Water quality multi-parameter real-time monitoring system

Abstract

The invention relates to the technical field of water quality monitoring, and discloses a water quality multi-parameter real-time monitoring system. The system comprises a monitoring point position configuration module, a water quality parameter acquisition module, a pollution index calculation module, an anomaly detection module, a central control unit and the like. The monitoring point position configuration module sets monitoring point positions and generates acquisition rules; the water quality parameter acquisition module acquires a water quality parameter set according to rules; the pollution index calculation module calculates a pollution index; the anomaly detection module obtains an anomaly detection index; and the central control unit comprehensively analyzes and generates water quality evaluation parameters. In addition, the system is further provided with a pollution source tracking module, a storage unit and an alarm module, pollution sources can be tracked, data can be stored, and an alarm can be given according to evaluation parameters. The system realizes multi-parameter real-time monitoring, accurate analysis and evaluation and pollution source tracking, provides comprehensive support for water quality management, effectively improves the water environment monitoring level, and guarantees the safety of water resources.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality monitoring, and in particular to a water quality multi-parameter real-time monitoring system. Background Art

[0002] With the acceleration of industrialization and urbanization, water pollution is becoming increasingly serious. Monitoring and controlling water quality has become a key component in ensuring ecological security and human health. Traditional water quality monitoring methods have exposed many limitations in practical applications.

[0003] From the perspective of monitoring methods, manual sampling and testing is one of the important methods of traditional monitoring. Manual sampling requires professionals to go to the monitoring points, collect water samples according to specific specifications, and then send them back to the laboratory for analysis and testing. This process consumes a lot of manpower, material resources and time costs, and the monitoring frequency is often low, which makes it difficult to meet the needs of real-time grasp of dynamic changes in water quality. In some sudden water pollution incidents, the lag of manual sampling and testing will lead to the inability to detect pollution and take effective measures in a timely manner, thereby expanding the scope of pollution and posing a greater threat to the ecological environment and human water safety. For example, if a chemical raw material leak occurs in the upper reaches of a river, if manual sampling and testing are relied upon, it may take hours or even days to detect water quality abnormalities. At this time, the pollution may have spread to many areas downstream, affecting the water use of a large number of residents and the survival of aquatic organisms.

[0004] In terms of monitoring parameters, early water quality monitoring systems were typically only able to monitor a few common parameters, such as pH and dissolved oxygen. However, pollutants in modern water environments are numerous and complex in composition, and monitoring only these conventional parameters cannot fully and accurately assess water quality. Taking lake eutrophication as an example, in addition to conventional parameters, it is also necessary to monitor a variety of nutrient indicators such as total nitrogen, total phosphorus, and ammonia nitrogen, as well as biological indicators such as algae density. If the monitoring system does not cover these key parameters, it will be impossible to detect lake eutrophication trends in a timely manner, making it difficult to provide early warning of the risk of algal blooms, which in turn will cause serious damage to the lake ecosystem and affect the surrounding ecological balance and economic development.

[0005] Traditional monitoring technologies face even greater challenges when it comes to tracing pollution sources. When water pollution occurs, it's difficult to quickly and accurately determine the location, type, and extent of the pollution source. Because water is fluid, pollutants diffuse and migrate with the flow, and their propagation paths are complex and varied. Furthermore, pollutants emitted by different pollution sources mix and transform within the water, further increasing the difficulty of tracing pollution sources. For example, in urban river pollution control, there may be multiple pollution sources, including multiple industrial enterprises, domestic sewage outlets, and agricultural non-point source pollution. Traditional monitoring methods are unable to accurately locate the main pollution sources, making control efforts less targeted. Even after investing significant amounts of money and manpower, the results remain unsatisfactory, and water resource waste and ecological damage persist.

[0006] In terms of data analysis and assessment, traditional monitoring systems often collect fragmented data, lacking effective integration and in-depth analysis capabilities. They are unable to conduct comprehensive assessments based on multi-parameter data, making it difficult to accurately determine the overall water quality status and potential risks. Furthermore, they suffer from serious deficiencies in real-time data processing and feedback, making it difficult to generate intuitive and understandable assessment reports and early warning information based on monitoring data in a timely manner, providing a scientific basis for water resource management decisions.

