection accuracy of water pollution in the concealed pipe drainage well. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is an exemplary flowchart of a method for detecting water pollution in a concealed pipe drainage well according to some embodiments of the present application; Figure 2 is a schematic diagram of an application scenario for detecting water pollution in a concealed pipe drainage well according to some embodiments of the present application; Figure 3 is a schematic flowchart for determining the vertical concentration gradient according to some embodiments of the present application; Figure 4 is a schematic structural diagram of a water pollution detection unit according to some embodiments of the present application; Figure 5 is a schematic structural diagram of a computer device for implementing the method for detecting water pollution in a concealed pipe drainage well according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0019] Reference Figure 1 , which is an exemplary flowchart of the water pollution detection method in the underground pipe drainage well shown in some embodiments of the present application. The water pollution detection method 100 in the underground pipe drainage well mainly includes the following steps: In step 101, a plurality of detection nodes and intelligent water quality sensors are arranged in the target underground pipe drainage well. The water pollution data of each detection node is detected by the intelligent water quality sensors, and then the water pollution concentration of each detection node is extracted.

[0020] It should be noted that in the present application, the underground pipe drainage well refers to an inspection well or catch basin that collects and discharges water bodies through underground closed pipes, and is mainly used for the collection, guidance, and detection of water flow in the urban drainage system; specifically, arranging a plurality of detection nodes and intelligent water quality sensors in the target underground pipe drainage well can be achieved by the following method, that is: according to the structural form, water flow path, and pollution distribution characteristics of the drainage well, representative detection positions are selected, nodes are arranged in layers in the vertical direction to cover water bodies at different depths, and nodes are arranged in combination with the main water flow channel and key positions such as bends and confluence inlets in the horizontal direction to capture pollution sources and change trends. An intelligent water quality sensor is installed at each detection node. The intelligent water quality sensor specifically includes:, and is connected to a unified data transmission system through a data acquisition module.

[0021] In some embodiments, reference Figure 2 shown, which is a schematic diagram of the application scenario of water pollution detection in the underground pipe drainage well in some embodiments of the present application. Among them, a plurality of intelligent water quality sensors 120 are installed in the underground pipe drainage well 110. The intelligent water quality sensors are responsible for collecting water quality data in the drainage well, and further transmitting the collected water quality data to the data processor 130 through a data line. By executing the data processing program of the water pollution detection unit by the data processor, the detection result of water pollution in the underground pipe drainage well is obtained, and the detection result is visually displayed through the visualization module 140, which is convenient for users to view and analyze through a computer device.

[0022] It should be noted that the intelligent water quality sensor in the present application refers to an integrated sensing device with multi-parameter water quality perception ability, data preprocessing function, and communication module, which can real-time monitor pollution-related physical or chemical parameters (such as chemical oxygen demand, ammonia nitrogen, turbidity) in water bodies. The intelligent water quality sensor includes a fluorescence method chemical oxygen demand sensor module, an electrochemistry type ammonia nitrogen sensor module, and an optical turbidity sensor module.

[0023] In some embodiments, the water pollution data of each detection node is detected by the intelligent water quality sensors, and then the water pollution concentration of each detection node is extracted, which can be achieved by the following steps: For each detection node, the water pollution data of the detection node is collected in real time by an intelligent water quality sensor; The collected water pollution data is smoothed to remove outliers and noise interference information, and the smoothed water pollution data is obtained; The water pollution concentration of the detection node is extracted from the smoothed water pollution data through a preset pollutant concentration calculation model, and then the water pollution concentrations of all detection nodes are obtained.

[0024] When specifically implemented, the smoothing process of the collected water pollution data to remove outliers and noise interference information and obtain the smoothed water pollution data can be achieved in the following way, that is: the collected water pollution data is transmitted to an edge computing device or a remote processing center, and the original data is smoothed. A common method is the moving average method, that is, the mean value within a set time window is used to replace the current data point to suppress short-term fluctuations. At the same time, the 3σ principle (that is, the mean ± 3 times the standard deviation) is combined to remove mutation outliers, and the smoothed water pollution data is obtained; the water pollution concentration of the detection node is extracted from the smoothed water pollution data through a preset pollutant concentration calculation model, and then the water pollution concentrations of all detection nodes can be achieved in the following way, that is: the smoothed water pollution data is input into a preset pollutant concentration calculation model. This pollutant concentration calculation model is constructed based on a large amount of experimental data and can adopt a linear regression model or a multi-variable mapping model. For example, by establishing a regression equation between "chemical oxygen demand - ammonia nitrogen - turbidity", the physical parameters are converted into the water pollution concentration of the detection node.

