Intelligent water quality detection method and system for water plant

Abstract

The invention provides an intelligent water quality detection method and system for a water plant, and relates to the technical field of water quality detection.The method comprises the steps that detection point position analysis is conducted on a main water supply trunk line, and water supply detection point positions are determined; performing detection control optimization on the water supply detection point according to the multi-parameter discrimination scheme to generate a parameter group; performing anomaly detection on the water supply detection point according to the parameter group to obtain a detection result; performing anomaly prediction on the detection result through a water quality anomaly tracking channel, and generating an anomaly prediction point location; and analyzing linkage abnormity of the abnormal prediction point, determining a pollution propagation network, and completing water quality detection through abnormity response. According to the method and the device, the technical problem of poor prediction precision of the pollutant diffusion trend in the prior art can be solved, and the technical effect of improving the prediction precision of the pollution propagation path is achieved.

Description

Technical Field

[0001] The present application relates to the field of water quality detection technology, and in particular to an intelligent water quality detection method and system for a water plant. Background Art

[0002] With the increasing complexity of urban water supply systems and the increasing demand for water quality safety from residents, the demand for intelligent water quality testing in water plants has significantly increased. The traditional method of relying on manual scheduled sampling and single-point sensor monitoring can no longer meet the needs of high-frequency response and precise management of large-scale, dynamically changing water quality.

[0003] Currently, existing water quality monitoring technologies typically rely on physical and chemical parameter sensors, rapid microbial detection modules, and centralized data acquisition platforms within SCADA systems to achieve real-time monitoring of key indicators such as turbidity, residual chlorine, pH, and conductivity. However, these technical approaches still have limitations in practical application. Most existing water quality monitoring systems lack intelligent data correlation and analysis capabilities, making it difficult to link and analyze multi-point detection data, predict pollutant transmission trends, and efficiently trace abnormalities.

[0004] In summary, the existing technology has technical problems such as the lack of dynamic detection point optimization and multi-parameter intelligent fusion judgment mechanism, which results in the identification of water quality anomalies being limited to local single-point over-limit alarms, further affecting the accurate prediction of pollutant diffusion trends and the rapid location of pollution sources. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent water quality detection method and system for a water plant, so as to solve the technical problem in the prior art that the identification of water quality anomalies is limited to local single-point over-limit alarms due to the lack of dynamic detection point optimization and multi-parameter intelligent fusion judgment mechanism, which further affects the accurate prediction of pollutant diffusion trends and the rapid location of pollution sources.

[0006] In view of the above problems, the present application provides an intelligent water quality detection method and system for a water plant.

[0007] In the first aspect, the present application provides an intelligent water quality detection method for a water plant, which is implemented through an intelligent water quality detection system for a water plant, including: analyzing the detection points of the main water supply trunk line to determine the water supply detection points; performing detection control optimization on the water supply detection points according to a multi-parameter discrimination scheme to generate a parameter group; performing anomaly detection on the water supply detection points according to the parameter group to obtain detection results; performing anomaly prediction on the detection results through a water quality anomaly tracking channel to generate anomaly prediction points; analyzing the linkage anomalies of the anomaly prediction points to determine the pollution transmission network, and completing water quality detection through anomaly response.

[0008] Preferably, the intelligent water quality detection method for a water plant also includes: introducing a multi-parameter discrimination scheme to construct a multi-parameter scheme set; clustering the parameters of the multi-parameter scheme set according to scene attention to obtain parameter aggregation; performing parameter optimization on the parameter aggregation according to the parameter detection effect to obtain parameter optimization aggregation; traversing and combining the parameter optimization aggregation to obtain a parameter group.

[0009] Preferably, the intelligent water quality detection method for a water plant also includes: extracting a first parameter group according to the parameter group, and extracting a first parameter based on the first parameter group; performing abnormality detection on the water supply detection point according to the first parameter to obtain a first detection result; if the first detection result is greater than or equal to a predetermined first type of abnormality, adding the water supply detection point to the abnormal detection point; continuing to perform abnormality confirmation on the abnormal detection point according to the first parameter group to obtain a detection result.

[0010] Preferably, the intelligent water quality detection method for a water plant also includes: extracting a second parameter based on the first parameter group; confirming the abnormality of the abnormal detection point based on the second parameter to obtain a second detection result; if the second detection result is greater than or equal to a predetermined second type of abnormality, retaining the abnormal detection point to obtain an abnormal detection point retention result; obtaining the first abnormality ratio of the number of parameters corresponding to the abnormal detection point retention result in the first parameter group; if the first abnormality ratio is greater than the preset abnormality ratio, adding the abnormal detection point to the abnormal detection result, and combining it with the normal detection result to obtain the detection result.

