Intelligent control method and system of intelligent water supply and drainage network

Abstract

The invention relates to an intelligent control method and system for an intelligent water supply and drainage network, and the method comprises the following steps: carrying out the time sequence clustering analysis of a water flow dynamic parameter, and obtaining a water flow mode type; if the water flow mode category is abnormal, performing causal relationship analysis on the target water supply and drainage network based on the abnormal water flow mode category to obtain a fault network causal relationship graph of the target water supply and drainage network; inputting the fault network causal relationship graph into a preset association rule mining algorithm for rule strategy extraction to obtain water supply and drainage triggering rule strategy data; performing pre-control instruction generation on the target water supply and drainage network through the water supply and drainage triggering rule strategy data to obtain a pre-control instruction sequence; and the target water supply and drainage network is controlled based on the pre-control instruction sequence, so that the technical problem that the system is relatively weak in response capability and cannot timely and effectively deal with emergencies due to the fact that a traditional water supply and drainage system has many defects in design and management is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of drainage networks, and in particular to an intelligent control method and system for a smart water supply and drainage network. Background Art

[0002] With the continuous acceleration of urbanization, urban infrastructure construction faces unprecedented challenges. As a key component of urban operation, the water supply and drainage system is not only related to the quality of life of residents, but also the basis for ensuring urban safety and sustainable development. However, there are many deficiencies in the design and management of traditional water supply and drainage systems, such as serious information island phenomenon and lack of effective dynamic monitoring methods, which leads to the weak response ability of the system in the face of emergencies and the inability to deal with problems such as pipe rupture and water pollution in a timely and effective manner. In addition, due to the lack of intelligent management and maintenance methods, traditional water supply and drainage systems often find it difficult to achieve efficient use of resources, which increases operating costs.

[0003] In recent years, with the development of emerging technologies such as the Internet of Things, big data analysis, and artificial intelligence, new ideas have been provided to solve the above problems. In particular, the application of the Internet of Things technology makes it possible to monitor the operating status of the water supply and drainage system in real time. By conducting in-depth analysis of the large amount of data collected, the operating mode of the system can be accurately identified and potential problems can be discovered in a timely manner. However, how to effectively extract valuable information from massive amounts of data and formulate reasonable control strategies based on this is still a technical problem that needs to be solved urgently. Existing solutions mostly focus on single-dimensional data analysis and fail to fully consider the complex interactions between various factors within the water supply and drainage system, which limits its effectiveness in practical applications.

[0004] It is in this context that this study proposes an intelligent control method for smart water supply and drainage networks, aiming to improve the intelligent management level of water supply and drainage systems by introducing advanced data analysis techniques, such as time series clustering analysis and Bayesian network algorithms. This method can not only realize real-time monitoring and dynamic management of water supply and drainage networks, but also conduct in-depth analysis of detected abnormalities, quickly locate the root cause of the problem and generate corresponding pre-control instructions, thereby improving the response speed and processing efficiency of the system. In addition, further optimizing the control strategy through association rule mining algorithms will help achieve the rational allocation and utilization of resources and promote the green and intelligent transformation of water supply and drainage systems. Summary of the invention

[0005] The main purpose of the present invention is to provide an intelligent control method and system for a smart water supply and drainage network, which solves the technical problems that the traditional water supply and drainage system has many deficiencies in design and management, resulting in the system's weak response capability when facing emergencies and its inability to handle them in a timely and effective manner.

[0006] To achieve the above object, the present invention provides an intelligent control method for a smart water supply and drainage network, comprising the following steps: Through the preset Internet of Things, the target water supply and drainage network is monitored in real time to obtain the dynamic parameters of water flow; Performing time series cluster analysis on the water flow dynamic parameters to obtain water flow pattern categories; If the water flow pattern category is abnormal, a causal relationship analysis is performed on the target water supply and drainage network based on the abnormal water flow pattern category through a Bayesian network algorithm to obtain a fault network causal relationship diagram of the target water supply and drainage network; wherein there are multiple abnormal water flow pattern categories; Input the fault network causal relationship diagram into a preset association rule mining algorithm to extract rule strategies and obtain water supply and drainage trigger rule strategy data; Generate pre-control instructions for the target water supply and drainage network through the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence; The target water supply and drainage network is controlled based on the pre-control instruction sequence.

