Water quality monitoring method, system and device for environmental protection

Abstract

The present application relates to the technical field of water quality information monitoring, in particular to a water quality monitoring method, system and device for environmental protection. The method uses the hierarchical clustering algorithm, clusters the monitoring nodes based on the pollution degree difference between the monitoring nodes, obtains the tree diagram, and then segments the tree diagram to obtain the combination of the clustering clusters of each segmentation. For each segmentation, the representative nodes are selected based on the pollution degree difference between the nodes, the distribution of the representative nodes in the drainage pipe network is combined, and the feature saliency of the representative nodes obtained by the current segmentation is evaluated according to the influence degree of the key area to obtain the reasonable degree, select the optimal segmentation process and determine the key monitoring nodes. The present application is based on the hierarchical clustering algorithm, can determine the feature salient key monitoring node position based on the dynamic characteristics of the current drainage pipe network water area, and can extract the effective pollution information in the current drainage pipe network based on the key monitoring node position.

Description

Technical Field

[0001] This invention relates to the field of water quality information monitoring technology, specifically to a water quality monitoring method, system, and device for environmental protection. Background Technology

[0002] For water pollution monitoring in large-scale drainage pipe networks, it is necessary to increase the density of monitoring points, optimize the distribution of monitoring point locations, and establish a hierarchical monitoring network to ensure effective monitoring, so as to promptly determine the location of pollution and pollution information in the water, track pollutants, and determine their origin and transmission routes.

[0003] To construct a monitoring network covering a large area of ​​water, existing technologies typically deploy sensors at fixed intervals or at predetermined key locations within the water body. However, this sensor monitoring network, failing to consider the dynamic characteristics of water bodies, results in redundant and complex information, numerous monitoring locations, and difficulty in effectively identifying pollution characteristics within the water. Summary of the Invention

[0004] To address the technical problems of excessive and redundant monitoring nodes and numerous monitoring locations in existing sensor monitoring networks for large bodies of water, making it difficult to effectively determine pollution characteristics, this invention aims to provide a water quality monitoring method, system, and device for environmental protection. The specific technical solution adopted is as follows:

[0005] This invention proposes a water quality monitoring method for environmental protection, the method comprising:

[0006] The pollution level of the drainage network at each monitoring node within a preset time period is obtained, and the pollution level is obtained by statistical analysis of information from multiple sensors deployed at the monitoring nodes;

[0007] Based on the differences in pollution levels among monitoring nodes, hierarchical clustering is performed on the monitoring nodes to obtain a tree diagram of the hierarchical clustering. In the tree diagram, the combination of clusters for each segment is obtained by changing the position of the horizontal dividing line.

[0008] For each segmentation, the representativeness of the nodes is obtained based on the difference in the degree of contamination among the nodes in the cluster. Based on the representativeness, representative nodes of each cluster are selected. For each representative node, it is determined whether the node location of the cluster to which the representative node belongs overlaps with the key area of ​​the drainage pipe network. Based on the overlap, the degree of influence of the key area on each representative node is obtained. Based on the degree of influence of each representative node, the uniformity of the distribution of representative nodes, and the concentration of the distribution of representative nodes with neighboring nodes, the optimality of each segmentation is obtained.

[0009] The rationality of each segmentation is obtained based on the degree of optimization and the representativeness of the representative nodes. The optimal segmentation process is selected based on the rationality, and the representative nodes corresponding to the optimal segmentation process are selected as key monitoring nodes.

[0010] Furthermore, the pollution level includes: for each monitoring node, obtaining COD pollution data obtained by the optical sensor, turbidity pollution data monitored by the suspended matter monitoring sensor, and temperature data monitored by the temperature sensor at a certain moment; and weighting and summing the COD pollution data, turbidity pollution data, and temperature data to obtain the pollution level of each monitoring node at each moment.

[0011] Furthermore, obtaining the combination of clusters for each segmentation includes:

[0012] Set an initial horizontal dividing line. In the tree diagram, gradually raise the initial horizontal dividing line to obtain the horizontal dividing line for each division. The number of clusters obtained from different divisions gradually increases.

[0013] Furthermore, the representative acquisition method includes:

[0014] For a target node in a cluster, obtain the difference in contamination level between the target node and other nodes in the same cluster at each time step. Then, sum up all the differences in contamination level obtained for the target node to obtain the representativeness of the target node.