[0011] Preferably, the intelligent water quality detection method for a water plant also includes: using the water flow sample set and the detection result sample set of the main water supply trunk line as input data, and the abnormal detection point sample set as output data, supervising the water quality anomaly tracking channel to obtain a water quality anomaly tracking learning coefficient; if the water quality anomaly tracking learning coefficient meets the water quality anomaly tracking learning constraint, generating the water quality anomaly tracking channel; based on the main water supply trunk line and the detection results, performing anomaly prediction according to the water quality anomaly tracking channel to generate the abnormal prediction point.

[0012] Preferably, the intelligent water quality detection method for a water plant also includes: extracting a first abnormal detection point and a second abnormal detection point based on the abnormal detection point; judging whether the first abnormal detection point and the second abnormal detection point exist simultaneously in the abnormal prediction point to obtain a first linkage point; traversing and judging the abnormal detection point based on the first linkage point to obtain a linkage point; and determining a pollution transmission network based on the linkage point.

[0013] Preferably, the intelligent water quality detection method of a water plant also includes: locating the abnormal source of the pollution propagation network according to the main water supply trunk line to obtain the abnormal source point; responding to abnormalities based on the pollution propagation network, continuously monitoring the abnormal source point, and completing water quality detection.

[0014] Preferably, the intelligent water quality detection method for a water plant also includes: performing grid processing according to the main water supply trunk line to obtain a water supply grid; performing abnormality prediction on the water supply grid according to the abnormal detection point sample set of the main water supply trunk line to obtain an abnormal prediction grid; performing detection density division according to the abnormal prediction grid to obtain multiple detection density grids, and setting detection points based on the multiple detection density grids to generate the water supply detection points.

[0015] Preferably, the intelligent water quality detection method for a water plant also includes: the multi-parameter discrimination scheme includes a physical and chemical parameter discrimination scheme, an organic parameter discrimination scheme, an inorganic ion parameter discrimination scheme, a particle and turbidity parameter discrimination scheme, a microbial indicator parameter discrimination scheme, and an auxiliary indicator parameter discrimination scheme.

[0016] In the second aspect, the present application also provides an intelligent water quality detection system for a water plant, which is used to execute an intelligent water quality detection method for a water plant as described in the first aspect, including: a water supply detection point determination module, which is used to analyze the detection points of the main water supply trunk line and determine the water supply detection points; a parameter group generation module, which is used to perform detection control optimization on the water supply detection points according to a multi-parameter discrimination scheme and generate a parameter group; a detection result acquisition module, which is used to perform anomaly detection on the water supply detection points according to the parameter group and obtain the detection results; an abnormal prediction point generation module, which is used to perform abnormality prediction on the detection results through a water quality anomaly tracking channel and generate an abnormal prediction point; a water quality detection module, which is used to analyze the linkage anomalies of the abnormal prediction points, determine the pollution transmission network, and complete water quality detection through abnormal response.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by realizing the technical goals of intelligent layout of detection points based on grid analysis of water supply trunk lines, parameter group optimization and anomaly tracking fusion analysis, the technical effects of improving the accuracy of water quality anomaly identification and realizing the linkage between pollution propagation path prediction and source point positioning response are achieved.

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0020] Figure 1 The present invention is a flowchart of an intelligent water quality detection method for a water plant.

[0021] Figure 2 This application is a structural diagram of an intelligent water quality detection system for a water plant.

[0022] Explanation of the accompanying symbols: water supply detection point determination module 1, parameter group generation module 2, detection result acquisition module 3, abnormal prediction point generation module 4, water quality detection module 5. DETAILED DESCRIPTION

[0023] This application provides an intelligent water quality detection method and system for water plants, resolving the existing technical issues of limiting the identification of water quality anomalies to localized single-point over-limit alarms due to the lack of dynamic detection point optimization and multi-parameter intelligent fusion judgment mechanisms, further hindering the accurate prediction of pollutant diffusion trends and the rapid location of pollution sources. This application achieves the technical goals of intelligently deploying detection points based on grid analysis of water supply trunk lines, optimizing parameter groups, and integrating anomaly tracking and analysis, achieving the technical effects of improving the accuracy of water quality anomaly identification and realizing the linkage between pollution propagation path prediction and source location response.