[0025] It should be noted that the pollutant concentration calculation model in this application refers to a mapping model used to convert the multi-parameter original water quality data collected by an intelligent water quality sensor into pollutant concentration values. Its technical principle is based on the stable functional relationship between pollutant concentration and multiple sensing parameters (such as chemical oxygen demand, ammonia nitrogen, turbidity). Through a large number of experimental samples, a statistical or machine learning model is established to complete parameter fitting and feature extraction. Common models include multiple linear regression, support vector regression or neural network models. The input is a multi-water quality parameter vector, and the output is the concentration estimate value of the target pollution factor. This model is trained offline and deployed to a device or server to achieve the rapid conversion of sensing data to pollution concentration; in addition, through the pollutant concentration calculation model in this application, multiple pollution parameters can be integrated into an evaluation index of water pollution.

[0026] In step 102, according to the water pollution data of each detection node in the historical time period, the cross-correlation coefficient between the water pollution concentrations of different detection nodes is determined, and then the mutual support degree of the water pollution detection results between each intelligent water quality sensor is determined through all the cross-correlation coefficients and the spatial topology structure of the intelligent water quality sensors.

[0027] In some embodiments, to determine the cross-correlation coefficient of the water pollution concentration between different detection nodes based on the water pollution data of each detection node in a historical time period, the following steps can be adopted: For every two detection nodes, perform time alignment processing on the water pollution data of the two detection nodes in the historical time period to obtain a group of time-aligned water pollution data; Based on the group of time-aligned water pollution data, perform cross-correlation analysis on the water pollution concentration between the two detection nodes to obtain the cross-correlation coefficient of the water pollution concentration between the two detection nodes, and further obtain the cross-correlation coefficient of the water pollution concentration between every two detection nodes.

[0028] It should be noted that in this application, the cross-correlation coefficient is an index to measure the similarity degree of the change trends of the water pollution concentrations of two detection nodes.

[0029] In specific implementation, for any two detection nodes, first, to perform time alignment processing on the water pollution data of the two detection nodes in the historical time period to obtain a group of time-aligned water pollution data, the following method can be adopted, that is: retrieve the water pollution data sequences of each detection node in the unified historical time period, and realize time synchronization through the time stamp alignment method. Specifically, select a common time reference point, and perform interpolation or downsampling processing on the data of the two nodes at a fixed sampling period (such as once every 2 minutes) to ensure that each pair of nodes forms a group of one-to-one corresponding time series, and use the processed data as the group of time-aligned water pollution data; to perform cross-correlation analysis on the water pollution concentration between the two detection nodes based on the group of time-aligned water pollution data to obtain the cross-correlation coefficient of the water pollution concentration between the two detection nodes, the following method can be adopted, that is: for each group of time-aligned data sequences, calculate using the Spearman rank correlation coefficient. The specific method is to respectively calculate the mean, variance and covariance of the two sequences, and divide the covariance by the product of the two standard deviations to obtain the Pearson correlation coefficient with a value range between -1 and 1, and then use the calculated Pearson correlation coefficient as the cross-correlation coefficient of the water pollution concentration between the two detection nodes.

[0030] In some embodiments, to determine the mutual support degree of the water pollution detection results between each intelligent water quality sensor through all the cross-correlation coefficients and the spatial topology structure of the intelligent water quality sensors, the following steps can be adopted: For every two intelligent water quality sensors, determine the confidence distance between the two intelligent water quality sensors according to the spatial topology structure of the intelligent water quality sensors; Perform an associated support evaluation on the consistency of the water pollution detection results between the two intelligent water quality sensors through all the cross-correlation coefficients and the confidence distance to obtain the mutual support degree of the water pollution detection results between the two intelligent water quality sensors, and further obtain the mutual support degree of the water pollution detection results between every two intelligent water quality sensors.