[0015] Furthermore, methods for determining whether the location of a node in a cluster to which a representative node belongs overlaps with key areas of the drainage network include:

[0016] For a target representative node, non-representative nodes in the same cluster as the target representative node are cluster nodes, the key area closest to the target representative node is the target key area, and the representative node within the target key area is the representative node to be analyzed.

[0017] The average distance between nodes in the same cluster and the representative node to be analyzed is obtained, and the maximum width of the target key area is obtained. If the average distance is less than or equal to the maximum width, it is considered that the node position of the cluster to which the target representative node belongs coincides with the key area of ​​the drainage pipe network; otherwise, it is determined that they do not coincide.

[0018] Furthermore, obtaining the degree of influence of the key area on each representative node based on the overlap includes:

[0019] If it is determined that the node location of the cluster to which the target node belongs coincides with the key area of ​​the drainage pipe network, then the average distance negative correlation mapping is followed by a preset first parameter as the degree of influence.

[0020] If it is determined that the node location of the cluster does not overlap with the key area of ​​the drainage network, the degree of influence is set to the preset first parameter.

[0021] Furthermore, the method for obtaining the degree of preference includes:

[0022] In any segmentation process, the distance between each representative node and its nearest representative node is taken as the neighbor distance, and the difference between the neighbor distance of each representative node and the average neighbor distance is taken as the neighbor distance deviation; the distance between each node and its nearest representative node is taken as the distribution distance; the neighbor distance deviation of all representative nodes and the distribution distance of all nodes are statistically analyzed to obtain the node distribution characteristics; the optimization degree is obtained based on the node distribution characteristics and the average influence of all representative nodes.

[0023] Furthermore, the method for obtaining the degree of reasonableness includes:

[0024] For any given segmentation process, the average representativeness of the representative nodes is obtained, and the product of the average representativeness and the normalized degree of optimization is taken as the degree of rationality.

[0025] The present invention also proposes a water quality monitoring system for environmental protection, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the steps of the water quality monitoring method for environmental protection described above.

[0026] This invention also proposes a water quality monitoring device for environmental protection, the device comprising:

[0027] The experimental information acquisition module is used to obtain the pollution level of each monitoring node in the drainage network within a preset time period. The pollution level is obtained by statistical analysis of information from multiple sensors deployed at the monitoring nodes.

[0028] The hierarchical clustering and segmentation module is used to perform hierarchical clustering of monitoring nodes based on the differences in pollution levels among monitoring nodes, and obtain a tree diagram of the hierarchical clustering. In the tree diagram, the combination of clusters for each segmentation is obtained by changing the position of the horizontal dividing line.

[0029] The segmentation result analysis module is used to, for each segmentation, obtain the representativeness of nodes based on the differences in pollution levels among nodes in the cluster, and select representative nodes for each cluster based on the representativeness; for each representative node, determine whether the node location of the cluster to which the representative node belongs overlaps with the key area of ​​the drainage pipe network, and obtain the degree of influence of the key area on each representative node based on the overlap; and obtain the optimality of each segmentation based on the degree of influence of each representative node, the uniformity of the distribution of representative nodes, and the concentration of the distribution of representative nodes with neighboring nodes.

[0030] The key monitoring node determination module is used to obtain the rationality of each segmentation based on the optimization degree and the representativeness of the representative nodes, select the optimal segmentation process based on the rationality degree, and take the representative node corresponding to the optimal segmentation process as the key monitoring node.

[0031] The present invention has the following beneficial effects:

[0032] This invention first sets a time period and then sets up multiple monitoring nodes in the drainage network within that time period. It then identifies key monitoring nodes through data analysis. This invention utilizes a hierarchical clustering algorithm to cluster monitoring nodes based on differences in pollution levels. After obtaining a dendrogram, it is segmented to obtain combinations of clusters from each segment. Each segmentation can be viewed as changing the scale of the clustering results, and the monitoring nodes with the most prominent characteristics are determined for monitoring at different scales. For each segmentation, this invention first selects representative nodes based on differences in pollution levels. Then, it assesses the saliency of the representative nodes obtained from the current segmentation by combining the distribution of these representative nodes in the drainage network and the degree of influence from key areas, thereby determining the reasonableness of the segmentation process, selecting the optimal segmentation process, and identifying key monitoring nodes. Based on the hierarchical clustering algorithm, this invention, through the integrated analysis of monitoring nodes, can determine the locations of key monitoring nodes with significant characteristics based on the dynamic characteristics of the current drainage network's water area. Based on the locations of these key monitoring nodes, effective pollution information in the current drainage network can be extracted. Attached Figure Description