[0024] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0025] For example, see the attached Figure 1 This application provides an intelligent water quality detection method for a water plant, which is applied to an intelligent water quality detection system for a water plant, and specifically includes the following steps: S1: Analyze the detection points of the main water supply line and determine the water supply detection points.

[0026] Furthermore, the present application also includes: performing gridding processing on the main water supply trunk line to obtain a water supply grid; performing abnormality prediction on the water supply grid based on the abnormal detection point sample set of the main water supply trunk line to obtain an abnormal prediction grid; performing detection density division based on the abnormal prediction grid to obtain multiple detection density grids, and setting detection points based on the multiple detection density grids to generate the water supply detection points.

[0027] Specifically, analyzing the inspection points on the main water supply trunk line and determining the water supply inspection points means zoning the entire water supply pipeline based on the spatial structure and water flow characteristics of the main water supply pipeline using mathematical or spatial modeling methods to form multiple water supply grids with independent geographical attributes and hydraulic characteristics. The main water supply trunk line refers to the core water supply channel connecting the water plant and the major branch pipelines, which undertakes the main transportation task of the entire water supply system. The water supply grid is a multiple continuous or non-continuous unit area divided by the main water supply trunk line according to spatial intervals or water pressure zones. Each water supply grid is a water supply unit to be analyzed and is used for subsequent abnormality analysis and detection point layout.

[0028] Next, anomaly predictions are performed on the water supply grid based on a sample set of historical anomaly detection points along the main water supply line to identify potential risk areas. The sample set of anomaly detection points refers to monitoring points where events such as water quality exceeding standards, abnormal residual chlorine levels, and sudden turbidity changes have occurred. Using time series data from these historical anomaly detection points, a prediction system can be trained to assess the probability of similar anomalies occurring in different water supply grids in the future.

[0029] Then, based on the anomaly prediction grid, we divide the detection density into three types: high-density, medium-density, and low-density detection zones. High-density grids correspond to areas with higher predicted risk and will be deployed with more monitoring points. Low-density grids correspond to areas with lower risk and will only have a small number of detection points for basic monitoring.

[0030] Finally, we set up detection points based on multiple detection density grids to generate water supply detection points. This involves deploying specific sensors or monitoring devices to specific locations in the water supply network according to the density division scheme. Once completed, we obtain a well-structured and fully functional set of water supply detection points, providing basic data support for subsequent water quality testing, anomaly identification, and source tracing analysis.

[0031] S2: Optimizing detection control of the water supply detection points according to a multi-parameter discrimination scheme to generate a parameter group.

[0032] Furthermore, the present application also includes: introducing a multi-parameter discrimination scheme to construct a multi-parameter scheme set; clustering the parameters of the multi-parameter scheme set according to scene attention to obtain parameter aggregation; performing parameter optimization on the parameter aggregation according to the parameter detection effect to obtain parameter optimization aggregation; traversing and combining the parameter optimization aggregation to obtain a parameter group.

[0033] Furthermore, the present application also includes: the multi-parameter discrimination scheme includes a physical and chemical parameter discrimination scheme, an organic parameter discrimination scheme, an inorganic ion parameter discrimination scheme, a particle and turbidity parameter discrimination scheme, a microbial indicator parameter discrimination scheme, and an auxiliary indicator parameter discrimination scheme.

[0034] Specifically, optimizing detection and control of water supply detection points based on a multi-parameter discrimination scheme to generate parameter groups involves developing and screening plans using different categories of water quality detection parameters at identified water supply detection points to optimize monitoring efficiency and anomaly detection accuracy. Water supply detection points are sensor installation points located at key locations in the main water supply network, used to obtain real-time water quality data. Detection and control optimization involves finding the optimal combination of multiple detection parameters and detection strategies for a specific scenario. This involves achieving optimal allocation of monitoring resources and maximizing the effectiveness of detection results while ensuring water quality safety.

[0035] Introducing multi-parameter discrimination schemes to build a multi-parameter solution set. Designing multiple discrimination schemes based on water quality indicators, each solution includes a set of functionally related detection parameters that can provide a rapid response to specific types of contamination or anomalies. A multi-parameter solution set is a collection of different parameter combinations that covers the detection needs of various water quality change scenarios.

[0036] Next, the multi-parameter solution set is clustered based on the scenario attention, and the corresponding water quality monitoring focus is evaluated based on the environment and functional characteristics of different detection points, such as the raw water inlet, the water outlet, or the user end. Scenario attention is a measure of the sensitivity of a detection scenario to changes in a certain type of parameter. For example, at the water plant outlet, residual chlorine and coliform bacteria are of higher concern; while in the industrial area pipeline network, ammonia nitrogen and conductivity may be of greater concern. Parameter clustering is to classify highly correlated parameter combinations into the same category after considering the scenario attention, so as to facilitate subsequent overall optimization.

