Intelligent water pollution monitoring method and system based on Internet of Things and edge computing
Through the Internet of Things and edge computing technology, an intelligent water pollution monitoring system is established, water quality data is collected and processed in real time, and a position relationship map is established, which solves the problems of low water quality monitoring accuracy and efficiency in the existing technology, and achieves rapid response and accurate identification of pollution Source, support efficient governance.
Patent Information
- Application Number
- CN202411085178.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-08
AI Technical Summary
The existing water pollution monitoring technology has shortcomings in covering water quality changes and identifying pollution sources, making it difficult to achieve real-time response and efficient governance, especially in areas with scarce water resources and low monitoring accuracy and efficiency.
Adopt an intelligent water pollution monitoring system based on the Internet of Things and edge computing, and through the location determination module, data acquisition module, related analysis module and pollution analysis module, water quality data is collected and processed in real time, establish a position relationship map, judge the type and source of pollution, and realize Multi-point monitoring and real-time data feedback.
Improve the accuracy and efficiency of water quality monitoring, quickly respond to pollution incidents, reduce data transmission costs and server burden, enhance system scalability and flexibility, reduce data leakage risks, and more accurately identify pollution types and sources. Support targeted governance measures.
Smart Images

Figure CN118604289B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing, and in particular to a method and system for intelligent monitoring of water pollution based on the Internet of Things and edge computing. Background Art
[0002] Water resources are the key material guarantee for human survival. Water quality testing is directly related to people's lives and provides a key basis for water resource protection and development. Through scientific analysis of the source of pollution, some heavily polluting enterprises can be effectively shut down, and enterprises with obviously excessive emissions can be focused on rectification. In view of the relative scarcity of water resources and the serious water shortage in some areas, water quality ecological environment monitoring is very important. Polluted areas need to be monitored, and unpolluted rivers also need to be protected, and effective control of pollution sources should be taken.
[0003] Therefore, it is necessary to provide an intelligent water pollution monitoring method and system based on the Internet of Things and edge computing to improve the reliability of water pollution monitoring. Summary of the invention
[0004] The present invention provides an intelligent water pollution monitoring system based on the Internet of Things and edge computing, including: a location determination module, used to determine multiple water pollution monitoring locations in an area to be monitored; a data acquisition module, including multiple water pollution monitoring devices set in the area to be monitored, determined based on the multiple water pollution monitoring locations in the area to be monitored, wherein the water pollution monitoring devices are used to collect water quality related data; a correlation analysis module, used to determine the correlation relationship between the multiple water pollution monitoring locations and establish a location relationship map; a data processing module, including multiple edge computing devices determined based on the location relationship map, wherein one edge computing device corresponds to at least one water pollution monitoring location, and the edge computing device is used to determine whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on the water quality related data collected by the water pollution monitoring device, and if so, mark the water pollution monitoring device as a target water pollution monitoring device; a pollution analysis module, used to determine the pollution type and pollution source based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality related data collected by the multiple water pollution monitoring devices, and the location relationship map.
[0005] Furthermore, the location determination module determines multiple water pollution monitoring locations in the area to be monitored, including: obtaining geographic information of the area to be monitored; determining multiple initial water pollution monitoring locations based on the geographic information of the area to be monitored; obtaining first test water quality information for each of the initial water pollution monitoring locations; calculating differentiation parameters of the multiple initial water pollution monitoring locations based on the first test water quality information for each of the initial water pollution monitoring locations; when the differentiation parameter is greater than a preset differentiation parameter, adding at least one water pollution monitoring location, wherein the multiple water pollution monitoring locations include the multiple initial water pollution monitoring locations and at least one newly added water pollution monitoring location.
[0006] Furthermore, the location determination module adds at least one water pollution monitoring location, including: adding the at least one water pollution monitoring location based on a water quality difference parameter of test water quality information of any two initial water pollution monitoring locations.