[0007] Given the aforementioned shortcomings of traditional water quality monitoring technology, it is imperative to develop a multi-parameter real-time water quality monitoring system that can monitor multiple parameters in real time, accurately calculate pollution indices, efficiently detect anomalies, accurately track pollution sources, and perform comprehensive analysis and assessment. This is of great practical significance for improving water environment monitoring and ensuring water resource security. Summary of the Invention

[0008] The purpose of the present invention is to provide a water quality multi-parameter real-time monitoring system to solve the problems raised in the above background technology.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a water quality multi-parameter real-time monitoring system, the system comprising: A monitoring point configuration module is used to set monitoring points within the target monitoring area and generate corresponding parameter collection rules based on the monitoring points; A water quality parameter acquisition module is used to obtain the water quality parameter set of the monitoring point from the water quality database in real time according to the parameter acquisition rule, and use all parameters in the water quality parameter set as monitoring dimension parameters of the monitoring point; A pollution index calculation module is used to calculate the pollution index of the monitoring point through a multi-dimensional fusion algorithm based on the pollution source association relationship preset in the water quality database, and use the pollution index of the monitoring point as the monitoring dimension parameter of the monitoring point; An anomaly detection module, configured to obtain an anomaly detection index of the monitoring point through a preset dynamic threshold analysis method, and use the anomaly detection index of the monitoring point as a monitoring dimension parameter of the monitoring point; A central control unit is configured to send the monitoring points to the pollution index calculation module and the anomaly detection module, send the parameter collection rules to the water quality parameter collection module, and perform a comprehensive analysis of all the monitoring dimension parameters of the monitoring points to generate water quality assessment parameters for the monitoring points; Wherein, the water quality database includes a preset pollution source database and / or a real-time monitoring database.

[0010] Preferably, the method of obtaining the abnormality detection index of the monitoring point by using a preset dynamic threshold analysis method includes: The monitoring point and a preset reference point within the watershed to which the monitoring point belongs are used as dynamic analysis units, all historical water quality data are obtained based on the watershed to which the monitoring point belongs, and a parameter fluctuation pattern of the dynamic analysis unit in a historical period is determined; On the basis of the parameter fluctuation pattern, and based on the fluctuation amplitude of each of the historical water quality data in the corresponding dynamic analysis unit, calculating the initial abnormality index of each of the dynamic analysis units and the initial deviation index of each of the historical water quality data; Based on the initial abnormality index of each dynamic analysis unit and the initial deviation index of each historical water quality data, a bidirectional iterative model is used to achieve synchronous optimization of the abnormality detection index of each dynamic analysis unit and the deviation index of each historical water quality data, so as to obtain the final abnormality index of each dynamic analysis unit, and the final abnormality index of the dynamic analysis unit corresponding to the monitoring point is used as the abnormality detection index of the monitoring point; Set the comparative dynamic analysis unit to be any one of all the dynamic analysis units, and the comparative historical water quality data to be any one of all the historical water quality data. At the same time, based on the parameter fluctuation pattern, take the fluctuation amount of the comparative dynamic analysis unit in the comparative historical water quality data as a separate fluctuation amount, take the total fluctuation amount of the comparative dynamic analysis unit in all the historical water quality data as a separate total fluctuation amount, take the fluctuation amount of all the dynamic analysis units in the comparative historical water quality data as an overall fluctuation amount, and take the total fluctuation amount of all the dynamic analysis units in all the historical water quality data as an overall total fluctuation amount. At this time, judge whether the ratio of the separate fluctuation amount to the separate total fluctuation amount is greater than the ratio of the overall fluctuation amount to the overall total fluctuation amount. If so, it is determined that the comparative dynamic analysis unit has significant anomalies in the comparative historical water quality data. Otherwise, it is determined that the comparative dynamic analysis unit does not have significant anomalies in the comparative historical water quality data. Preferably, the parameter collection rules include a basic parameter type group and an extended parameter type group; the basic parameter type group contains multiple basic parameter types and a fixed weight corresponding to each basic parameter type; the extended parameter type group contains multiple extended parameter types and a dynamic weight corresponding to each extended parameter type.

[0011] Preferably, the step of acquiring the water quality parameter set of the monitoring point in real time from the water quality database according to the parameter collection rule includes: The water quality parameter acquisition module extracts the structured monitoring data of the monitoring point from the water quality database, extracts the corresponding basic parameters from the structured monitoring data based on each basic parameter type in the basic parameter type group, and extracts the corresponding extended parameters from the structured monitoring data based on each extended parameter type in the extended parameter type group, and summarizes all the basic parameters and all the extended parameters into a water quality parameter set for the monitoring point.

[0012] Preferably, when the preset pollution source association relationship is a direct pollution source relationship, it is determined whether the monitoring point is associated with a pollution source node in the water quality database. If so, the pollution index of the monitoring point is the accumulation of pollution contribution values of all pollution source nodes associated with the monitoring point. Otherwise, the pollution index of the monitoring point is the basic pollution value of the monitoring point itself. When the preset pollution source association relationship is an indirect pollution source relationship, the pollution index of the monitoring point is the weighted sum of the pollution contribution values of all pollution source nodes obtained by the monitoring point through the upstream and downstream association paths.