[0037] Subsequently, parameter optimization is performed on the parameter aggregation based on the parameter detection results. Actual detection performance is used to evaluate the comprehensive performance of each parameter set in terms of anomaly identification, water quality change response speed, and false alarm rate. Parameter detection performance includes indicators such as monitoring sensitivity, false alarm rate, and cost-effectiveness. By comparing parameter detection results, the most suitable parameter combinations for the target detection points can be screened, resulting in the parameter optimization aggregation, which is the high-quality combination selected based on the parameter aggregation.

[0038] Next, the parameter optimization aggregation is traversed and combined to obtain a parameter group. By combining and reorganizing multiple optimization results in different ways, the effects of parameter combinations with different quantities and arrangements are explored. The parameter group is the final parameter list used for actual testing.

[0039] The multi-parameter identification scheme includes physical and chemical parameters, organic matter parameters, inorganic ion parameters, particle and turbidity parameters, microbial indicator parameters, and auxiliary indicator parameters. Physical and chemical parameters such as temperature, pH, and conductivity primarily reflect the physical and acid-base state of the water; organic matter parameters such as COD, BOD, and TOC reflect the degree of organic contamination in the water; inorganic ions such as ammonia nitrogen, nitrate, and total nitrogen reveal abnormalities in the nitrogen cycle; particle and turbidity parameters such as turbidity and suspended solids reflect water clarity; microbial indicators such as coliforms and heterotrophic bacteria counts indicate biological contamination risks; and auxiliary indicators such as color and odor are used for the early detection of sensory abnormalities. Table 1 shows the data for the multi-parameter water quality identification scheme.

[0040] Table 1: Water quality multi-parameter identification scheme data table

[0041] S3: Perform abnormality detection on the water supply detection point according to the parameter group to obtain a detection result.

[0042] Furthermore, the present application also includes: extracting a first parameter group according to the parameter group, and extracting a first parameter based on the first parameter group; performing abnormality detection on the water supply detection point according to the first parameter to obtain a first detection result; if the first detection result is greater than or equal to a predetermined first type of abnormality, adding the water supply detection point to the abnormal detection point; continuing to perform abnormality confirmation on the abnormal detection point according to the first parameter group to obtain a detection result.

[0043] Furthermore, the present application also includes: extracting a second parameter based on the first parameter group; confirming the abnormality of the abnormal detection point based on the second parameter to obtain a second detection result; if the second detection result is greater than or equal to a predetermined second type of abnormality, retaining the abnormal detection point to obtain an abnormal detection point retention result; obtaining the first abnormality ratio of the number of parameters corresponding to the abnormal detection point retention result in the first parameter group; if the first abnormality ratio is greater than the preset abnormality ratio, adding the abnormal detection point to the abnormal detection result, and combining it with the normal detection result to obtain the detection result.

[0044] Specifically, the water supply detection points are detected for abnormalities according to the parameter group, water quality data is collected for each water supply detection point, and abnormalities are judged by identifying whether the water quality indicators exceed the normal range to obtain the detection results.

[0045] The parameters of multiple category combinations in the parameter group are divided into multiple parameter combinations, each parameter combination contains parameters of each category, and then a parameter combination for preliminary screening is arbitrarily selected from the multiple parameter combinations as the first parameter group. Any parameter is extracted from the first parameter group as the first parameter, such as turbidity, residual chlorine, pH, etc.

[0046] Subsequently, the water supply detection points are checked for anomalies based on the first parameter to obtain a first detection result. A preliminary anomaly determination is performed at each detection point using the first parameter to determine whether the indicator corresponding to the first parameter has crossed a certain threshold, experienced a sudden change, or exhibited an abnormal trend, thereby obtaining the first detection result. The first detection result is a preliminary screening of suspected anomalies, which is used for subsequent, more accurate verification. If the first detection result is greater than or equal to the predetermined abnormality level corresponding to the first parameter, the water supply detection point where the anomaly is detected by the first parameter is marked as an abnormal detection point.

[0047] Next, any parameter other than the first parameter is extracted from the first parameter group as the second parameter. Anomaly detection based on the second parameter is performed on the abnormal detection point to obtain a second detection result, ensuring the accuracy of the abnormality determination. If the second detection result is greater than or equal to the predetermined second-category abnormality degree corresponding to the second parameter, the abnormal detection point is retained, forming an abnormal detection point retention result.