[0007] Furthermore, the correlation analysis module determines the association relationship among multiple water pollution monitoring locations and establishes a position relationship map, including: obtaining the second test water quality information of each of the water pollution monitoring locations; calculating the correlation coefficient between any two of the water pollution monitoring locations based on the second test water quality information of each of the water pollution monitoring locations; for each of the water pollution monitoring locations, determining the associated water pollution monitoring locations of the water pollution monitoring locations based on the correlation coefficient between any two of the water pollution monitoring locations, and determining the association relationship between the water pollution monitoring location and each of the associated water pollution monitoring locations based on the second test water quality information of each of the water pollution monitoring locations; and establishing the position relationship map based on the association relationship between the water pollution monitoring location and each of the associated water pollution monitoring locations.
[0008] Furthermore, the correlation analysis module calculates the correlation coefficient between any two of the water pollution monitoring positions based on the second test water quality information of each of the initial water pollution monitoring positions, including: for any two of the water pollution detection positions, calculating the parameter correlation coefficient of the two water pollution detection positions in the target detection parameters based on the second test water quality information of the two water pollution detection positions, and calculating the correlation coefficient of the two water pollution monitoring positions based on the parameter correlation coefficient of the two water pollution detection positions in the target detection parameters.
[0009] Furthermore, the correlation analysis module determines the association relationship between the water pollution monitoring location and each of the associated water pollution monitoring locations based on the second test water quality information of each of the water pollution monitoring locations, including: determining multiple time lag windows; for each of the associated water pollution monitoring locations, determining the water quality similarity between the water pollution monitoring location and the associated water pollution monitoring location in the time lag window based on the second test water quality information of each of the water pollution monitoring locations; when the water quality similarity is greater than a preset water quality similarity, marking the time lag window as a target time lag window; and determining the association relationship between the water pollution monitoring location and the associated water pollution monitoring location based on the target time lag window.
[0010] Furthermore, the edge computing device determines whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on the water quality-related data collected by the water pollution monitoring device, including: determining whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on the water quality-related data collected by the water pollution monitoring device at multiple time points in the current water quality detection cycle through a pollution judgment model.
[0011] Furthermore, the pollution analysis module determines the pollution type based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality-related data collected by the multiple water pollution monitoring devices, and the position relationship map, including: determining the associated water pollution monitoring device of the target water pollution monitoring device based on the position relationship map; determining the pollution type based on the water quality-related data collected by the associated water pollution monitoring device of the target water pollution monitoring device at multiple time points in the current water quality detection cycle and the water quality-related data collected by the associated water pollution monitoring device of the target water pollution monitoring device at multiple time points in the current water quality detection cycle.
[0012] Furthermore, the pollution analysis module determines the source of pollution based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality-related data collected by the multiple water pollution monitoring devices, and the position relationship map, including: determining the target water pollution monitoring position based on the target water pollution monitoring device; determining the pollution source based on the position relationship map and the target water pollution monitoring position.
[0013] The present invention provides an intelligent water pollution monitoring method based on the Internet of Things and edge computing, including: determining multiple water pollution monitoring locations in an area to be monitored; based on the multiple water pollution monitoring locations in the area to be monitored, determining multiple water pollution monitoring devices arranged in the area to be monitored, wherein the water pollution monitoring devices are used to collect water quality related data; determining the correlation between the multiple water pollution monitoring locations and establishing a position relationship map; based on the position relationship map, determining multiple edge computing devices, wherein one edge computing device corresponds to at least one water pollution monitoring location; the edge computing device determines whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on the water quality related data collected by the water pollution monitoring device, and if so, marking the water pollution monitoring device as a target water pollution monitoring device; based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality related data collected by the multiple water pollution monitoring devices, and the position relationship map, determining the pollution type and pollution source.