[0031] It should be noted that the mutual support degree in this application is a reliability evaluation index for measuring the reliability of water pollution detection results between two intelligent water quality sensors in terms of spatial proximity and concentration correlation.

[0032] When specifically implemented, for every two intelligent water quality sensors, first, the confidence distance between the two intelligent water quality sensors can be determined according to the spatial topological structure of the intelligent water quality sensors in the following way, that is: obtain the spatial distance between the two intelligent water quality sensors from the spatial topological structure of the intelligent water quality sensors, and then use the natural exponential function value of the opposite number of the spatial distance as the confidence distance between the two intelligent water quality sensors. This confidence distance reflects the spatial proximity of the sensors, and the water quality measured by adjacent sensors should be more relevant; second, the consistency of the water pollution detection results between the two intelligent water quality sensors can be evaluated by associative support through all cross-correlation coefficients and the confidence distance, and the mutual support degree of the water pollution detection results between the two intelligent water quality sensors can be implemented in the following way, that is: obtain the cross-correlation coefficient of the water pollution concentration between the corresponding detection nodes of the two intelligent water quality sensors, and use the product of the cross-correlation coefficient and the confidence distance as the mutual support degree of the water pollution detection results between the two intelligent water quality sensors.

[0033] In step 103, extract the vertical concentration gradient of water pollution in the target concealed pipe drainage well, and perform a fuzzy evaluation on the intensity of the layered interference effect of water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of water bodies at different depths, to obtain the interference evaluation index of water pollution detection at different depths.

[0034] In some embodiments, as shown in Figure 3 This figure is a schematic flow chart for determining the vertical concentration gradient in some embodiments of this application. In this embodiment, the vertical concentration gradient of water pollution in the target concealed pipe drainage well can be extracted by the following steps: In step 1031, divide the detection nodes into at least three detection layers in the vertical direction, and obtain the pollutant concentration of each layer; In step 1032, perform cubic spline interpolation on the water pollution concentration in the vertical direction based on the concentration difference between adjacent detection layers to generate a continuous vertical concentration distribution curve; In step 1033, determine the first derivative of the vertical concentration distribution curve within a preset depth interval, and extract the maximum gradient value as the vertical concentration gradient of water pollution in the target concealed pipe drainage well.

[0035] It should be noted that in this application, cubic spline interpolation constructs a cubic polynomial between adjacent data points to ensure the continuity of the interpolation curve in terms of numerical values, as well as first and second derivatives, achieving a smooth transition of the curve and effectively eliminating the mutation phenomenon caused by uneven detection node spacing or data fluctuations. The vertical concentration gradient in this application is an index to measure the change rate of pollutant concentration in the vertical direction of water bodies. The vertical concentration distribution curve in this application refers to a smooth curve representing the continuous change of pollutant concentration in water bodies with depth.

[0036] In specific implementation, first, the detection nodes are divided into at least three detection layers in the vertical direction. The pollutant concentration of each layer can be obtained in the following way: that is, the detection nodes arranged along the vertical direction of the drainage well can be divided into at least three detection layers according to depth, and the pollutant concentrations of all detection nodes in each layer are respectively counted and averaged, and this average value is used as the pollutant concentration of the corresponding detection layer. Then, based on the concentration difference between adjacent detection layers, cubic spline interpolation is performed on the water pollution concentration in the vertical direction, and a continuous vertical concentration distribution curve can be generated in the following way: that is, the concentration difference between adjacent detection layers is used as the mean feature of the node data items of the cubic spline interpolation algorithm. The water pollution concentration of the vertical detection nodes is calculated through the cubic spline interpolation algorithm, and the interpolated output curve is used as the vertical concentration distribution curve. This cubic spline interpolation algorithm constructs a cubic polynomial between every two adjacent data points, making the interpolation curve not only continuous in concentration values, but also ensuring the continuity of the first and second derivatives, thereby generating a smooth continuous vertical concentration distribution curve that can eliminate the mutation caused by uneven node spacing or data fluctuations. Finally, the first derivative of the vertical concentration distribution curve within a preset depth interval is determined, and the maximum gradient value is extracted as the vertical concentration gradient of water pollution in the target concealed pipe drainage well, which can be achieved in the following way: that is, based on the vertical concentration distribution curve, concentration values are uniformly sampled at preset depth intervals (such as every 0.1 meter), and the numerical first derivative is calculated by dividing the concentration difference between adjacent sampling points by the depth interval. The first derivative reflects the change rate of concentration with depth. By traversing the first derivatives of all sampling points, the maximum value among them is extracted as the vertical concentration gradient of water pollution in the concealed pipe drainage well. The vertical concentration gradient represents the maximum change amplitude of water pollution concentration in the vertical direction.