[0033] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of a water quality monitoring method for environmental protection provided in one embodiment of the present invention. Detailed Implementation

[0035] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a water quality monitoring method, system, and apparatus for environmental protection proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0037] The following description, in conjunction with the accompanying drawings, details a specific scheme for a water quality monitoring method, system, and device for environmental protection provided by the present invention.

[0038] Please see Figure 1 The diagram illustrates a flowchart of a water quality monitoring method for environmental protection according to an embodiment of the present invention, the method comprising:

[0039] Step S1: Obtain the pollution level of each monitoring node in the drainage network within a preset time period. The pollution level is obtained by statistical analysis of information from various sensors deployed at the monitoring nodes.

[0040] In this embodiment of the invention, the focus is on a large-scale drainage pipe network in a waterway where existing monitoring nodes have already been deployed. In constructing the monitoring node network, this embodiment sets monitoring nodes at intervals around the drainage outlets. Starting from the drainage outlets, monitoring nodes are set and numbered at fixed intervals of 200 meters, thus obtaining the monitoring node network. This embodiment sets the information collection interval at each monitoring node location to 30 seconds and the data analysis period to 250 minutes, meaning 500 pollution level data points are collected at each monitoring node location.

[0041] It should be noted that, in this embodiment of the invention, optical sensors, suspended matter monitoring sensors, and temperature sensors are deployed at the monitoring node locations. The degree of pollution is determined by the data from these three types of sensors. That is, within a preset time period in this embodiment of the invention, each monitoring node will obtain a time-series sequence of pollution levels, with each moment corresponding to a specific pollution level.

[0042] Preferably, in this embodiment of the invention, for each monitoring node, COD pollution data obtained by the optical sensor, turbidity pollution data monitored by the suspended matter monitoring sensor, and temperature data monitored by the temperature sensor are obtained at a given time. The COD pollution data, turbidity pollution data, and temperature data are then weighted and summed to obtain the pollution level of each monitoring node at each time. As an example, in one specific implementation of the invention, the weight of the COD pollution data is set to 0.6, the weight of the turbidity pollution data is set to 0.3, and the weight of the temperature data is set to 0.1.

[0043] It should be noted that at the monitoring node location of this embodiment of the invention, after each sensor collects data, range standardization processing can be performed based on the maximum and minimum values ​​in the corresponding dimension to achieve dimensionless and normalized data.

[0044] Step S2: Perform hierarchical clustering on the monitoring nodes based on the differences in pollution levels among the monitoring nodes to obtain a tree diagram of the hierarchical clustering; in the tree diagram, by changing the position of the horizontal dividing line, obtain the combination of clusters for each division.

[0045] This invention considers the existence of many redundant nodes in the existing monitoring node network, which represent the same pollution information. Therefore, to efficiently obtain characteristic data from the current drainage network, it is necessary to focus on monitoring node information with significant characteristics. Thus, this invention, based on the idea of ​​aggregated hierarchical clustering, performs cluster analysis on the monitoring nodes to obtain a dendrogram of aggregated hierarchical clustering. A dendrogram is a common graphical representation method for visualizing tree-like clustering results. It shows the hierarchical relationship between clustering results, including the order and distance (dissimilarity) between samples. In a dendrogram, each measurement is represented as a bottom node, and hierarchical clustering is formed by merging individual nodes or existing lower-level clusters. Dendrograms help visually assign related objects to clusters. Horizontal lines in a dendrogram indicate the location where clusters are merged, while vertical lines indicate the distance when lower-level clusters are merged into new higher-level clusters. The dendrogram can be cut at any height on the vertical axis using horizontal dividing lines to obtain the desired number of clusters; lower heights correspond to more clusters. That is, each division yields multiple clusters.

[0046] Through hierarchical clustering, different levels can be considered as clustering results at different scales. Higher levels have higher clustering scales and fewer clusters; lower levels have more specific clustering scales and more clusters. This invention aims to screen effective key monitoring nodes from multiple monitoring nodes. Therefore, it cannot analyze clustering results at only one scale. This invention changes the position of the horizontal dividing line in the dendrogram to obtain the combination of clusters for each division. Then, in subsequent steps, the results of each division are analyzed to determine the optimal division process.