[0048] The retained anomaly detection points are the set of points confirmed as abnormal after the second screening and requiring further response. Next, the first anomaly ratio is calculated based on the number of parameters corresponding to the retained anomaly detection points in the first parameter group. This ratio indicates that if the majority of the parameters corresponding to the anomaly detection point show an anomaly after being tested across multiple parameters, the anomaly detection point is added to the anomaly detection results. Finally, the complete detection results are obtained by combining the normal test results of all points with the abnormal test points.

[0049] S4: Anomaly prediction is performed on the detection result through the water quality anomaly tracking channel to generate anomaly prediction points.

[0050] Furthermore, the present application also includes: using the water flow sample set and the detection result sample set of the main water supply trunk line as input data, and the abnormal detection point sample set as output data, supervising the water quality anomaly tracking channel to obtain a water quality anomaly tracking learning coefficient; if the water quality anomaly tracking learning coefficient satisfies the water quality anomaly tracking learning constraint, generating the water quality anomaly tracking channel; based on the main water supply trunk line and the detection results, performing anomaly prediction according to the water quality anomaly tracking channel to generate the anomaly prediction point.

[0051] Specifically, the water quality anomaly tracking channel predicts anomalies at water supply detection points, generating predicted anomaly points. This is used to predict the potential spread of anomalies and infer areas of the pipe network where anomalies have not yet been detected but may soon occur. Anomaly predicted points are water supply points where model calculations predict the potential for anomalies in the future.

[0052] The input data is a water flow sample set from the main water supply line and a test result sample set. The main water supply line is the main channel in the water supply network that runs from the water plant to the branch pipelines in each region. The water flow sample set refers to hydraulic information such as flow velocity, flow direction, pressure, and water volume collected at different times and locations to simulate the flow path of water in the pipe network. The test result sample set refers to the historical data set marked as normal or abnormal in the previous test process.

[0053] Next, the water quality anomaly tracking channel is supervised and trained using the anomaly detection point sample set as output data. The anomaly detection point sample set refers to a collection of locations where anomaly events have been confirmed in history. It serves as the target label for training the water quality anomaly tracking channel and is used to guide the water quality anomaly tracking channel to identify potential propagation paths and risk areas. Subsequently, if the water quality anomaly tracking learning coefficient meets the water quality anomaly tracking learning constraints, it means that the water quality anomaly tracking channel has met the performance indicators required for training, and the water quality anomaly tracking channel can be formally formed. The water quality anomaly tracking learning coefficient is a set of weights or parameters formed by the water quality anomaly tracking channel during the training process to describe the mathematical relationship between water flow and anomaly propagation. The constraints may include indicators such as low error rate and goodness of fit. Only when they are met can the water quality anomaly tracking channel be considered to have reliable prediction capabilities.

[0054] Once the water quality anomaly tracking channel is established, it can be used to predict anomalies based on the main water supply line's structural information and test results. The channel analyzes normal points that may be affected by abnormal conditions upstream and calculates the probability of them becoming abnormal within a certain period of time, generating predicted abnormality points. While currently within the normal range, these areas are marked as potential risk areas for the future, allowing for early monitoring or early warning.

[0055] S5: Analyze the linkage anomalies of the abnormal prediction points, determine the pollution propagation network, and complete water quality detection through abnormal response.

[0056] Furthermore, the present application also includes: extracting a first abnormal detection point and a second abnormal detection point based on the abnormal detection point; judging whether the first abnormal detection point and the second abnormal detection point exist synchronously in the abnormal prediction point to obtain a first linkage point; traversing and judging the abnormal detection point based on the first linkage point to obtain a linkage point; and determining a pollution propagation network based on the linkage point.

[0057] Furthermore, the present application also includes: locating the abnormal source of the pollution propagation network based on the main water supply trunk line to obtain the abnormal source point; responding to abnormalities based on the pollution propagation network, continuously monitoring the abnormal source point, and completing water quality testing.

[0058] Specifically, the system analyzes the linkage anomalies of predicted anomaly points to determine the pollution transmission network. Water quality testing is completed through anomaly response. By comparing the relationship between predicted anomaly points and actual anomaly points, it identifies whether there are abnormal linkages between multiple points. This allows the pollution diffusion path to be constructed, and the pollution source is then identified and the response mechanism is activated. Linked anomalies refer to abnormal phenomena that are correlated in time or space at multiple points, which may be caused by the same pollution event. The pollution transmission network is a pollution diffusion map constructed based on the water flow path and the time series relationship of anomalies. It is used to analyze how pollution spreads from the source to multiple areas. Anomaly response is the action taken to prevent further deterioration after the pollution spread is identified. It includes operations such as alarm triggering, regional isolation, water quality re-inspection, and pollution source tracking.