[0013] Preferably, it further comprises a pollution source tracking module connected to the central control unit; The pollution source tracking module is used to set the target pollution type, obtain the spatiotemporal correlation between the monitoring point and the target pollution type through a preset spatiotemporal correlation analysis method, and use the spatiotemporal correlation as the monitoring dimension parameter of the monitoring point.

[0014] Preferably, the pollution source tracking module obtains the spatiotemporal correlation between the monitoring point and the target pollution type by a preset spatiotemporal correlation analysis method, including: Obtaining a historical pollution diffusion path set of the monitoring point from a pollution diffusion model library, obtaining a standard diffusion path set of the target pollution type from the pollution diffusion model library, and using the spatiotemporal overlap between the historical pollution diffusion path set and the standard diffusion path set as a first correlation degree between the monitoring point and the target pollution type; Dynamically matching the pollution concentration change curve of the monitoring point within a preset time period with the standard concentration change curve of the target pollution type, and obtaining the waveform similarity between the two as a second correlation degree between the monitoring point and the target pollution type; The first correlation degree, the second correlation degree, or a weighted average of the first correlation degree and the second correlation degree is used as the spatiotemporal correlation degree between the monitoring point and the target pollution type.

[0015] Preferably, the central control unit performs linear superposition or nonlinear fusion on all the monitoring dimension parameters of the monitoring points to generate the water quality assessment parameters.

[0016] Preferably, it also includes a storage unit connected to the central control unit, the storage unit is used to store the water quality parameter set of the monitoring point, the pollution index of the monitoring point, the abnormality detection index of the monitoring point and the water quality assessment parameter of the monitoring point.

[0017] Preferably, it also includes an alarm module connected to the central control unit, which is used to generate a graded alarm signal based on the comparison result of the water quality assessment parameter and the preset safety threshold, and send the graded alarm signal to the designated terminal device through the communication network.

[0018] Compared with the prior art, the present invention has the following beneficial effects: In terms of comprehensive and real-time monitoring capabilities, the Monitoring Point Configuration Module allows for flexible configuration of monitoring points within the target monitoring area and generates corresponding parameter collection rules. The Water Quality Parameter Collection Module, based on these rules, retrieves the water quality parameter set for each monitoring point from the water quality database in real time. This includes both basic and extended parameters, significantly enriching the range of monitoring parameters and providing a comprehensive picture of water quality. Compared to traditional monitoring methods, this eliminates the need for frequent manual sampling and testing, enabling real-time updates of water quality data. This allows managers to promptly monitor dynamic changes in water quality and respond quickly to sudden pollution incidents.

[0019] For pollution analysis, the pollution index calculation module uses a multi-dimensional fusion algorithm based on pre-set pollution source relationships to calculate the pollution index. Whether directly or indirectly related to pollution sources, it can accurately determine the pollution index at each monitoring point, providing precise data support for pollution control. For example, when monitoring rivers in industrial areas, it can clearly distinguish the degree of impact of different pollution sources at each monitoring point, helping control personnel develop targeted control plans, improve control efficiency, and reduce control costs.

[0020] The anomaly detection module uses a preset dynamic threshold analysis method to obtain anomaly detection indicators. This method comprehensively considers historical water quality data and parameter fluctuation patterns at the monitoring point and preset reference points within the basin. It then optimizes the indicators through a bidirectional iterative model to accurately identify water quality anomalies. This method is more flexible and accurate than traditional fixed threshold detection, effectively avoiding false positives and missed positives, promptly identifying potential water quality risks, and ensuring the stability of the aquatic ecosystem and water safety.

[0021] For pollution source tracking, the system has added a pollution source tracking module that uses a preset spatiotemporal correlation analysis method to determine the spatiotemporal correlation between monitoring points and target pollution types. This module accurately tracks pollution sources through multi-dimensional analysis, including the spatiotemporal overlap between historical pollution diffusion paths and standard diffusion paths, as well as the waveform similarity of pollution concentration curves. This provides a strong basis for pollution source tracing and responsibility determination, helping to address water pollution issues at their source.