[0047] It should be noted that during the aggregation hierarchical clustering process, the dissimilarity can be based on the difference distance between the pollution degree sequences of monitoring nodes. This difference distance can be calculated using Euclidean distance, which is a technique well known to those skilled in the art and will not be elaborated further.

[0048] Preferably, in one embodiment of the present invention, the initial horizontal dividing line is set at a dissimilarity level of 0.85. In the tree diagram, the initial horizontal dividing line is gradually raised to obtain the horizontal dividing line for each division, and the number of clusters obtained from different divisions gradually increases. It should be noted that setting an initial horizontal dividing line can reduce the computational load of the algorithm and can be regarded as setting the maximum number of key monitoring nodes. The specific position of the initial horizontal dividing line can be set according to the specific needs of the implementer, and the embodiments of the present invention are not limited thereto.

[0049] Step S3: For each segmentation, the representativeness of the nodes is obtained based on the difference in the degree of contamination among the nodes in the cluster. Representative nodes of each cluster are selected based on representativeness. For each representative node, it is determined whether the node location of the cluster to which the representative node belongs overlaps with the key area of ​​the drainage network. The degree of influence of the key area on each representative node is obtained based on the overlap. The optimality of each segmentation is obtained based on the degree of influence of each representative node, the uniformity of the distribution of representative nodes, and the concentration of the distribution of representative nodes and neighboring nodes.

[0050] Because the embodiments of this invention aim to select the monitoring nodes with the most obvious feature information as key monitoring nodes, in each segmentation process, the representativeness of the nodes can first be obtained based on the differences in the degree of contamination among the nodes in each cluster, and then the representative node of each cluster can be selected based on the representativeness. The representative node is the node with the most significant feature in the cluster.

[0051] Preferably, in this embodiment of the invention, considering that each monitoring node can obtain a pollution level difference at each moment within a time period, the representative acquisition method includes:

[0052] For a target node in a cluster, the difference in contamination level between the target node and other nodes in the same cluster at each time step is obtained. All the contamination level differences obtained for the target node are summed to obtain the representativeness of the target node. In this embodiment of the invention, the contamination level difference is the difference between the contamination level of the target node and the contamination level of other nodes. That is, the larger the difference in contamination level, the more severe the contamination level of the target node, and the more significant its contamination feature in the cluster. Specifically, in each cluster, the monitoring node with the highest representativeness is selected as the representative node.

[0053] After determining the representative nodes for each segmentation process, the distribution of these representative nodes within the drainage network should be analyzed. It's possible that the distribution of representative nodes is too concentrated in a particular segmentation process, and there are also key areas within the drainage network, including drinking water sources, industrial discharge outlets, and agricultural runoff areas. Pollutants in these key areas diffuse relatively quickly, with higher discharge frequencies and faster water flow. Therefore, it's necessary to determine the impact of the relative distribution of key areas and representative nodes. This invention aims to plan a set of representative nodes with a relatively uniform distribution, a large number of surrounding monitoring nodes, and the ability to cover key areas as key monitoring nodes. A uniform distribution ensures that the key monitoring nodes cover a large area of ​​the drainage network; a large number of surrounding monitoring nodes indicates a more reasonable distribution of the key monitoring nodes, making them prominent nodes in a particular area; the more the key monitoring nodes cover the key areas, the more effective the monitoring of those areas. Therefore, in this embodiment of the invention, for each representative node, it is determined whether the node position of the cluster to which the representative node belongs overlaps with the key area of ​​the drainage pipe network. Based on the overlap, the degree of influence of the key area on each representative node is obtained. Based on the degree of influence of each representative node, the uniformity of the distribution of representative nodes, and the concentration of the distribution of representative nodes with neighboring nodes, the optimization degree of each segmentation is obtained. That is, the higher the optimization degree, the more effective the division of the representative node set in that segmentation process.

[0054] Preferably, in this embodiment of the invention, the method for determining whether the location of a node in the cluster to which a representative node belongs overlaps with a key area of ​​the drainage pipe network includes:

[0055] For a target representative node, non-representative nodes in the same cluster as the target representative node are cluster nodes, the key area closest to the target representative node is the target key area, and the representative node within the target key area is the representative node to be analyzed.