[0037] In some embodiments, the fuzzy evaluation of the stratification interference effect intensity of water pollution detection at different depths can be carried out according to the vertical concentration gradient and the local flow velocity of water bodies at different depths, and the interference evaluation index of water pollution detection at different depths can be obtained by the following steps: Initialize the initial membership degree of the interference effect of different depth detection layers; Construct an interference effect intensity matrix between each detection layer based on the vertical concentration gradient and the local flow velocity of water bodies at different depths; Map the numerical values in the interference effect intensity matrix into a fuzzy set through a fuzzy membership function; Construct a fuzzy interference evaluation matrix based on all the initial membership degrees and the fuzzy set; Conduct a fuzzy evaluation on the interference effect intensity of each detection layer based on the fuzzy interference evaluation matrix to obtain the interference evaluation index for water pollution detection corresponding to each detection layer.

[0038] It should be noted that the initial membership degree in this application refers to the preliminary quantitative attribution degree representing the interference effect intensity of each detection layer; the interference effect intensity matrix in this application refers to the relationship matrix reflecting the mutual interference degree of water pollution detection between different detection layers; the fuzzy interference evaluation matrix in this application refers to the evaluation matrix used to comprehensively evaluate the interference influence of each detection layer after converting the interference effect intensity into a fuzzy set through a fuzzy membership function; the interference evaluation index in this application refers to the index that quantitatively represents the interference intensity of water pollution detection of each detection layer based on the fuzzy evaluation result.

[0039] In specific implementation, first, the initial membership degrees of the interference effects of different depth detection layers can be initialized in the following manner: retrieve the historical water quality monitoring records of the target subsurface drainage well at different water depth levels, extract the index data related to the interference intensity such as the concentration fluctuation frequency, disturbance amplitude, mutation time point, etc., then set a group of empirical rules based on the number of significant concentration changes of each detection layer in the historical data (for example, the higher the change frequency, the greater the initial membership degree), and then combine the grade division in the rule base (for example, the three grades of low, medium, and high respectively correspond to different membership degree value intervals), and use a membership degree assignment function (such as a linear piecewise function) to perform an initial membership degree mapping on the interference effect of each layer to obtain the initial membership degrees of the interference effects of each detection layer; second, the interference effect intensity matrix between each detection layer can be constructed based on the vertical concentration gradient and the local flow velocity of the water at different depths in the following manner: the detection nodes arranged can be divided into at least three detection layers according to the depth in the vertical direction of the drainage well, and the corresponding vertical concentration gradient value and local flow velocity value of each layer are obtained. According to the preset interference effect evaluation rule, the potential interference intensity caused by the concentration change amplitude and flow velocity difference between any two detection layers is calculated respectively. This rule can adopt a linear superposition model, that is, the interference intensity is synthesized by weighting the concentration gradient difference and the flow velocity difference. The interference intensity values between each detection layer and other layers are calculated in turn, and all the calculation results are filled into a two-dimensional matrix according to the layer combination, and this two-dimensional matrix is used as the interference effect intensity matrix. It should be further noted that in this application, the interference effect intensity matrix also needs to be normalized to ensure that its values meet the input requirements of the fuzzy evaluation system; third, the values in the interference effect intensity matrix can be mapped into a fuzzy set through a fuzzy membership function in the following manner: based on the qualitative evaluation grades (such as "weak interference", "medium interference", "strong interference") corresponding to the values in the interference effect intensity matrix, use a fuzzy membership function (such as a triangular membership function) to map each value in the interference effect intensity matrix into the membership degree value of the corresponding evaluation grade in the fuzzy set, and construct a fuzzy membership degree set to represent the membership degree of the interference intensity grade; then, the fuzzy interference evaluation matrix can be constructed based on all the initial membership degrees and the fuzzy set in the following manner: according to the general construction process of the fuzzy comprehensive evaluation model, with the initial membership degree of each detection layer as the weight and the fuzzy membership degree set of the corresponding layer as the evaluation index, the final fuzzy interference evaluation matrix is obtained by combining by rows. Each row in this fuzzy interference evaluation matrix represents the membership degree distribution of a certain detection layer under different interference grades and has the input format of fuzzy comprehensive evaluation.Finally, based on the fuzzy interference evaluation matrix, a fuzzy evaluation of the interference effect intensity of each detection layer is carried out to obtain the interference evaluation index of water pollution detection corresponding to each detection layer, which can be realized by the following method, that is: based on the constructed fuzzy interference evaluation matrix, each row is extracted as the fuzzy evaluation vector of the corresponding detection layer. Each element in this vector represents the membership degree of the corresponding detection layer to different interference levels (such as weak, medium, strong). The fuzzy comprehensive evaluation method is used to normalize this evaluation vector and introduce a quantitative weight vector (for example, corresponding to "weak = 0.2", "medium = 0.5", "strong = 0.8"). Multiply the fuzzy membership degree and the corresponding weight item by item and sum them to obtain the fuzzy expected value corresponding to each detection layer, and then use this fuzzy expected value as the interference evaluation index of this detection layer.