[0022] The central control unit comprehensively analyzes all monitored parameters to generate water quality assessment parameters, using either linear superposition or nonlinear fusion methods to fully leverage the data's value and provide a comprehensive and accurate assessment of water quality. Furthermore, the storage unit stores all monitoring data for easy query, analysis, and comparison, providing data support for long-term water environment research and governance. The alarm module generates graded alarm signals based on the comparison of water quality assessment parameters with preset safety thresholds and transmits them to designated terminal devices via the communication network, ensuring that relevant personnel receive timely information on water quality anomalies and can quickly implement countermeasures to minimize losses caused by water pollution.

[0023] The entire system integrates water quality monitoring, analysis, assessment, early warning and pollution source tracking, improves the intelligence and scientific level of water quality monitoring, provides efficient and reliable technical means for water resource protection and management, and effectively promotes the development of water environment governance. It is of great significance to ensuring ecological balance and promoting sustainable social and economic development. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a working principle diagram of the water quality multi-parameter real-time monitoring system of the present invention; Figure 2 Flowchart obtained for anomaly detection metrics; Figure 3 Flowcharts obtained for the water quality parameter set; Figure 4 Flowchart generated for water quality assessment parameters. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] See also Figure 1-Figure 4 The present invention provides a water quality multi-parameter real-time monitoring system, and its specific implementation method is described in detail below.

[0027] The monitoring point configuration module is responsible for setting the monitoring points within the target monitoring area. Staff determine the locations of each monitoring point based on the actual conditions of the monitoring area, such as river flow and water area functional divisions. Once the monitoring points are determined, the module generates corresponding parameter collection rules based on these monitoring points. These rules specify which parameters to collect from the water quality database and how to collect them.

[0028] The water quality parameter collection module uses the parameter collection rules generated above to retrieve the water quality parameter sets for each monitoring point in real time from the water quality database. This database includes a pre-defined pollution source database and / or a real-time monitoring database. This module uses all acquired parameters as monitoring dimension parameters for each monitoring point, providing basic data for subsequent analysis.

[0029] The pollution index calculation module uses a multi-dimensional fusion algorithm to calculate the pollution index of each monitoring point based on the pollution source associations preset in the water quality database. This pollution index also serves as a monitoring dimension parameter for the monitoring point, used to measure the degree of pollution at the monitoring point.

[0030] The anomaly detection module uses a preset dynamic threshold analysis method to obtain the anomaly detection index of the monitoring point, and also uses it as the monitoring dimension parameter of the monitoring point to determine whether there is an abnormality in the water quality.

[0031] As the core of the system, the central control unit (CCU) undertakes several important tasks. It transmits monitoring point data to the pollution index calculation module and anomaly detection module, while also sending parameter collection rules to the water quality parameter collection module, enabling data exchange between these modules. Furthermore, the CCU performs a comprehensive analysis of all monitoring parameters at each monitoring point to generate water quality assessment parameters for that point, providing a comprehensive assessment of the water quality at that point.

[0032] The present invention will be further described below in conjunction with Examples 1 to 6: Example 1

[0033] This embodiment is used to illustrate the process of the anomaly detection module obtaining the anomaly detection index of the monitoring point through a preset dynamic threshold analysis method. The monitoring point and the preset reference point in the watershed to which the monitoring point belongs are set as dynamic analysis units. In order to accurately grasp the law of water quality changes, it is necessary to obtain all historical water quality data based on the watershed to which the monitoring point belongs. For example, by collecting and arranging the water quality monitoring records of the watershed over the past years, data from different seasons and different weather conditions are covered. Then determine the parameter fluctuation pattern of these dynamic analysis units in the historical period. For example, at some monitoring points in the summer flood season, the dissolved oxygen content in the water will have a certain upward trend, and it will decrease during the winter dry season. This is a parameter fluctuation pattern.

[0034] Based on the determined parameter fluctuation pattern, the initial abnormality index and initial deviation index for each historical water quality data point are calculated for each dynamic analysis unit. For each historical water quality data point, the fluctuation range within the corresponding dynamic analysis unit is observed. If the fluctuation range of a water quality parameter (such as ammonia nitrogen content) at a monitoring point within a certain time period is significantly greater than its normal fluctuation range, it can be preliminarily determined that the data may be abnormal, and the corresponding initial abnormality index and initial deviation index are calculated.

[0035] Based on the initial anomaly indicator for each dynamic analysis unit and the initial deviation indicator for each historical water quality data set, a bidirectional iterative model is used to simultaneously optimize the anomaly detection indicator for each dynamic analysis unit and the deviation indicator for each historical water quality data set. During the iterative process, the indicator calculation method is continuously adjusted to more accurately reflect the actual situation. After multiple iterations, the final anomaly indicator for each dynamic analysis unit is obtained, and the final anomaly indicator of the dynamic analysis unit corresponding to the monitoring point is used as the anomaly detection indicator for that monitoring point.