[0056] Obtain the average distance between nodes in the same cluster and the representative node to be analyzed. It should be noted that if the target key area includes multiple representative nodes to be analyzed, only the closest representative node to be analyzed is calculated.

[0057] The smaller the average distance, the more likely the nodes in the same cluster of the target representative node are to be close to the target key area, indicating that the representative node is more affected by the key area.

[0058] The maximum width of the target key area is obtained. If the average distance is less than or equal to the maximum width, the node position of the cluster to which the target representative node belongs is considered to coincide with the key area of ​​the drainage pipe network; otherwise, it is determined that they do not coincide.

[0059] Furthermore, based on the overlap, the degree of influence of the key area on each representative node is obtained, including:

[0060] If it is determined that the node location of the cluster to which the target node belongs coincides with the key area of ​​the drainage pipe network, then the average distance negative correlation mapping is added to a preset first parameter as the degree of influence; if it is determined that the node location of the cluster to which the target node belongs does not coincide with the key area of ​​the drainage pipe network, then the degree of influence is set to the preset first parameter.

[0061] That is, the influence when they overlap is always greater than the influence when they don't overlap. Furthermore, the smaller the average distance, the closer the target representative node's nodes in the same cluster are to the target key area, and the greater the influence of the target representative node on the target key area. Therefore, a negative correlation mapping is needed for the average distance. It should be noted that in this embodiment of the invention, the first parameter is set to 1. Considering that the distance between a node in the same cluster and the representative node to be analyzed cannot be 0, the reciprocal of the average distance can be directly used as the negative correlation mapping result.

[0062] Preferably, in this embodiment of the invention, the method for obtaining the degree of preference includes:

[0063] In any given segmentation process, the distance between each representative node and its nearest representative node is taken as the neighbor distance, and the difference between each representative node's neighbor distance and the average neighbor distance is taken as the neighbor distance deviation. If the neighbor distance deviation of each representative node is small, it indicates that the representative nodes are relatively evenly distributed in the drainage network.

[0064] The distance between each node and its nearest representative node is used as the distribution distance. If the distribution distances of all nodes are small, it indicates that the representative node's location has greater reference value and is more reasonable.

[0065] The node distribution characteristics are obtained by statistically analyzing the neighbor distance deviations of all representative nodes and the distribution distances of all nodes. In this embodiment of the invention, the neighbor distance deviations of all representative nodes and the distribution distances of all nodes are summed. The reciprocal of the product of these two sums is taken as the node distribution characteristics. That is, the larger the node distribution characteristics, the more reasonable the selection of representative nodes in this segmentation process, and the greater the degree of optimization.

[0066] The degree of preference is obtained based on the node distribution characteristics and the average influence of all representative nodes. In this embodiment of the invention, the node distribution characteristics are quantified, and the influence is also quantified by an assignment method. The larger the node distribution characteristics, the greater the degree of preference should be; the larger the average influence, the greater the degree of preference should be. Therefore, the product of the two is used as the degree of preference.

[0067] Step S4: Based on the optimization degree and the representativeness of the representative nodes, obtain the rationality of each segmentation, select the optimal segmentation process based on the rationality, and take the representative nodes corresponding to the optimal segmentation process as key monitoring nodes.

[0068] After obtaining the optimization degree after each segmentation, the rationality degree of each segmentation can be obtained by combining it with the representativeness of the representative nodes in each segmentation process. That is, the optimization degree characterizes the rationality of the positional distribution of representative nodes, and the representativeness characterizes the rationality of the salience of the features of representative nodes. Therefore, based on the rationality degree, the optimal segmentation process can be selected, that is, the segmentation process with the highest rationality degree is selected as the optimal segmentation process, and the representative nodes corresponding to the optimal segmentation process are selected as key monitoring nodes.

[0069] In this embodiment of the invention, after identifying key monitoring nodes, the number of other monitoring nodes can be directly reduced, thus lowering monitoring costs. When tracing the source of pollution information at key monitoring node locations, a cellular automata model can be established to reproduce the migration process of pollutants in the river channel, achieving the purpose of source tracing. A cellular automata (CA) is a grid dynamics model where time, space, and state are discrete, and spatial interactions and temporal causality are local, possessing the ability to simulate the spatiotemporal evolution of complex systems. Specific methods are well-known techniques to those skilled in the art and will not be elaborated upon here.