[0014] Compared with the prior art, the water pollution intelligent monitoring method and system based on the Internet of Things and edge computing provided by the present invention have at least the following beneficial effects:
[0015] 1. Multi-point monitoring can cover the monitored area more comprehensively, capture more potential water quality change points, and improve the accuracy of monitoring. Edge computing devices can process water quality data in real time or near real time, respond quickly to water quality changes, and improve monitoring efficiency. Edge computing devices can determine whether pollution occurs at the water pollution monitoring location based on real-time data, and immediately mark the relevant monitoring device as a target device, thereby quickly discovering pollution events. This helps to take measures early to prevent the spread of pollution and reduce losses. Through the collaborative work of position relationship maps and multiple edge computing devices, data from multiple monitoring points can be comprehensively analyzed to more accurately determine the source of pollution. This helps to implement targeted governance measures and improve the efficiency of pollution control. The edge computing device performs preliminary processing at the source of data generation, reducing the amount of data that needs to be transmitted to the central server and reducing the cost of data transmission. At the same time, due to the reduction of the processing burden of the central server, the operation and maintenance costs of the server are also reduced. Through modular design, water pollution monitoring locations and edge computing devices can be easily increased or decreased to adapt to monitoring tasks of different scales and needs. This makes the system more scalable and flexible, and can better adapt to possible changes in the future. Since part of the data processing is performed on the edge computing device, the transmission distance and number of times of sensitive data in the network are reduced, thereby reducing the risk of data leakage.
[0016] 2. By obtaining the geographic information of the area to be monitored, we can more accurately understand the characteristics of water flow, terrain, pollution source distribution and other characteristics in the area, so as to arrange the monitoring positions more reasonably. The setting of multiple initial monitoring positions can cover a wider area, reduce monitoring blind spots and improve the comprehensiveness of monitoring. Through testing and calculation, we can identify areas with more serious pollution, so as to add new monitoring positions in a targeted manner and track and locate pollution sources more accurately. When the differentiation parameter is greater than the preset value, the new monitoring position can be flexibly adjusted according to the actual situation to meet the needs of water quality changes and environmental changes. By adding new monitoring positions, more water quality data can be obtained in real time, water quality anomalies can be discovered in time, and monitoring efficiency can be improved. When a pollution incident occurs, multi-point monitoring and real-time data feedback can respond quickly and provide strong support for pollution control and emergency disposal. By scientifically and reasonably determining and adding new monitoring positions, unnecessary monitoring point settings can be avoided, monitoring costs and resource waste can be reduced. By improving the pertinence and accuracy of monitoring, the generation of invalid data can be reduced, data quality can be improved, and more valuable information can be provided for subsequent analysis and decision-making.
[0017] 3. By comprehensively considering the water quality data of multiple related monitoring devices, the water quality status can be analyzed from multiple angles and dimensions, so as to more accurately identify the type and degree of pollution. The position relationship map reveals the spatial relationship between the monitoring points, which helps to understand the distribution and diffusion of pollutants in space, and further improves the accuracy of pollution identification. By comparing the changes in water quality data at different monitoring points, the source and diffusion path of pollutants can be tracked, which helps to quickly locate the source of pollution. Combining geographic location information and water quality data, it is possible to conduct in-depth analysis of the pollution source, understand the type, concentration and possible impact range of pollutants, and provide strong support for subsequent pollution control. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:
[0019] Figure 1 It is a module schematic diagram of a water pollution intelligent monitoring system based on the Internet of Things and edge computing according to some embodiments of this specification;
[0020] Figure 2 is a schematic diagram of a position relationship map according to some embodiments of this specification;
[0021] Figure 3 It is a flow chart of an intelligent water pollution monitoring method based on the Internet of Things and edge computing as shown in some embodiments of this specification. DETAILED DESCRIPTION
[0022] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.
[0023] Figure 1 is a module schematic diagram of a water pollution intelligent monitoring system based on the Internet of Things and edge computing according to some embodiments of this specification, such as Figure 1 As shown, the intelligent water pollution monitoring system based on the Internet of Things and edge computing can include a location determination module, a data acquisition module, a correlation analysis module, a data processing module and a pollution analysis module.
[0024] The location determination module can be used to determine multiple water pollution monitoring locations in the area to be monitored.