[0036] Perform abnormality judgment. Set the comparative dynamic analysis unit to any one of all dynamic analysis units, and the comparative historical water quality data to any one of all historical water quality data. Based on the parameter fluctuation pattern, calculate the fluctuation amount of the comparative dynamic analysis unit in the comparative historical water quality data, and use it as a separate fluctuation amount; calculate the total fluctuation amount of the comparative dynamic analysis unit in all historical water quality data as a separate total fluctuation amount; calculate the fluctuation amount of all dynamic analysis units in the comparative historical water quality data as an overall fluctuation amount; calculate the total fluctuation amount of all dynamic analysis units in all historical water quality data as an overall total fluctuation amount. By judging whether the ratio of the individual fluctuation amount to the individual total fluctuation amount is greater than the ratio of the overall fluctuation amount to the overall total fluctuation amount, determine whether there is a significant abnormality in the comparative historical water quality data of the comparative dynamic analysis unit. If it is greater, it is determined that there is a significant abnormality; otherwise, there is no significant abnormality. In this way, the abnormality of the water quality at the monitoring point can be accurately detected, providing a strong basis for taking corresponding measures later. Example 2

[0037] Parameter collection rules include basic parameter type groups and extended parameter type groups. The basic parameter type group contains multiple basic parameter types, such as common water temperature, acidity (pH value), dissolved oxygen and other parameter types. And each basic parameter type corresponds to a fixed weight. This is because the importance of different basic parameters varies in the comprehensive assessment of water quality. Taking drinking water source monitoring as an example, dissolved oxygen is crucial for maintaining the survival of aquatic organisms and the self-purification capacity of water bodies, so its weight may be relatively high when assessing water quality; although water temperature also affects water quality, in some cases, its impact on the comprehensive assessment of water quality is relatively small, and its weight is also lower.

[0038] Assume that the base parameter type is , respectively , ,..., , and the corresponding fixed weights are , ,..., , the calculation formula for the comprehensive impact value of basic parameters is: in, Indicates the comprehensive impact value of basic parameters and the serial number of basic parameter type. Indicates the The value of the basic parameter type, Indicates the Fixed weights corresponding to the basic parameter types.

[0039] The extended parameter type group also contains multiple extended parameter types, such as specific heavy metal content (such as lead and mercury) and organic pollutant indicators (such as chemical oxygen demand and biochemical oxygen demand). Unlike basic parameter types, each extended parameter type corresponds to a dynamic weight. This is because the importance of these extended parameters changes in different monitoring scenarios and time periods. In areas with frequent industrial activity, the weight of the heavy metal content parameter may be adjusted according to fluctuations in industrial production; in agricultural irrigation water monitoring, the weight of the organic pollutant indicator related to agricultural non-point source pollution may change with the seasons (such as the agricultural fertilization season).

[0040] Assume that the extended parameter type is , respectively , ,..., , and the corresponding dynamic weights are , ,..., , the calculation formula for the comprehensive impact value of the extended parameters is: in, Indicates the comprehensive impact value of the extended parameters, Indicates the serial number of the extended parameter type, Indicates the A value of the extended parameter type, Indicates the Dynamic weight corresponding to each extended parameter type.

[0041] During the actual collection process, the water quality parameter collection module will obtain data from the water quality database based on these rules. The module first extracts the structured monitoring data of the monitoring points from the water quality database. These data are stored in a specific format to facilitate subsequent extraction operations. Then, based on each basic parameter type in the basic parameter type group, the corresponding basic parameters are extracted from the structured monitoring data. For example, the values of basic parameters such as water temperature and pH are accurately extracted from the data. Next, based on each extended parameter type in the extended parameter type group, the corresponding extended parameters are extracted from the structured monitoring data. Finally, all the extracted basic parameters and extended parameters are summarized into a water quality parameter set for the monitoring point to ensure that the collected data is comprehensive and meets the monitoring requirements. Example 3

[0042] When the default pollution source association is a direct pollution source relationship, the pollution index calculation module determines whether the monitoring point is associated with a pollution source node in the water quality database. For example, if a chemical company is located near a river and its wastewater flows directly into the river, then the chemical company is a pollution source node in the water quality database. If a monitoring point is associated with such a pollution source node, such as a monitoring point located near a chemical company's sewage outlet, then the pollution index of that monitoring point is the sum of the pollution contribution values of all its associated pollution source nodes. Each pollution source node has a corresponding pollution contribution value, which is determined by factors such as the type and amount of pollutants discharged, and the degree of impact of the discharged pollutants on water quality. If a monitoring point is not associated with a pollution source node, such as a monitoring point located upstream of a river far from a pollution source, then the pollution index of that monitoring point is its own baseline pollution value, which is typically determined based on the natural background pollution conditions in the area and historical monitoring data.