[0059] Based on the anomaly detection points, the first and second anomaly detection points are randomly extracted, and the confirmed anomaly detection points are further grouped or sorted. Next, a determination is made as to whether the first and second anomaly detection points are simultaneously present in the anomaly prediction points, yielding the first linkage points. Anomaly prediction points are locations where anomalies may occur, as inferred by the model. If the actual anomaly detection results coincide with the predicted points, especially if two or more anomalies appear simultaneously in the predicted points, a correlated anomaly relationship is established, known as the first linkage point. The first linkage point is an important relay point for analyzing contamination paths and reflects the degree of match between prediction and reality.

[0060] Afterwards, the system traverses the abnormal detection points based on the first linkage point to further determine whether other points in the detection data have similar time or flow path connections to the first linkage point. This allows the system to identify more points that may be affected by the same pollution source, ultimately forming a more complete set of linkage points. Linkage points are a collection of multiple interconnected detection locations that are affected by the same pollution source and have experienced anomalies within a certain period of time.

[0061] Then, based on the linkage points, a pollution propagation network is determined. These linkage points are connected within the water supply network based on conditions such as flow direction, distance, and time windows to construct a possible pollution propagation path. The pollution propagation network includes pollution starting points, pathways, and impact points, reflecting how pollutants spread with water flow and at which nodes they are detected. The pollution propagation network is a core data structure in the water quality monitoring system, used to visualize pollution spread, predict the next direction of spread, and perform source tracing analysis.

[0062] Next, the source of anomalies in the pollution transmission network is located along the main water supply line. Using the hydraulic model and pollution paths of the main pipeline, the possible source of pollution is deduced. The main water supply line is the most important water transmission route in the water supply system. Source location is based on flow direction inversion, time backtracking, and pollutant concentration gradients. For example, if multiple downstream points have anomalies with similar time intervals, and their common upstream node has an anomaly at an earlier time, the upstream node is likely the anomaly source.

[0063] Finally, anomaly response based on the pollution propagation network involves identifying the pollution path and source and initiating corresponding emergency response mechanisms. This includes high-frequency water quality monitoring of the source, closing valves on contaminated branch lines, and issuing water supply warnings to relevant areas. Continuous monitoring involves deploying more sensors around the anomaly point or increasing the frequency of existing sensors to ensure that the contamination does not spread further. This completes a complete closed-loop water quality monitoring system, from anomaly detection and prediction to spread identification, source location, and response.

[0064] To sum up, the intelligent water quality detection method for water plants provided in this application has the following technical effects: by realizing the technical goals of intelligent layout of detection points based on grid analysis of water supply trunk lines, parameter group optimization and anomaly tracking fusion analysis, the accuracy of water quality anomaly identification is improved, and the technical effect of realizing the linkage between pollution propagation path prediction and source point positioning response is achieved.

[0065] Example 2: Based on the same inventive concept as the water plant intelligent water quality detection method in the above embodiment, this application also provides a water plant intelligent water quality detection system, please refer to the attached Figure 2 , including: a water supply detection point determination module 1, used to analyze the detection points of the main water supply trunk line and determine the water supply detection points; a parameter group generation module 2, used to perform detection control optimization on the water supply detection points according to a multi-parameter discrimination scheme and generate a parameter group; a detection result acquisition module 3, used to perform abnormality detection on the water supply detection points according to the parameter group and obtain detection results; an abnormality prediction point generation module 4, used to perform abnormality prediction on the detection results through a water quality abnormality tracking channel and generate an abnormality prediction point; a water quality detection module 5, used to analyze the linkage abnormalities of the abnormality prediction points, determine the pollution transmission network, and complete water quality detection through abnormal response.

[0066] Furthermore, the intelligent water quality detection system for a water plant is also used to: introduce a multi-parameter discrimination scheme to construct a multi-parameter scheme set; cluster the parameters of the multi-parameter scheme set through scene attention to obtain parameter aggregation; optimize the parameter aggregation according to the parameter detection effect to obtain parameter optimization aggregation; traverse and combine the parameter optimization aggregation to obtain a parameter group.