[0070] Preferably, in this embodiment of the invention, for any segmentation process, the average representativeness of the representative nodes is obtained, and the product of the average representativeness and the normalized degree of preference is taken as the degree of rationality.

[0071] In summary, this invention utilizes a hierarchical clustering algorithm to cluster monitoring nodes based on differences in pollution levels. After obtaining a dendrogram, the clusters are segmented to obtain combinations of clusters for each segmentation. For each segmentation, representative nodes are selected based on the differences in pollution levels. The saliency of the representative nodes obtained from the current segmentation is evaluated by considering their distribution within the drainage network and their influence from key areas, thus determining their reasonableness and selecting the optimal segmentation process to identify key monitoring nodes. Based on a hierarchical clustering algorithm, this invention, through integrated analysis of monitoring nodes, can determine the locations of key monitoring nodes with significant characteristics based on the dynamic characteristics of the current drainage network's water area. Based on the locations of these key monitoring nodes, effective pollution information within the current drainage network can be extracted.

[0072] Based on the same inventive concept, the present invention also proposes a water quality monitoring system for environmental protection, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the steps of the water quality monitoring method for environmental protection described above.

[0073] Based on the same inventive concept, a water quality monitoring device for environmental protection is provided, the device comprising:

[0074] The experimental information acquisition module is used to obtain the pollution level of each monitoring node in the drainage network within a preset time period. The pollution level is obtained by statistical analysis of information from multiple sensors deployed at the monitoring nodes.

[0075] The hierarchical clustering and segmentation module is used to perform hierarchical clustering of monitoring nodes based on the differences in pollution levels among monitoring nodes, and obtain a tree diagram of the hierarchical clustering. In the tree diagram, the combination of clusters for each segmentation is obtained by changing the position of the horizontal dividing line.

[0076] The segmentation result analysis module is used to, for each segmentation, obtain the representativeness of nodes based on the differences in pollution levels among nodes in the cluster, and select representative nodes for each cluster based on the representativeness; for each representative node, determine whether the node location of the cluster to which the representative node belongs overlaps with the key area of ​​the drainage pipe network, and obtain the degree of influence of the key area on each representative node based on the overlap; and obtain the optimality of each segmentation based on the degree of influence of each representative node, the uniformity of the distribution of representative nodes, and the concentration of the distribution of representative nodes with neighboring nodes.

[0077] The key monitoring node determination module is used to obtain the rationality of each segmentation based on the optimization degree and the representativeness of the representative nodes, select the optimal segmentation process based on the rationality degree, and take the representative node corresponding to the optimal segmentation process as the key monitoring node.

[0078] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0079] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. An environment-friendly water quality monitoring method, characterized by, The method includes: The pollution level of the drainage network at each monitoring node within a preset time period is obtained, and the pollution level is obtained by statistical analysis of information from multiple sensors deployed at the monitoring nodes; Based on the differences in pollution levels among monitoring nodes, hierarchical clustering is performed on the monitoring nodes to obtain a tree diagram of the hierarchical clustering. In the tree diagram, the combination of clusters for each segment is obtained by changing the position of the horizontal dividing line. For each segmentation, the representativeness of the nodes is obtained based on the difference in the degree of contamination among the nodes in the cluster. Based on the representativeness, representative nodes of each cluster are selected. For each representative node, it is determined whether the node location of the cluster to which the representative node belongs overlaps with the key area of ​​the drainage pipe network. Based on the overlap, the degree of influence of the key area on each representative node is obtained. Based on the degree of influence of each representative node, the uniformity of the distribution of representative nodes, and the concentration of the distribution of representative nodes with neighboring nodes, the optimality of each segmentation is obtained. The rationality of each segmentation is obtained based on the degree of optimization and the representativeness of the representative nodes. The optimal segmentation process is selected based on the rationality, and the representative nodes corresponding to the optimal segmentation process are selected as key monitoring nodes. The representative acquisition methods include: For a target node in a cluster, obtain the difference in contamination level between the target node and other nodes in the same cluster at each time step. Then, sum up all the differences in contamination level obtained for the target node to obtain the representativeness of the target node.