[0043] When the preset pollution source association relationship is an indirect pollution source relationship, the calculation of the pollution index of the monitoring point is relatively complex. In this case, the pollution index of the monitoring point is the weighted sum of the pollution contribution values of all pollution source nodes obtained by the monitoring point through the upstream and downstream association paths. Taking a river flowing through multiple cities as an example, although the sewage discharge of upstream cities does not directly affect a certain monitoring point downstream, the pollutants will gradually spread and migrate through the flow of the river. The pollution index calculation module will determine the upstream and downstream association paths of the monitoring point and find all the pollution source nodes on the path. For each pollution source node, the weight is determined based on factors such as its distance from the monitoring point and the attenuation of pollutants in the water body. Then, the weighted sum of the pollution contribution values of these pollution source nodes is calculated to obtain the pollution index of the monitoring point. This can more accurately reflect the impact of indirect pollution sources on the water quality of the monitoring point and provide more targeted data support for water pollution control. Example 4

[0044] This example describes the operation of a pollution source tracking module connected to a central control unit. The module first sets the target pollution type, such as heavy metal pollution or organic pollution. It then uses a pre-defined spatiotemporal correlation analysis method to determine the spatiotemporal correlation between the monitoring point and the target pollution type. This spatiotemporal correlation serves as the monitoring dimension parameter for the monitoring point.

[0045] To obtain spatiotemporal correlation, the pollution source tracing module retrieves a set of historical pollution diffusion paths for each monitoring point from the pollution diffusion model library. This library contains a variety of models based on different geographical environments, meteorological conditions, and pollutant characteristics. These models can simulate pollutant diffusion paths under different circumstances. For example, in a river, models based on factors such as water flow velocity and channel shape can calculate the diffusion paths of pollutants over different time periods. Simultaneously, the pollution diffusion model library retrieves a set of standard diffusion paths for the target pollution type. These are ideal diffusion paths for that pollution type, determined based on extensive experimental data and theoretical analysis. The spatiotemporal overlap between the set of historical pollution diffusion paths and the set of standard diffusion paths is used as the first correlation between the monitoring point and the target pollution type. If a monitoring point's historical pollution diffusion paths overlap significantly with the standard diffusion paths of the target pollution type in both time and space, it indicates a high correlation between the monitoring point and the target pollution type.

[0046] Dynamically match the pollution concentration change curve at a monitoring point over a preset time period with the standard concentration change curve for the target pollution type. For example, the heavy metal concentration change at a monitoring point can be monitored over a period of time and compared with the standard concentration change curve for heavy metal pollution. The second correlation between the monitoring point and the target pollution type is calculated by calculating the waveform similarity between the two. If the shapes of the two curves are similar, it indicates that the monitoring point is likely to be affected by the target pollution type.

[0047] The first correlation, the second correlation, or the weighted average of the first and second correlations is used as the spatiotemporal correlation between the monitoring point and the target pollution type. The specific method chosen depends on the actual monitoring needs and the importance attached to the two correlations. This approach can more accurately track pollution sources and provide powerful clues for pollution control. Example 5

[0048] After receiving all the monitoring dimension parameters from the monitoring points, the central control unit conducts a comprehensive analysis of these parameters to generate water quality assessment parameters. One approach is to perform linear superposition. Assume that the monitoring dimension parameters include a water quality parameter set, a pollution index, and anomaly detection indicators. The central control unit assigns a weight to each parameter based on its importance. For example, certain key parameters in the water quality parameter set (such as dissolved oxygen and pH) have higher weights, and the pollution index and anomaly detection indicators are also weighted according to their importance to water quality assessment. These parameters are then multiplied by their corresponding weights and added together to obtain a composite value, which serves as the preliminary water quality assessment parameter. This linear superposition method quickly generates a value that reflects the overall water quality status.

[0049] Another approach is nonlinear fusion. Because water quality monitoring parameters can have complex interrelationships, simple linear superposition may not accurately reflect the true water quality. Therefore, the central control unit employs nonlinear fusion, utilizing machine learning algorithms or other complex mathematical models to process these monitoring dimension parameters. For example, a neural network model can be used, taking all monitoring dimension parameters as input. Through multiple layers of neurons within the network, the model outputs a more accurate water quality assessment parameter. This approach better captures the complex relationships between parameters and improves the accuracy of water quality assessment.