[0067] Furthermore, the intelligent water quality detection system of a water plant is also used to: extract a first parameter group according to the parameter group, and extract a first parameter based on the first parameter group; perform abnormality detection on the water supply detection point according to the first parameter to obtain a first detection result; if the first detection result is greater than or equal to a predetermined first type of abnormality, add the water supply detection point to the abnormal detection point; continue to perform abnormality confirmation on the abnormal detection point according to the first parameter group to obtain a detection result.

[0068] Furthermore, the intelligent water quality detection system for a water plant is also used to: extract a second parameter based on the first parameter group; confirm the abnormality of the abnormal detection point based on the second parameter to obtain a second detection result; if the second detection result is greater than or equal to a predetermined second type of abnormality, retain the abnormal detection point to obtain an abnormal detection point retention result; obtain the first abnormality ratio of the number of parameters corresponding to the abnormal detection point retention result in the first parameter group; if the first abnormality ratio is greater than the preset abnormality ratio, add the abnormal detection point to the abnormal detection result, and combine it with the normal detection result to obtain the detection result.

[0069] Furthermore, the intelligent water quality detection system for a water plant is also used to: use the water flow sample set and the detection result sample set of the main water supply trunk line as input data, and the abnormal detection point sample set as output data, to perform supervised training on the water quality anomaly tracking channel to obtain a water quality anomaly tracking learning coefficient; if the water quality anomaly tracking learning coefficient satisfies the water quality anomaly tracking learning constraint, generate the water quality anomaly tracking channel; based on the main water supply trunk line and the detection results, perform anomaly prediction according to the water quality anomaly tracking channel to generate the abnormal prediction point.

[0070] Furthermore, the intelligent water quality detection system for a water plant is also used to: extract a first abnormal detection point and a second abnormal detection point based on the abnormal detection point; determine whether the first abnormal detection point and the second abnormal detection point exist simultaneously in the abnormal prediction point to obtain a first linkage point; traverse and determine the abnormal detection point based on the first linkage point to obtain a linkage point; and determine a pollution transmission network based on the linkage point.

[0071] Furthermore, the intelligent water quality detection system of a water plant is also used to: locate the abnormal source of the pollution propagation network according to the main water supply trunk line and obtain the abnormal source point; respond to abnormalities based on the pollution propagation network, continuously monitor the abnormal source point, and complete water quality detection.

[0072] Furthermore, the intelligent water quality detection system of a water plant is also used to: perform grid processing according to the main water supply trunk line to obtain a water supply grid; perform abnormality prediction on the water supply grid according to the abnormal detection point sample set of the main water supply trunk line to obtain an abnormal prediction grid; perform detection density division according to the abnormal prediction grid to obtain multiple detection density grids, and set detection points based on the multiple detection density grids to generate the water supply detection points.

[0073] Furthermore, the intelligent water quality detection system for a water plant is also used for: the multi-parameter discrimination scheme includes a physical and chemical parameter discrimination scheme, an organic parameter discrimination scheme, an inorganic ion parameter discrimination scheme, a particle and turbidity parameter discrimination scheme, a microbial indicator parameter discrimination scheme, and an auxiliary indicator parameter discrimination scheme.

[0074] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The intelligent water quality detection method for a water plant and the specific examples in the aforementioned embodiment 1 are also applicable to an intelligent water quality detection system for a water plant in this embodiment. Through the aforementioned detailed description of an intelligent water quality detection method for a water plant, those skilled in the art can clearly understand an intelligent water quality detection system for a water plant in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0075] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0076] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A water plant intelligent water quality detection method, characterized in that: include: Analyze the detection points of the main water supply line and determine the water supply detection points; Performing detection and control optimization on the water supply detection points according to a multi-parameter discrimination scheme to generate a parameter group; Performing abnormality detection on the water supply detection point according to the parameter group to obtain a detection result; Perform anomaly prediction on the detection results through a water quality anomaly tracking channel to generate anomaly prediction points; Analyze the linkage anomalies of the abnormal prediction points, determine the pollution propagation network, and complete water quality detection through abnormal response.

2. The intelligent water quality detection method for a water plant according to claim 1, characterized in that: The water supply detection points are optimized for detection and control according to a multi-parameter discrimination scheme to generate a parameter group, including: Introducing multi-parameter discrimination scheme to construct multi-parameter scheme set; Performing parameter clustering on the multi-parameter solution set according to scene attention to obtain parameter aggregation; Performing parameter optimization on the parameter aggregation according to the parameter detection effect to obtain a parameter optimization aggregation; The parameter optimization aggregation is traversed and combined to obtain a parameter group.