[0040] It should be noted that, by combining the vertical concentration gradient and the local flow velocity of water bodies at different depths, the present application constructs an interference effect intensity matrix and uses the fuzzy membership function to realize the fuzzy evaluation of the interference of water pollution detection, effectively solving the problem in the traditional technology that the complex interference relationship between water layers at different depths cannot be accurately quantified and dynamically reflected. First, initializing the membership degree provides a reasonable starting point for subsequent fuzzy evaluation, improving the accuracy and stability of the evaluation; second, using the vertical concentration gradient and the flow velocity to construct the interference intensity matrix scientifically reflects the diffusion and perturbation mechanism of pollutants at different depths, overcoming the limitation of single-index analysis; third, converting the interference intensity into a fuzzy set through the fuzzy membership function enhances the adaptability of the model to uncertainty and data fluctuations; finally, based on the fuzzy evaluation matrix for comprehensive evaluation, the interference evaluation index of each detection layer is obtained, realizing the quantitative expression of the layered interference effect of water pollution detection; in summary, the solution of the present application can improve the accuracy and reliability of water quality monitoring, optimize the fusion processing of water pollution data at different depths, and contribute to more scientifically guiding pollution control and risk assessment.

[0041] In step 104, based on all the mutual support degrees and the interference evaluation indexes of water pollution detection at different depths, the water pollution concentration of each detection node is subjected to cost fusion to obtain the fusion pollution degree of water pollution, and then the fusion pollution degree is used as the pollution degree of the water body in the target hidden pipe drainage well.

[0042] In some embodiments, the cost fusion of the water pollution concentration of each detection node based on all the mutual support degrees and the interference evaluation indexes of water pollution detection at different depths to obtain the fusion pollution degree of water pollution can be realized by the following steps: Taking the fusion weight of the water pollution concentration at each detection node as the optimization variable, aiming at minimizing the difference in mutual support degree and the deviation of the interference evaluation index between detection nodes, a fusion cost function is constructed. All mutual support degrees and interference evaluation indices for water pollution detection at different depths are introduced into the fusion cost function in the form of weighted penalty terms; The fusion cost function is iteratively solved through a genetic algorithm until the pollution fusion weights of each detection node converge to an optimal state, and then the fusion pollution degree of water pollution in the target hidden pipe drainage well is obtained.