[0050] The system also includes a storage unit connected to the central control unit. This storage unit is used to store various data from monitoring points, including water quality parameter sets. This data is collected and updated in real time, recording various water quality parameters at each monitoring point at different times, facilitating subsequent querying and analysis of water quality trends. The storage unit also stores the pollution index for each monitoring point. By recording the pollution index over a long period of time, it is possible to observe changes in the degree of pollution at each monitoring point and determine the effectiveness of pollution control measures. Anomaly detection indicators are also stored, facilitating the review and summary of historical anomalies, providing data support for optimizing anomaly detection algorithms. Furthermore, the storage unit stores water quality assessment parameters for each monitoring point. These parameters provide a comprehensive evaluation of water quality conditions and provide an important basis for water resource management and protection. By storing this data, the system can better manage and analyze data, providing strong support for water quality monitoring. Example 6

[0051] The alarm module is connected to the central control unit. Its main function is to generate graded alarm signals based on the comparison results of water quality assessment parameters with preset safety thresholds, and send these signals to designated terminal devices through the communication network.

[0052] Preset safety thresholds are set based on relevant water quality standards and actual monitoring needs. For example, for drinking water source monitoring, safety threshold ranges for various water quality parameters are set according to national drinking water hygiene standards. For dissolved oxygen, minimum limits are set; for heavy metal content, maximum allowable concentrations are set.

[0053] The alarm module receives water quality assessment parameters generated by the central control unit in real time. When water quality assessment parameters exceed preset safety thresholds, the alarm module generates graded alarm signals based on the degree of excess. For example, when water quality parameters slightly exceed the safety threshold, a level 1 alarm is generated, indicating a possible risk of mild contamination. When water quality parameters significantly exceed the safety threshold, a higher-level alarm signal, such as a level 3 alarm, is generated, indicating a severe contamination risk.

[0054] After generating an alarm signal, the alarm module transmits it to a designated terminal device via a communication network. This communication network can be implemented in a variety of ways, including wireless communication technologies (such as 4G and 5G networks) or wired communication networks (such as fiber optic networks). Designated terminal devices include mobile phones and computers used by relevant management personnel. This allows relevant personnel to receive the alarm information promptly and take appropriate measures, such as initiating emergency response plans and investigating and treating contaminated areas, thereby effectively ensuring the safety and rational use of water resources.

[0055] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0056] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A water quality multi-parameter real-time monitoring system, characterized in that: include: A monitoring point configuration module is used to set monitoring points within the target monitoring area and generate corresponding parameter collection rules based on the monitoring points; A water quality parameter acquisition module is used to obtain the water quality parameter set of the monitoring point from the water quality database in real time according to the parameter acquisition rule, and use all parameters in the water quality parameter set as monitoring dimension parameters of the monitoring point; A pollution index calculation module is used to calculate the pollution index of the monitoring point through a multi-dimensional fusion algorithm based on the pollution source association relationship preset in the water quality database, and use the pollution index of the monitoring point as the monitoring dimension parameter of the monitoring point; An anomaly detection module, configured to obtain an anomaly detection index of the monitoring point through a preset dynamic threshold analysis method, and use the anomaly detection index of the monitoring point as a monitoring dimension parameter of the monitoring point; A central control unit is configured to send the monitoring points to the pollution index calculation module and the anomaly detection module, send the parameter collection rules to the water quality parameter collection module, and perform a comprehensive analysis of all the monitoring dimension parameters of the monitoring points to generate water quality assessment parameters for the monitoring points; Wherein, the water quality database includes a preset pollution source database and / or a real-time monitoring database.

2. The real-time monitoring system according to claim 1, characterized in that: The abnormality detection index of the monitoring point is obtained by using a preset dynamic threshold analysis method, including: The monitoring point and a preset reference point within the watershed to which the monitoring point belongs are used as dynamic analysis units, all historical water quality data are obtained based on the watershed to which the monitoring point belongs, and a parameter fluctuation pattern of the dynamic analysis unit in a historical period is determined; On the basis of the parameter fluctuation pattern, and based on the fluctuation amplitude of each of the historical water quality data in the corresponding dynamic analysis unit, calculating the initial abnormality index of each of the dynamic analysis units and the initial deviation index of each of the historical water quality data; Based on the initial abnormality index of each dynamic analysis unit and the initial deviation index of each historical water quality data, a bidirectional iterative model is used to achieve synchronous optimization of the abnormality detection index of each dynamic analysis unit and the deviation index of each historical water quality data, so as to obtain the final abnormality index of each dynamic analysis unit, and the final abnormality index of the dynamic analysis unit corresponding to the monitoring point is used as the abnormality detection index of the monitoring point; Set the comparative dynamic analysis unit to be any one of all the dynamic analysis units, and the comparative historical water quality data to be any one of all the historical water quality data. At the same time, based on the parameter fluctuation pattern, take the fluctuation amount of the comparative dynamic analysis unit in the comparative historical water quality data as a single fluctuation amount, take the total fluctuation amount of the comparative dynamic analysis unit in all the historical water quality data as a single total fluctuation amount, take the fluctuation amount of all the dynamic analysis units in the comparative historical water quality data as the overall fluctuation amount, and take the total fluctuation amount of all the dynamic analysis units in all the historical water quality data as the overall total fluctuation amount. At this time, judge whether the ratio of the single fluctuation amount to the single total fluctuation amount is greater than the ratio of the overall fluctuation amount to the overall total fluctuation amount. If so, it is determined that the comparative dynamic analysis unit has significant anomalies in the comparative historical water quality data. Otherwise, it is determined that the comparative dynamic analysis unit does not have significant anomalies in the comparative historical water quality data.