2. The water quality monitoring method according to claim 1, wherein The pollution level includes: for each monitoring node, obtaining COD pollution data obtained by the optical sensor, turbidity pollution data monitored by the suspended matter monitoring sensor, and temperature data monitored by the temperature sensor at a certain moment; and weighting and summing the COD pollution data, turbidity pollution data, and temperature data to obtain the pollution level of each monitoring node at each moment.

3. The water quality monitoring method according to claim 1, wherein The process of obtaining the combination of clusters for each segmentation includes: Set an initial horizontal dividing line. In the tree diagram, gradually raise the initial horizontal dividing line to obtain the horizontal dividing line for each division. The number of clusters obtained from different divisions gradually increases.

4. The method for monitoring water quality according to environmental protection of claim 1, wherein, Methods for determining whether the location of a node in a cluster to which a representative node belongs overlaps with a key area of ​​the drainage network include: For a target representative node, non-representative nodes in the same cluster as the target representative node are cluster nodes, the key area closest to the target representative node is the target key area, and the representative node within the target key area is the representative node to be analyzed. The average distance between nodes in the same cluster and the representative node to be analyzed is obtained, and the maximum width of the target key area is obtained. If the average distance is less than or equal to the maximum width, it is considered that the node position of the cluster to which the target representative node belongs coincides with the key area of ​​the drainage pipe network; otherwise, it is determined that they do not coincide.

5. A water quality monitoring method for environmental protection according to claim 4, characterized in that, The process of determining the degree of influence of the key area on each representative node based on the overlap includes: If it is determined that the node location of the cluster to which the target node belongs coincides with the key area of ​​the drainage pipe network, then the average distance negative correlation mapping is followed by a preset first parameter as the degree of influence. If it is determined that the node location of the cluster does not overlap with the key area of ​​the drainage network, the degree of influence is set to the preset first parameter.

6. The method for monitoring water quality according to environmental protection of claim 1, wherein, The method for obtaining the degree of preference includes: In any segmentation process, the distance between each representative node and its nearest representative node is taken as the neighbor distance, and the difference between the neighbor distance of each representative node and the average neighbor distance is taken as the neighbor distance deviation; the distance between each node and its nearest representative node is taken as the distribution distance; the neighbor distance deviation of all representative nodes and the distribution distance of all nodes are statistically analyzed to obtain the node distribution characteristics; the optimization degree is obtained based on the node distribution characteristics and the average influence of all representative nodes.

7. The method for monitoring water quality according to environmental protection of claim 1, wherein, The methods for obtaining the degree of reasonableness include: For any given segmentation process, the average representativeness of the representative nodes is obtained, and the product of the average representativeness and the normalized degree of optimization is taken as the degree of rationality.

8. An environmental protection-oriented water quality monitoring system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the water quality monitoring method for environmental protection as described in any one of claims 1 to 7.

9. An environment-friendly water quality monitoring device, characterized by, The device includes: The experimental information acquisition module is used to obtain the pollution level of each monitoring node in the drainage network within a preset time period. The pollution level is obtained by statistical analysis of information from multiple sensors deployed at the monitoring nodes. The hierarchical clustering and segmentation module is used to perform hierarchical clustering of monitoring nodes based on the differences in pollution levels among monitoring nodes, and obtain a tree diagram of the hierarchical clustering. In the tree diagram, the combination of clusters for each segmentation is obtained by changing the position of the horizontal dividing line. The segmentation result analysis module is used to, for each segmentation, obtain the representativeness of nodes based on the differences in pollution levels among nodes in the cluster, and select representative nodes for each cluster based on the representativeness; for each representative node, determine whether the node location of the cluster to which the representative node belongs overlaps with the key area of ​​the drainage pipe network, and obtain the degree of influence of the key area on each representative node based on the overlap; and obtain the optimality of each segmentation based on the degree of influence of each representative node, the uniformity of the distribution of representative nodes, and the concentration of the distribution of representative nodes with neighboring nodes. The key monitoring node determination module is used to obtain the rationality of each segmentation based on the optimization degree and the representativeness of the representative nodes, select the optimal segmentation process based on the rationality, and take the representative node corresponding to the optimal segmentation process as the key monitoring node. The representative acquisition methods include: For a target node in a cluster, obtain the difference in contamination level between the target node and other nodes in the same cluster at each time step. Then, sum up all the differences in contamination level obtained for the target node to obtain the representativeness of the target node.

Images