[0043] It should be noted that the fusion cost function in this application refers to the objective function used to quantify the difference in mutual support degrees and interference evaluation deviations between the water pollution concentrations of detection nodes; the fusion pollution degree in this application is a comprehensive evaluation index for measuring the water pollution concentration in the target hidden pipe drainage well.

[0044] In the specific implementation, first, the fusion weight of the water pollution concentration at each detection node is used as the optimization variable, with the goal of minimizing the mutual support difference and interference evaluation index deviation between the detection nodes. The construction of the fusion cost function can be implemented in the following way, namely: the cost function model is constructed with the concentration weight of each node as a variable, in which the optimization target consists of two parts. One is that the node pairs with strong mutual support should have higher concentration consistency, that is, the weighted sum of the square of the concentration difference between any two nodes and the product of their mutual support is constructed to reflect the matching degree between the concentration distribution and the node synergy; the second is the response of the concentration value of each node to the interference evaluation index of its detection layer, that is, the detection with smaller interference degree has better consistency. The concentration value of the measured layer should have a higher credibility. It should also be noted that the expression of the fusion cost function in this application can be described as: the cost function consists of two main weighted sub-items. The first item represents the deviation between the water pollution concentration and its corresponding mutual support between all detection nodes, that is, the higher the support of the node pair, the more the difference in pollution concentration should be suppressed. This item is reflected by summing the square of the concentration difference between all node pairs and the product of their support value. The second item represents the deviation between the water pollution concentration of each detection node and the interference evaluation index of the depth layer where it is located, that is, the smaller the interference index of the layer, the more its concentration value should be retained. Trust, this item is expressed by the difference between the concentration of each node and its interference index. The overall fusion cost function is composed of the sum of the above two items, and the optimization strength of the concentration consistency target and the interference suppression target are controlled by setting two weight factors, so as to achieve the global optimal fusion estimation of the fusion pollution degree; then, all the mutual support and the interference evaluation index of water pollution detection at different depths are introduced into the fusion cost function in the form of weighted penalty terms. The following method can be used to achieve this, namely: integrating the above two parts into the unified cost function in the form of weighted penalty terms, setting the weight factors of the support difference term and the interference index deviation term, and controlling their contribution to the optimization target; finally, the fusion cost function is optimized by a genetic algorithm. Iterative solution is performed until the pollution fusion weight of each detection node converges to the optimal state, and then the fused pollution degree of water pollution in the target underground drainage well is obtained. This can be achieved in the following way, namely: using a genetic algorithm for solution, specifically including initializing the concentration population, calculating the cost function value of each group of concentration combinations as fitness, iteratively generating a new population through operations such as selection, crossover and mutation, and continuously optimizing the cost function value, and finally outputting the concentration result with the minimum cost (that is, the fusion result obtained by weighted fusion of the water pollution concentrations of all detection nodes through the optimized fusion weights) as the fused pollution degree of water pollution in the target underground drainage well under the condition of convergence within a preset number of iterations or an error threshold.

[0045] It should be noted that, in this application, by constructing a fusion cost function, the differences in the mutual support degrees between detection nodes and the deviation of the hierarchical interference evaluation index are incorporated into a unified optimization objective, avoiding the fusion deviation caused by a single index and enhancing the comprehensiveness and accuracy of the fusion model. The solution of this application uses a genetic algorithm for iterative solution, effectively overcoming the defect that traditional optimization methods are prone to falling into local optima and ensuring the global optimality and stability of the fusion result. Generally speaking, the solution of this application solves the problems of information conflict and trade-off in multi-node and multi-depth fusion, realizes the reasonable fusion of water pollution concentration data, improves the accuracy and credibility of the fusion data, and has strong technical innovation and application value.