[0007] Furthermore, the Internet of Things is a distributed sensor network, and the target water supply and drainage network is monitored in real time through the preset Internet of Things to obtain water flow dynamic parameters, including: Real-time data collection of key nodes in the water supply and drainage network is carried out through a distributed sensor network to obtain original monitoring data; Performing multi-source data fusion processing on the original monitoring data to obtain fused monitoring data; Performing data denoising and feature extraction on the fused monitoring data to obtain a water flow feature vector; Detecting whether there are abnormal values ​​in the water flow characteristic vector, and if so, removing the abnormal values ​​in the water flow characteristic vector to obtain the water flow characteristic vector after removal; The eliminated water flow feature vector is predicted and supplemented to obtain water flow dynamic parameters; wherein the water flow dynamic parameters include water flow rate, water flow pressure and water quality parameters.

[0008] Furthermore, the water flow dynamic parameters are subjected to time series cluster analysis to obtain water flow pattern categories, including: Performing time series segmentation on the water flow dynamic parameters to obtain data segments in multiple time windows; The data segments are similarly measured by a preset dynamic time warping algorithm to obtain a distance matrix; wherein the distance matrix includes rows, columns and elements, the rows represent data segments in different time windows, the columns represent different data segments, and the elements represent similarity measurement values ​​between two data segments; Performing cluster analysis on the distance matrix using a preset hierarchical clustering algorithm to generate a cluster tree; wherein the cluster tree is used to display the hierarchical relationship between the data segments; According to a preset cluster quantity threshold, a horizontal line of a specific height is intercepted from the cluster tree to obtain a plurality of clusters; wherein each of the clusters represents a type of water flow pattern; Extract features from the data segments in each cluster to obtain representative feature vectors; The representative feature vector is mapped to a predefined water flow pattern category to obtain a water flow pattern category; wherein the water flow pattern category includes a normal mode, an abnormal mode and a peak mode.

[0009] Furthermore, the Bayesian network algorithm is used to perform a causal relationship analysis on the target water supply and drainage network based on the abnormal water flow pattern category to obtain a fault network causal relationship diagram of the target water supply and drainage network, including: Through the Bayesian network algorithm, the abnormal water flow pattern category is deeply analyzed to obtain the probability distribution diagram of abnormal water flow parameters; Based on the probability distribution diagram of abnormal water flow parameters, quantitatively evaluate the influence of each node in the target water supply and drainage network to obtain an influence matrix between nodes; wherein the influence matrix is ​​used to represent the strength of the causal relationship between each node; Using a preset identification algorithm, based on the inter-node influence matrix, path identification is performed on the target water supply and drainage network to obtain an influence path; wherein there are multiple influence paths; Performing time-series causal reasoning and analysis on each path in the impact path to obtain a path impact trend graph; wherein the path impact trend graph is the impact trend of each path over time; Identify the fault nodes and the fault factors corresponding to the fault nodes in the target water supply and drainage network based on the path influence trend graph and the abnormal water flow parameter probability distribution graph; The fault nodes and the fault factors corresponding to the fault factors are marked in the target water supply and drainage network to obtain a fault network causal relationship diagram of the target water supply and drainage network.

[0010] Furthermore, the fault network causal relationship diagram is input into a preset association rule mining algorithm to extract rule strategies to obtain water supply and drainage trigger rule strategy data, including: Identifying and classifying the fault nodes and the fault factors corresponding to the fault nodes in the fault network causal relationship diagram to obtain a fault factor classification diagram; Performing association rule mining based on the fault factor classification diagram to obtain preliminary association rules; Performing strength and confidence analysis on the preliminary association rules to obtain screened association rules; Performing graph mining analysis on the fault network causal relationship graph based on the filtered association rules to obtain a causal relationship association graph; Based on the causal relationship diagram, trigger rule strategy extraction is performed on the fault node to obtain water supply and drainage trigger rule strategy data.