[0025] Specifically include:
[0026] Obtain geographic information of the area to be monitored;
[0027] Determine multiple initial water pollution monitoring locations based on geographic information of the area to be monitored;
[0028] Obtaining first test water quality information for each initial water pollution monitoring location;
[0029] Calculating differential parameters of a plurality of initial water pollution monitoring locations based on first test water quality information of each initial water pollution monitoring location;
[0030] When the differentiation parameter is greater than a preset differentiation parameter, at least one water pollution monitoring position is added, wherein the multiple water pollution monitoring positions include multiple initial water pollution monitoring positions and at least one newly added water pollution monitoring position.
[0031] Specifically, the geographic information of the area to be monitored may include the natural environment of the area to be monitored, for example, the topography and geomorphic features, including the distribution and flow direction of water bodies such as rivers, lakes, reservoirs, and wetlands. The geographic information of the area to be monitored may also include the land use types in the area, such as industrial areas, agricultural areas, residential areas, nature reserves, etc. The geographic information of the area to be monitored may also include hydrological conditions, including water flow velocity, water level changes, water body capacity, etc.
[0032] The area to be monitored is divided into grids, and then the initial water pollution monitoring locations are set at the intersection or boundary of each grid.
[0033] The first test water quality information may include values of various detection parameters (eg, turbidity, conductivity, pH value, chemical oxygen demand, biochemical oxygen demand, etc.).
[0034] The differentiation parameter can be calculated based on the following formula:
[0035]
[0036] in, is the differentiation parameter, is the cosine similarity between the first test water quality information of the i-th initial water pollution monitoring location and the first test water quality information of the j-th initial water pollution monitoring location, is the total number of initial water pollution monitoring locations.
[0037] In some embodiments, the location determination module adds at least one water pollution monitoring location, including:
[0038] Based on the water quality difference parameters of the test water quality information of any two initial water pollution monitoring locations, at least one water pollution monitoring location is added.
[0039] Specifically, the number of newly added water pollution monitoring locations between two initial water pollution monitoring locations can be determined based on the following formula:
[0040] N i , j = [ α 1 S i , j × N 0 ]
[0041] in, is the number of newly added water pollution monitoring locations between the i-th initial water pollution monitoring location and the j-th initial water pollution monitoring location, is the preset parameter, and , [ ] is the rounding operation, The preset quantity.
[0042] The data acquisition module may include a plurality of water pollution monitoring devices set in the area to be monitored based on a plurality of water pollution monitoring positions in the area to be monitored, wherein the water pollution monitoring devices are used to collect water quality related data.
[0043] The correlation analysis module can be used to determine the correlation between multiple water pollution monitoring locations and establish a location relationship map.
[0044] Specifically include:
[0045] Obtaining water quality information for a second test at each water pollution monitoring location;
[0046] Calculate the correlation coefficient between any two water pollution monitoring locations based on the second test water quality information of each water pollution monitoring location;
[0047] For each water pollution monitoring location, based on the correlation coefficient of any two water pollution monitoring locations, determine the associated water pollution monitoring location of the water pollution monitoring location, and based on the second test water quality information of each water pollution monitoring location, determine the association relationship between the water pollution monitoring location and each associated water pollution monitoring location;
[0048] Based on the association between the water pollution monitoring location and each associated water pollution monitoring location, a position relationship map is established.
[0049] Specifically, the water quality information for the second test is similar to the water quality information for the first test, and will not be described in detail here.
[0050] In some embodiments, the correlation analysis module calculates the correlation coefficient of any two water pollution monitoring locations based on the second test water quality information of each initial water pollution monitoring location, including:
[0051] For any two water pollution detection locations, based on the second test water quality information of the two water pollution detection locations, the parameter correlation coefficients of the two water pollution detection locations in the target detection parameters (for example, turbidity, conductivity, pH value, chemical oxygen demand, biochemical oxygen demand, etc.) are calculated; based on the parameter correlation coefficients of the two water pollution detection locations in the target detection parameters, the correlation coefficients of the two water pollution monitoring locations are calculated.