[0046] On the other hand, in some embodiments, this application provides a water pollution monitor, which includes a water pollution detection unit. Refer to Figure 4 , which is a schematic structural diagram of the water pollution detection unit shown in some embodiments of this application. The water pollution detection unit 400 includes: a detection module 401, a processing module 402, and an execution module 403, which are described as follows: Detection module 401. In this application, the detection module 401 is mainly used to detect the water pollution data of each detection node through an intelligent water quality sensor, and then extract the water pollution concentration of each detection node; Processing module 402. In this application, the processing module 402 is used to determine the cross-correlation coefficient of the water pollution concentration between different detection nodes according to the water pollution data of each detection node in the historical time period, and then determine the mutual support degree of the water pollution detection results between each intelligent water quality sensor through all the cross-correlation coefficients and the spatial topology structure of the intelligent water quality sensor; In this application, the processing module 402 is also used to extract the vertical concentration gradient of water pollution in the target hidden pipe drainage well, and perform a fuzzy evaluation on the intensity of the hierarchical interference effect of water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of water bodies at different depths, so as to obtain the interference evaluation index of water pollution detection at different depths; Execution module 403. In this application, the execution module 403 is mainly used to perform cost fusion on the water pollution concentration of each detection node based on all the mutual support degrees and the interference evaluation index of water pollution detection at different depths, obtain the fusion pollution degree of water pollution, and then use the fusion pollution degree as the pollution degree of the water body in the target hidden pipe drainage well.

[0047] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned water pollution detection method in the hidden pipe drainage well.

[0048] In some embodiments, refer to Figure 5, The figure is a schematic structural diagram of a computer device for implementing the water pollution detection method in the buried drainage well according to some embodiments of the present application. The water pollution detection method in the buried drainage well in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0049] The processor 501 can be a general-purpose central processing unit (CPU) or an application specific integrated circuit (ASIC).

[0050] The communication bus 502 can be used to transmit information between the above components.

[0051] The memory 503 can be a read only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It can also be an electrically erasable programmable read only memory (EEPROM), a compact disc read only memory (CD ROM), or other optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 503 can exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0052] Among them, the memory 503 is used to store the program code for executing the solution of the present application and is controlled by the processor 501 for execution. The processor 501 is used to execute the program code stored in the memory 503. The program code can include one or more software modules. The water pollution detection method in the buried drainage well in the above embodiments can be implemented by one or more software modules in the program code of the processor 501 and the memory 503.

[0053] A communication interface 504, using any device such as a transceiver, for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0054] In a specific implementation, as an example, a computer device may include multiple processors, and each of these processors may be a single CPU processor or a multi CPU processor. Here, the processor may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0055] The above computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0056] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the water pollution detection method in the concealed pipe drainage well described above is implemented.

[0057] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concept. Therefore, the appended claims are intended to be interpreted to include the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0058] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A method for detecting water pollution in a concealed pipe drainage well, characterized in that, Including the following steps: Deploy a plurality of detection nodes and intelligent water quality sensors in the target subsurface drainage well. Detect the water pollution data of each detection node through the intelligent water quality sensors, and then extract the water pollution concentration of each detection node; Determine the cross-correlation coefficient of the water pollution concentration between different detection nodes according to the water pollution data of each detection node in the historical time period, and then determine the mutual support degree of the water pollution detection results between each intelligent water quality sensor through all the cross-correlation coefficients and the spatial topology structure of the intelligent water quality sensors; Extract the vertical concentration gradient of the water pollution in the target subsurface drainage well, and perform a fuzzy evaluation on the intensity of the stratified interference effect of the water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of the water body at different depths, and obtain the interference evaluation index of the water pollution detection at different depths; Perform cost fusion on the water pollution concentration of each detection node based on all the mutual support degrees and the interference evaluation index of the water pollution detection at different depths to obtain the fusion pollution degree of the water pollution, and then use the fusion pollution degree as the pollution degree of the water body in the target subsurface drainage well.

2. The method according to claim 1, wherein Detect the water pollution data of each detection node through the intelligent water quality sensors, and then extract the water pollution concentration of each detection node specifically including: For each detection node, collect the water pollution data of the detection node in real time through the intelligent water quality sensors; Perform smoothing processing on the collected water pollution data, remove outliers and noise interference information, and obtain the smoothed water pollution data; Extract the water pollution concentration of the detection node from the smoothed water pollution data through a preset pollutant concentration calculation model, and then obtain the water pollution concentration of each detection node.