3. The real-time monitoring system according to claim 1, characterized in that: The parameter collection rules include a basic parameter type group and an extended parameter type group; the basic parameter type group contains multiple basic parameter types and a fixed weight corresponding to each basic parameter type; the extended parameter type group contains multiple extended parameter types and a dynamic weight corresponding to each extended parameter type.

4. The real-time monitoring system according to claim 2, characterized in that: The step of acquiring the water quality parameter set of the monitoring point in real time from the water quality database according to the parameter acquisition rule comprises: The water quality parameter acquisition module extracts the structured monitoring data of the monitoring point from the water quality database, extracts the corresponding basic parameters from the structured monitoring data based on each basic parameter type in the basic parameter type group, and extracts the corresponding extended parameters from the structured monitoring data based on each extended parameter type in the extended parameter type group, and summarizes all the basic parameters and all the extended parameters into a water quality parameter set for the monitoring point.

5. The real-time monitoring system according to claim 1, characterized in that: When the preset pollution source association relationship is a direct pollution source relationship, determine whether the monitoring point is associated with a pollution source node in the water quality database. If so, the pollution index of the monitoring point is the accumulation of pollution contribution values of all pollution source nodes associated with the monitoring point. Otherwise, the pollution index of the monitoring point is the basic pollution value of the monitoring point itself. When the preset pollution source association relationship is an indirect pollution source relationship, the pollution index of the monitoring point is the weighted sum of the pollution contribution values of all pollution source nodes obtained by the monitoring point through the upstream and downstream association paths.

6. The real-time monitoring system according to claim 1, characterized in that: Also included is a pollution source tracking module connected to the central control unit; The pollution source tracking module is used to set the target pollution type, obtain the spatiotemporal correlation between the monitoring point and the target pollution type through a preset spatiotemporal correlation analysis method, and use the spatiotemporal correlation as the monitoring dimension parameter of the monitoring point.

7. The real-time monitoring system according to claim 6, characterized in that: The pollution source tracking module obtains the spatiotemporal correlation between the monitoring point and the target pollution type by a preset spatiotemporal correlation analysis method, including: Obtaining a historical pollution diffusion path set of the monitoring point from a pollution diffusion model library, obtaining a standard diffusion path set of the target pollution type from the pollution diffusion model library, and using the spatiotemporal overlap between the historical pollution diffusion path set and the standard diffusion path set as a first correlation degree between the monitoring point and the target pollution type; Dynamically matching the pollution concentration change curve of the monitoring point within a preset time period with the standard concentration change curve of the target pollution type, and obtaining the waveform similarity between the two as a second correlation degree between the monitoring point and the target pollution type; The first correlation degree, the second correlation degree, or a weighted average of the first correlation degree and the second correlation degree is used as the spatiotemporal correlation degree between the monitoring point and the target pollution type.

8. The real-time monitoring system according to claim 1, characterized in that: The central control unit performs linear superposition or nonlinear fusion on all the monitoring dimension parameters of the monitoring points to generate the water quality assessment parameters.

9. The real-time monitoring system according to claim 1, characterized in that: It also includes a storage unit connected to the central control unit, which is used to store the water quality parameter set of the monitoring point, the pollution index of the monitoring point, the abnormality detection index of the monitoring point and the water quality assessment parameter of the monitoring point.

10. The real-time monitoring system according to claim 1, characterized in that: It also includes an alarm module connected to the central control unit, which is used to generate a graded alarm signal based on the comparison result of the water quality assessment parameter and the preset safety threshold, and send the graded alarm signal to the designated terminal device through the communication network.

Images