[0052] The correlation coefficient of two water pollution monitoring locations can be calculated based on the following formula:
[0053]
[0054]
[0055]
[0056] in, is the correlation coefficient between the ith water pollution monitoring location and the jth water pollution monitoring location, is the association weight corresponding to the nth target detection parameter, is the parameter correlation coefficient of the target detection parameters at the i-th water pollution monitoring location and the j-th water pollution monitoring location, is the value of the nth target detection parameter at the tth time point in the second test water quality information at the ith water pollution monitoring location, is the mean value of the nth target detection parameter in the second test water quality information at the i-th water pollution monitoring location, is the value of the nth target detection parameter of the jth water pollution monitoring location at the tth time point in the second test water quality information, is the mean value of the nth target detection parameter in the second test water quality information at the jth water pollution monitoring location, It is the total number of time points sampled in the water quality information used in the second test.
[0057] When the correlation coefficient of two water pollution monitoring locations is greater than a preset correlation coefficient, the two water pollution monitoring locations are mutually associated water pollution monitoring locations. Figure 2 is a schematic diagram of a position relationship map according to some embodiments of this specification, such as Figure 2 As shown, the corresponding nodes of the mutually related water pollution monitoring locations in the position relationship map can be connected by edges, and the edges can also represent the correlation relationship between the mutually related water pollution monitoring locations.
[0058] In some embodiments, the correlation analysis module determines the correlation relationship between the water pollution monitoring location and each associated water pollution monitoring location based on the second test water quality information of each water pollution monitoring location, including:
[0059] Determine multiple time lag windows;
[0060] For each associated water pollution monitoring location, based on the second test water quality information of each water pollution monitoring location, the water quality similarity between the water pollution monitoring location and the associated water pollution monitoring location in the time lag window is determined; when the water quality similarity is greater than the preset water quality similarity, the time lag window is marked as a target time lag window; based on the target time lag window, the association relationship between the water pollution monitoring location and the associated water pollution monitoring location is determined.
[0061] For example, for the associated water pollution monitoring position A of the water pollution monitoring position, the second test water quality information of the associated water pollution monitoring position is advanced by 3 minutes, 5 minutes, 10 minutes and delayed by 3 minutes, 5 minutes, and 10 minutes respectively to obtain the second test water quality information advanced by 3 minutes, the second test water quality information advanced by 3 minutes, the second test water quality information advanced by 10 minutes, the second test water quality information delayed by 3 minutes, the second test water quality information delayed by 3 minutes and the second test water quality information delayed by 10 minutes corresponding to the associated water pollution monitoring position A, and the water quality similarity between the second test water quality information advanced by 3 minutes, the second test water quality information advanced by 3 minutes, the second test water quality information advanced by 10 minutes, the second test water quality information delayed by 3 minutes, the second test water quality information delayed by 10 minutes and the second test water quality information delayed by 10 minutes and the original second test water quality information of the associated water pollution monitoring position A is calculated respectively. When the water quality similarity between the second test water quality information 3 minutes in advance and the original second test water quality information of the associated water pollution monitoring location A is greater than the preset water quality similarity, the 3 minutes in advance is determined to be the target time lag window, and the water pollution monitoring location is determined to be upstream of the associated water pollution monitoring location A. When the water quality similarity between the second test water quality information 5 minutes delayed and the original second test water quality information of the associated water pollution monitoring location A is greater than the preset water quality similarity, the 5 minutes delay is determined to be the target time lag window, and the water pollution monitoring location is determined to be downstream of the associated water pollution monitoring location A.
[0062] If the target time lag window is an advance time window, the association relationship between the water pollution monitoring position and the associated water pollution monitoring position is that the water pollution monitoring position is upstream of the associated water pollution monitoring position; if the target time lag window is a delayed time window, the association relationship between the water pollution monitoring position and the associated water pollution monitoring position is that the water pollution monitoring position is downstream of the associated water pollution monitoring position; if the target time lag window is 0, the association relationship between the water pollution monitoring position and the associated water pollution monitoring position is a parallel relationship.