3. The intelligent water quality detection method for a water plant according to claim 1, characterized in that: Performing abnormality detection on the water supply detection point according to the parameter group to obtain a detection result includes: Extracting a first parameter group according to the parameter group, and extracting a first parameter based on the first parameter group; Performing an abnormality detection on the water supply detection point according to the first parameter to obtain a first detection result; If the first detection result is greater than or equal to a predetermined first type of abnormality, the water supply detection point is added to the abnormal detection points; Continue to perform abnormal confirmation on the abnormal detection point according to the first parameter group to obtain a detection result.

4. The intelligent water quality detection method for a water plant according to claim 3, characterized in that: Continuing to perform abnormality confirmation on the abnormal detection point according to the first parameter group to obtain a detection result, including: extracting a second parameter according to the first parameter group; Performing abnormality confirmation on the abnormal detection point according to the second parameter to obtain a second detection result; If the second detection result is greater than or equal to the predetermined second type abnormality degree, retain the abnormal detection point to obtain an abnormal detection point retention result; Obtain the first abnormal proportion of the number of parameters corresponding to the retention result of the abnormal detection point in the first parameter group. If the first abnormal proportion is greater than the preset abnormal proportion, add the abnormal detection point to the abnormal detection result, and combine it with the normal detection result to obtain the detection result.

5. The intelligent water quality detection method for a water plant according to claim 1, characterized in that: The water quality anomaly tracking channel is used to predict anomalies in the test results and generate anomaly prediction points, including: Using the water flow sample set and the detection result sample set of the main water supply line as input data and the anomaly detection point sample set as output data, the water quality anomaly tracking channel is supervised trained to obtain the water quality anomaly tracking learning coefficient; If the water quality anomaly tracking learning coefficient satisfies the water quality anomaly tracking learning constraint, generating the water quality anomaly tracking channel; Based on the main water supply line and the detection result, anomaly prediction is performed according to the water quality anomaly tracking channel to generate the anomaly prediction point.

6. The intelligent water quality detection method for a water plant according to claim 1, characterized in that: Analyze the linkage anomalies of the abnormal prediction points and determine the pollution transmission network, including: Extracting a first abnormality detection point and a second abnormality detection point according to the abnormality detection point; Determining whether the first abnormality detection point and the second abnormality detection point exist simultaneously in the abnormality prediction point to obtain a first linkage point; Traversing and judging the abnormal detection points according to the first linkage points to obtain linkage points; A pollution transmission network is determined based on the linkage points.

7. The intelligent water quality detection method for a water plant according to claim 1, characterized in that: Complete water quality testing through abnormal response, including: Positioning the abnormal source of the pollution propagation network according to the main water supply line to obtain the abnormal source point; An abnormal response is performed based on the pollution propagation network, the abnormal source point is continuously monitored, and water quality detection is completed.

8. The intelligent water quality detection method for a water plant according to claim 1, characterized in that: Analyze the detection points of the main water supply line and determine the water supply detection points, including: Performing grid processing on the main water supply line to obtain a water supply grid; Performing anomaly prediction on the water supply grid based on the abnormality detection point sample set of the main water supply trunk line to obtain an abnormality prediction grid; Detection density is divided according to the abnormal prediction grid to obtain multiple detection density grids, and detection points are set based on the multiple detection density grids to generate the water supply detection points.

9. The intelligent water quality detection method for a water plant according to claim 1, characterized in that: The multi-parameter discrimination scheme includes a physical and chemical parameter discrimination scheme, an organic parameter discrimination scheme, an inorganic ion parameter discrimination scheme, a particle and turbidity parameter discrimination scheme, a microbial indicator parameter discrimination scheme, and an auxiliary indicator parameter discrimination scheme.

10. An intelligent water quality detection system for a water plant, characterized in that: The steps for implementing the intelligent water quality detection method for a water plant as described in any one of claims 1 to 9 include: The water supply detection point determination module is used to analyze the detection points of the main water supply trunk line and determine the water supply detection points; A parameter group generating module is used to perform detection control optimization on the water supply detection points according to a multi-parameter discrimination scheme to generate a parameter group; A detection result acquisition module, configured to perform abnormality detection on the water supply detection point according to the parameter group and obtain a detection result; An abnormality prediction point generation module is used to predict abnormalities of the detection results through a water quality abnormality tracking channel and generate abnormality prediction points; The water quality detection module is used to analyze the linkage anomalies of the abnormal prediction points, determine the pollution propagation network, and complete water quality detection through abnormal response.

Images