[0011] Furthermore, the pre-control instruction generation for the target water supply and drainage network is performed by using the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence, including: Parsing the water supply and drainage trigger rule strategy data to obtain a strategy parsing result; Based on the strategy analysis results, the target water supply and drainage network is simulated in the operating state scenario to obtain water flow dynamic simulation data; Performing status evaluation on each node in the target water supply and drainage network based on the water flow dynamic simulation data to obtain a node status evaluation report; Based on the logic strategy matching algorithm, a control strategy matching analysis is performed on the node status assessment report to obtain a strategy matching result; Based on the strategy matching result, pre-control instructions are generated for the faulty nodes in the target water supply and drainage network to obtain a preliminary pre-control instruction sequence; Based on the preliminary pre-control instruction sequence, a response prediction analysis is performed on the target water supply and drainage network to obtain response prediction data; The pre-control instruction is optimized and adjusted based on the response prediction data to obtain a pre-control instruction sequence.

[0012] Furthermore, the control strategy matching analysis is performed on the node status assessment report based on the logic strategy matching algorithm to obtain a strategy matching result, including: By using a logic strategy matching algorithm, a logic state analysis is performed on the faulty nodes of the water supply and drainage network based on the node state evaluation report to obtain a logic state analysis report; Generate operation scenario logic rules for the target water supply and drainage network based on the logic status analysis report to obtain a logic rule set; Performing state logic reasoning analysis on the fault node using the logic rule set to obtain a logic reasoning result; The control strategy is logically matched based on the logical reasoning result to obtain a strategy matching result.

[0013] The present invention also provides an intelligent control system for a smart water supply and drainage network, comprising: The monitoring module is used to monitor the target water supply and drainage network in real time through the preset Internet of Things to obtain the dynamic parameters of water flow; A first analysis module is used to perform time series cluster analysis on the water flow dynamic parameters to obtain water flow pattern categories; The second analysis module is used for, if the water flow pattern category is abnormal, performing a causal relationship analysis on the target water supply and drainage network based on the abnormal water flow pattern category through a Bayesian network algorithm to obtain a fault network causal relationship diagram of the target water supply and drainage network; wherein there are multiple abnormal water flow pattern categories; An extraction module, used for inputting the fault network causal relationship diagram into a preset association rule mining algorithm to extract rule strategies and obtain water supply and drainage trigger rule strategy data; A generation module, used to generate pre-control instructions for the target water supply and drainage network according to the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence; A control module is used to control the target water supply and drainage network based on a pre-control instruction sequence.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0016] The intelligent control method of the smart water supply and drainage network provided by the present invention comprises the following steps: real-time monitoring of the target water supply and drainage network is performed through a preset Internet of Things to obtain water flow dynamic parameters; time series clustering analysis is performed on the water flow dynamic parameters to obtain water flow pattern categories; if the water flow pattern category is abnormal, a causal relationship analysis is performed on the target water supply and drainage network based on the abnormal water flow pattern category through a Bayesian network algorithm to obtain a fault network causal relationship diagram of the target water supply and drainage network; wherein there are multiple abnormal water flow pattern categories; the fault network causal relationship diagram is input into a preset association rule mining algorithm to extract rule strategies to obtain a water supply and drainage trigger rule strategy data. According to the water supply and drainage trigger rule strategy data; pre-control instructions are generated for the target water supply and drainage network to obtain a pre-control instruction sequence; based on the pre-control instruction sequence, the target water supply and drainage network is controlled, which solves the technical problems that many deficiencies in the design and management of traditional water supply and drainage systems lead to weak response capabilities of the system when facing emergencies and inability to deal with them in a timely and effective manner, and realizes that the pre-control instruction sequence generated according to the water supply and drainage trigger rule strategy data can be directly used to control the target water supply and drainage network, realizing closed-loop management from monitoring, analysis to control, greatly improving the automation level and intelligence level of the system, reducing the need for human intervention, and reducing the beneficial effects of operating errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the steps of an intelligent control method of a smart water supply and drainage network in one embodiment of the present invention; Figure 2 It is a structural block diagram of an intelligent control system of a smart water supply and drainage network in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, Figure 1 It is a schematic diagram of the steps of an intelligent control method for a smart water supply and drainage network in one embodiment of the present invention; In one embodiment of the present invention, a smart control method for a smart water supply and drainage network is provided, comprising the following steps: Step S1, real-time monitoring of the target water supply and drainage network is performed through a preset Internet of Things to obtain water flow dynamic parameters.