[0063] The water quality similarity between the water pollution monitoring location and the associated water pollution monitoring location in the time lag window can be calculated based on the following formula:
[0064]
[0065] in, is the water quality similarity between the ith water pollution monitoring location and the jth associated water pollution monitoring location of the ith water pollution monitoring location in the time lag window, is the preset parameter, and , It is the value of the nth target detection parameter at the tth time point in the second test water quality information of the jth associated water pollution monitoring position corresponding to the time lag window of the ith water pollution monitoring position.
[0066] The data processing module may include determining multiple edge computing devices based on a position relationship map, wherein one edge computing device corresponds to at least one water pollution monitoring location, and the edge computing device is used to determine whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on water quality-related data collected by the water pollution monitoring device. If so, the water pollution monitoring device is marked as a target water pollution monitoring device.
[0067] In some embodiments, the edge computing device determines whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on the water quality related data collected by the water pollution monitoring device, including:
[0068] The pollution judgment model is used to judge whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on water quality related data collected by the water pollution monitoring device at multiple time points in the current water quality detection cycle. The pollution judgment model can be a long short-term memory network (LSTM, Long Short-Term Memory) model.
[0069] The pollution analysis module can be used to determine the type and source of pollution based on the target water pollution monitoring devices determined by multiple edge computing devices, the water quality-related data collected by multiple water pollution monitoring devices, and the location relationship map.
[0070] In some embodiments, the pollution analysis module determines the pollution type based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality related data collected by the multiple water pollution monitoring devices, and the position relationship map, including:
[0071] Determine the associated water pollution monitoring devices of the target water pollution monitoring device based on the position relationship map;
[0072] The pollution type is determined based on the water quality related data collected by the associated water pollution monitoring device of the target water pollution monitoring device at multiple time points in the current water quality detection cycle and the water quality related data collected by the associated water pollution monitoring device of the target water pollution monitoring device at multiple time points in the current water quality detection cycle.
[0073] Specifically, the pollution type (for example, organic pollution, heavy metal pollution, etc.) can be determined through the pollution type prediction model based on water quality related data collected by the associated water pollution monitoring device of the target water pollution monitoring device at multiple time points in the current water quality detection cycle and water quality related data collected by the associated water pollution monitoring device of the target water pollution monitoring device at multiple time points in the current water quality detection cycle, wherein the pollution type prediction model can be a long short-term memory network (LSTM, Long Short-Term Memory) model.
[0074] In some embodiments, the pollution analysis module determines the pollution source based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality related data collected by the multiple water pollution monitoring devices, and the position relationship map, including:
[0075] Based on the target water pollution monitoring device, determine the target water pollution monitoring position. Specifically, the water pollution monitoring position where the target water pollution monitoring device is located is the target water pollution monitoring position.
[0076] Determine the source of pollution based on the location relationship map and target water pollution monitoring locations.
[0077] Specifically, the pollution source can be determined through a source analysis model based on a position relationship map and a target water pollution monitoring location, wherein the source analysis model can be a convolutional neural network (CNN) model.
[0078] Figure 3 is a flow chart of a water pollution intelligent monitoring method based on the Internet of Things and edge computing according to some embodiments of this specification, such as Figure 3 As shown, the intelligent water pollution monitoring method based on the Internet of Things and edge computing may include the following steps.
[0079] Step 310, determining a plurality of water pollution monitoring locations in the area to be monitored;
[0080] Step 320, based on a plurality of water pollution monitoring locations in the area to be monitored, determining a plurality of water pollution monitoring devices arranged in the area to be monitored, wherein the water pollution monitoring devices are used to collect water quality related data;
[0081] Step 330, determining the correlation relationship between multiple water pollution monitoring locations and establishing a location relationship map;
[0082] Step 340, determining a plurality of edge computing devices based on the position relationship map, wherein one edge computing device corresponds to at least one water pollution monitoring location;
[0083] Step 350: The edge computing device determines whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on the water quality-related data collected by the water pollution monitoring device. If so, the water pollution monitoring device is marked as a target water pollution monitoring device.