3. The method according to claim 1, wherein Determine the cross-correlation coefficient of the water pollution concentration between different detection nodes according to the water pollution data of each detection node in the historical time period specifically including: For every two detection nodes, perform time alignment processing on the water pollution data of the two detection nodes in the historical time period to obtain a group of time-aligned water pollution data; Perform cross-correlation analysis on the water pollution concentration between the two detection nodes based on the time-aligned water pollution data group to obtain the cross-correlation coefficient of the water pollution concentration between the two detection nodes, and then obtain the cross-correlation coefficient of the water pollution concentration between every two detection nodes.

4. The method according to claim 1, characterized in that Determine the mutual support degree of the water pollution detection results between each intelligent water quality sensor through all the cross-correlation coefficients and the spatial topology structure of the intelligent water quality sensors specifically including: For every two intelligent water quality sensors, determine the confidence distance between the two intelligent water quality sensors according to the spatial topology structure of the intelligent water quality sensors; Perform an associated support evaluation on the consistency of the water pollution detection results between the two intelligent water quality sensors through all the cross-correlation coefficients and the confidence distance to obtain the mutual support degree of the water pollution detection results between the two intelligent water quality sensors, and then obtain the mutual support degree of the water pollution detection results between every two intelligent water quality sensors.

5. The method according to claim 1, wherein Extract the vertical concentration gradient of the water pollution in the target subsurface drainage well specifically including: Divide the detection nodes into at least three detection layers in the vertical direction, and obtain the pollutant concentration of each layer; Perform cubic spline interpolation on the water pollution concentration in the vertical direction based on the concentration difference between adjacent detection layers to generate a continuous vertical concentration distribution curve; Determine the first derivative of the vertical concentration distribution curve within a preset depth interval, and extract the maximum gradient value as the vertical concentration gradient of water pollution in the target illegal sewer well.

6. The method according to claim 1, wherein Perform a fuzzy evaluation on the stratification interference effect intensity of water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of water bodies at different depths, and obtain the interference evaluation index of water pollution detection at different depths. Specifically, it includes: Initialize the initial membership degree of the interference effect of the detection layer at different depths; Construct an interference effect intensity matrix between each detection layer based on the vertical concentration gradient and the local flow velocity of water bodies at different depths; Map the values in the interference effect intensity matrix to a fuzzy set through a fuzzy membership function; Construct a fuzzy interference evaluation matrix based on all the initial membership degrees and the fuzzy set; Perform a fuzzy evaluation on the interference effect intensity of each detection layer based on the fuzzy interference evaluation matrix to obtain the interference evaluation index of water pollution detection corresponding to each detection layer.

7. The method according to claim 1, wherein The intelligent water quality sensor refers to an integrated sensing device with multi-parameter water quality perception ability, data preprocessing function, and communication module.

8. A water pollution monitor, which includes a water pollution detection unit, is characterized in that, The water pollution detection unit includes: A detection module, configured to detect the water pollution data of each detection node through an intelligent water quality sensor, and then extract the water pollution concentration of each detection node; A processing module, configured to determine the cross-correlation coefficient of the water pollution concentration between different detection nodes according to the water pollution data of each detection node within a historical time period, and then determine the mutual support degree of the water pollution detection results between each intelligent water quality sensor through all the cross-correlation coefficients and the spatial topology structure of the intelligent water quality sensor; The processing module is further configured to extract the vertical concentration gradient of water pollution in the target illegal sewer well, and perform a fuzzy evaluation on the stratification interference effect intensity of water pollution detection at different depths according to the vertical concentration gradient and the local flow velocity of water bodies at different depths, and obtain the interference evaluation index of water pollution detection at different depths; An execution module, configured to perform cost fusion on the water pollution concentration of each detection node based on all the mutual support degrees and the interference evaluation index of water pollution detection at different depths to obtain the fusion pollution degree of water pollution, and then use the fusion pollution degree as the pollution degree of the water body in the target illegal sewer well.

9. A computer device, the computer device includes a memory and a processor, the memory stores code, characterized in that, The processor is configured to obtain the code and execute the method for detecting water pollution in an illegal sewer well according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for detecting water pollution in an illegal sewer well according to any one of claims 1 to 7.

Images