[0021] Specifically, the target water supply and drainage network is monitored in real time through the preset Internet of Things to obtain the dynamic parameters of water flow. This process is one of the key steps in the intelligent control method of the smart water supply and drainage network. Specifically, the Internet of Things technology plays a core role here. It consists of a series of sensors, data acquisition devices and communication modules deployed in the water supply and drainage network. These devices can continuously collect various dynamic parameters of water flow, such as flow rate, pressure, temperature, water quality and other information. For example, in a city's water supply and drainage system, smart sensors installed on water pipes can send data about water flow rate and water pressure to the central control system once a minute. These data reflect the real-time working status of the pipe network. In this way, the system can capture any subtle changes or abnormalities in time, such as a sudden high flow or low pressure in a section of the pipeline, which may be caused by a rupture or blockage of the pipeline. Then, these real-time collected data will be transmitted to the cloud or local server for storage and preliminary processing, so as to facilitate subsequent time series clustering analysis and other advanced analysis tasks. Throughout the process, the Internet of Things not only ensures the comprehensiveness and accuracy of data collection, but also lays a solid foundation for subsequent intelligent analysis and control.

[0022] Step S2, performing time series cluster analysis on the water flow dynamic parameters to obtain water flow pattern categories.

[0023] Specifically, the water flow dynamic parameters are subjected to time series clustering analysis to obtain the water flow pattern category, which is another important link in the intelligent control method of the smart water supply and drainage network. In this step, the system will use the water flow dynamic parameters previously collected through the Internet of Things technology, such as flow rate, pressure, temperature and other data, for in-depth analysis and processing. Time series clustering analysis is a technology that can identify similar patterns in time series data. It can help us find patterns from a large amount of historical data, and then classify water flow patterns in different time periods into several categories. For example, in a city's water supply and drainage system, through long-term data accumulation, we can observe that there are obvious differences in water flow characteristics in different time periods (such as morning and evening peak hours, late at night, etc.), and these differences may reflect changes in people's water use habits. Through time series clustering analysis, the system can automatically identify these different water use patterns and classify them, such as distinguishing the high-demand water use pattern during the morning peak hours from the low-demand pattern at night. This classification not only helps to understand the changes in user demand, but also provides an important reference for subsequent anomaly detection and fault diagnosis. When the system detects that the current water flow pattern deviates significantly from the known normal pattern, it may indicate an abnormal situation, such as a pipe leak or equipment failure, so that measures can be taken in advance for prevention and repair. In short, by performing time series clustering analysis on water flow dynamic parameters, the operating efficiency and safety of the water supply and drainage system can be effectively improved, ensuring the rational use of water resources.

[0024] Step S3: If the water flow pattern category is abnormal, a causal analysis is performed on the target water supply and drainage network based on the abnormal water flow pattern category through a Bayesian network algorithm to obtain a fault network causal relationship diagram of the target water supply and drainage network; wherein there are multiple abnormal water flow pattern categories.

[0025] Specifically, if the water flow pattern category is abnormal, the Bayesian network algorithm is used to perform a causal analysis on the target water supply and drainage network based on the abnormal water flow pattern category to obtain a fault network causal relationship diagram of the target water supply and drainage network. This process is a key step for fault diagnosis and prediction in the intelligent control method of the smart water supply and drainage network. After the system identifies that certain water flow pattern categories are abnormal through time series clustering analysis, it is necessary to further explore the causes of these abnormal patterns and their scope of influence. As a probabilistic graph model, the Bayesian network algorithm is very suitable for representing the dependencies between variables, especially in the presence of uncertainty. In this case, the algorithm can build a model that reflects the internal causal structure of the water supply and drainage network by learning the probabilistic relationship between known abnormal patterns and potential fault sources. For example, in the aforementioned urban water supply and drainage system application scenario, it is assumed that the system detects a sudden drop in water flow pressure in a certain area, accompanied by an abnormal increase in flow, which may be due to a rupture or leakage in the pipeline in the area. Through the Bayesian network algorithm, the system can comprehensively consider a variety of possible influencing factors, such as pipe material, service life, surrounding environmental conditions, etc., calculate the probability of each factor leading to the current abnormal mode, and finally generate a detailed fault network causal relationship diagram. This diagram not only shows the interaction between various factors, but also clarifies which factors are most likely to be the root cause of the abnormality, providing a clear direction for subsequent fault handling and preventive measures. In addition, since there may be multiple categories of abnormal water flow patterns, the Bayesian network algorithm can handle multi-variable situations at the same time, ensuring the comprehensiveness and accuracy of the analysis results. In this way, the intelligent control method of the smart water supply and drainage network can accurately identify and locate faults at the first time, thereby improving the stability and reliability of the system.