[0084] Step 360, determine the pollution type and pollution source based on the target water pollution monitoring device determined by multiple edge computing devices, the water quality related data collected by multiple water pollution monitoring devices, and the position relationship map.
[0085] The intelligent water pollution monitoring method based on the Internet of Things and edge computing can be executed by an intelligent water pollution monitoring system based on the Internet of Things and edge computing. For more descriptions of the intelligent water pollution monitoring method based on the Internet of Things and edge computing, please refer to the relevant descriptions of the intelligent water pollution monitoring system based on the Internet of Things and edge computing, which will not be repeated here.
[0086] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.
Claims
1. The intelligent water pollution monitoring system based on the Internet of Things and edge computing is characterized by: include: A location determination module, used to determine multiple water pollution monitoring locations in the area to be monitored; A data acquisition module, comprising a plurality of water pollution monitoring devices set in the area to be monitored, determined based on a plurality of water pollution monitoring positions in the area to be monitored, wherein the water pollution monitoring devices are used to collect water quality related data; Correlation analysis module, used to determine the correlation between multiple water pollution monitoring locations and establish a location relationship map; A data processing module, comprising: determining a plurality of edge computing devices based on the position relationship map, wherein one edge computing device corresponds to at least one water pollution monitoring location, and the edge computing device is used to determine whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on water quality-related data collected by the water pollution monitoring device, and if so, marking the water pollution monitoring device as a target water pollution monitoring device; A pollution analysis module, configured to determine the type and source of pollution based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality-related data collected by the multiple water pollution monitoring devices, and the position relationship map; The location determination module determines a plurality of water pollution monitoring locations in the area to be monitored, including: Obtain geographic information of the area to be monitored; Based on the geographic information of the area to be monitored, determining a plurality of initial water pollution monitoring locations; Acquire first test water quality information for each of the initial water pollution monitoring locations; Calculating the differential parameters of the plurality of initial water pollution monitoring locations based on the first test water quality information of each of the initial water pollution monitoring locations; When the differentiation parameter is greater than a preset differentiation parameter, at least one water pollution monitoring position is added, wherein the multiple water pollution monitoring positions include the multiple initial water pollution monitoring positions and at least one newly added water pollution monitoring position.
2. The water pollution intelligent monitoring system based on the Internet of Things and edge computing according to claim 1 is characterized in that: The location determination module adds at least one water pollution monitoring location, including: Based on the water quality difference parameter of the test water quality information of any two initial water pollution monitoring locations, at least one water pollution monitoring location is added.
3. The water pollution intelligent monitoring system based on the Internet of Things and edge computing according to claim 1 or 2 is characterized in that: The correlation analysis module determines the correlation relationship between multiple water pollution monitoring locations and establishes a location relationship map, including: Acquire the second test water quality information for each of the water pollution monitoring locations; Calculate the correlation coefficient between any two water pollution monitoring locations based on the second test water quality information of each water pollution monitoring location; For each of the water pollution monitoring positions, based on the correlation coefficient of any two of the water pollution monitoring positions, determine the associated water pollution monitoring position of the water pollution monitoring position, and based on the second test water quality information of each of the water pollution monitoring positions, determine the association relationship between the water pollution monitoring position and each of the associated water pollution monitoring positions; The position relationship map is established based on the association relationship between the water pollution monitoring location and each of the associated water pollution monitoring locations.
4. The water pollution intelligent monitoring system based on the Internet of Things and edge computing according to claim 2 is characterized in that: The correlation analysis module calculates the correlation coefficient of any two water pollution monitoring positions based on the second test water quality information of each of the initial water pollution monitoring positions, including: For any two of the water pollution monitoring locations, based on the second test water quality information of the two water pollution monitoring locations, the parameter correlation coefficients of the target detection parameters at the two water pollution monitoring locations are calculated; based on the parameter correlation coefficients of the target detection parameters at the two water pollution monitoring locations, the correlation coefficients of the two water pollution monitoring locations are calculated.
5. The water pollution intelligent monitoring system based on the Internet of Things and edge computing according to claim 2 is characterized in that: The correlation analysis module determines the correlation relationship between the water pollution monitoring location and each of the associated water pollution monitoring locations based on the second test water quality information of each of the water pollution monitoring locations, including: Determine multiple time lag windows; For each of the associated water pollution monitoring locations, based on the second test water quality information of each of the water pollution monitoring locations, the water quality similarity between the water pollution monitoring location and the associated water pollution monitoring location in the time lag window is determined; when the water quality similarity is greater than a preset water quality similarity, the time lag window is marked as a target time lag window; based on the target time lag window, the association relationship between the water pollution monitoring location and the associated water pollution monitoring location is determined.
6. The water pollution intelligent monitoring system based on the Internet of Things and edge computing according to claim 1 or 2 is characterized in that: The edge computing device determines whether pollution occurs at a water pollution monitoring location where the water pollution monitoring device is located based on the water quality related data collected by the water pollution monitoring device, including: The pollution judgment model is used to judge whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on water quality related data collected by the water pollution monitoring device at multiple time points in the current water quality detection cycle.
7. The water pollution intelligent monitoring system based on the Internet of Things and edge computing according to claim 3 is characterized in that: The pollution analysis module determines the pollution type based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality related data collected by the multiple water pollution monitoring devices, and the position relationship map, including: Determining the associated water pollution monitoring device of the target water pollution monitoring device based on the position relationship map; The pollution type is determined based on the water quality related data collected by the associated water pollution monitoring device of the target water pollution monitoring device at multiple time points in the current water quality detection cycle and the water quality related data collected by the associated water pollution monitoring device of the target water pollution monitoring device at multiple time points in the current water quality detection cycle.
8. The water pollution intelligent monitoring system based on the Internet of Things and edge computing according to claim 3 is characterized in that: The pollution analysis module determines the pollution source based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality related data collected by the multiple water pollution monitoring devices, and the position relationship map, including: Based on the target water pollution monitoring device, determining a target water pollution monitoring location; Based on the position relationship map and the target water pollution monitoring location, the pollution source is determined.
9. The intelligent water pollution monitoring method based on the Internet of Things and edge computing is characterized by: include: Identify multiple water pollution monitoring locations in the area to be monitored; Based on the multiple water pollution monitoring positions in the area to be monitored, determining multiple water pollution monitoring devices set in the area to be monitored, wherein the water pollution monitoring devices are used to collect water quality related data; Determine the correlation between multiple water pollution monitoring locations and establish a location relationship map; Based on the position relationship map, determining a plurality of edge computing devices, wherein one edge computing device corresponds to at least one of the water pollution monitoring locations; The edge computing device determines whether pollution occurs at the water pollution monitoring location where the water pollution monitoring device is located based on the water quality related data collected by the water pollution monitoring device, and if so, marks the water pollution monitoring device as a target water pollution monitoring device; Determine the type and source of pollution based on the target water pollution monitoring devices determined by the multiple edge computing devices, the water quality-related data collected by the multiple water pollution monitoring devices, and the position relationship map; Identify multiple water pollution monitoring locations in the area to be monitored, including: Obtain geographic information of the area to be monitored; Based on the geographic information of the area to be monitored, determining a plurality of initial water pollution monitoring locations; Acquire first test water quality information for each of the initial water pollution monitoring locations; Calculating the differential parameters of the plurality of initial water pollution monitoring locations based on the first test water quality information of each of the initial water pollution monitoring locations; When the differentiation parameter is greater than a preset differentiation parameter, at least one water pollution monitoring position is added, wherein the multiple water pollution monitoring positions include the multiple initial water pollution monitoring positions and at least one newly added water pollution monitoring position.