[0026] Step S4, inputting the fault network causal relationship diagram into a preset association rule mining algorithm to extract rule strategies and obtain water supply and drainage triggering rule strategy data.

[0027] Specifically, the fault network causal relationship diagram is input into the preset association rule mining algorithm for rule strategy extraction to obtain water supply and drainage trigger rule strategy data. This process is an important link in realizing fault handling and prevention in the intelligent control method of the smart water supply and drainage network. After the Bayesian network algorithm completes the causal relationship analysis of the abnormal water flow pattern category and generates a detailed fault network causal relationship diagram, the next step is to use the association rule mining algorithm to extract valuable rules and strategies from these causal relationships. The association rule mining algorithm can help the system identify the correlation between different fault factors and find out which combinations are more likely to cause specific types of faults. For example, in the aforementioned urban water supply and drainage system application scenario, it is assumed that the fault network causal relationship diagram shows that there is a close connection between the drop in water flow pressure in a certain area and the aging of the pipeline, the high groundwater level and the recent construction activities. By inputting this causal relationship diagram into the association rule mining algorithm, the system can automatically analyze and extract specific rules, such as "If the service life of the pipeline in a certain area exceeds 20 years, and the groundwater level rises by more than 2 meters in the last month, and construction activities are ongoing in the area, the risk of pipeline rupture in the area will increase significantly." Such rule strategy data can not only help operation and maintenance personnel quickly identify high-risk areas, but also guide them to take targeted preventive measures, such as increasing the monitoring frequency, replacing old pipes in advance, or coordinating with construction parties to avoid additional damage to pipes. Through this series of analysis and rule extraction, the intelligent control method of the smart water supply and drainage network can more proactively respond to potential failure risks, improve the reliability and safety of the system, and reduce maintenance costs and downtime. In this way, the overall management level of the urban water supply and drainage system will be significantly improved to better serve the living needs of citizens.

[0028] Step S5, generating pre-control instructions for the target water supply and drainage network using the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence.

[0029] Specifically, the target water supply and drainage network is pre-controlled by the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence, which is one of the key steps to achieve fault prevention and efficient management in the intelligent water supply and drainage system. After completing the in-depth analysis of the fault network causal relationship diagram and extracting the water supply and drainage trigger rule strategy data from it, the next task is to generate a pre-control instruction sequence for a specific water supply and drainage network environment based on these rule strategy data. This process involves converting the identified rule strategy into specific operation instructions, aiming to take measures in advance to prevent the occurrence of potential faults or mitigate their impact. For example, in the aforementioned application scenario, if the system has determined the rule strategy that "when the service life of the pipeline in a certain area exceeds 20 years, and the groundwater level has risen by more than 2 meters in the past month, and there is construction activity in the area, the risk of pipeline rupture in the area is significantly increased", then a series of pre-control instructions can be generated based on this rule. These instructions may include but are not limited to: increasing the pressure monitoring frequency of the pipeline in the area, notifying relevant departments to suspend or adjust the construction plan to reduce the impact on the underground pipeline, arranging technicians to conduct on-site inspections to assess the pipeline condition, etc. In this way, the system can take effective preventive measures before the actual failure occurs, thereby avoiding or reducing losses. In addition, the generation of pre-control instruction sequences also takes into account execution efficiency and resource optimization configuration to ensure that each instruction can be executed at the most appropriate time to achieve the best preventive effect. For example, when resources are limited, the system may give priority to comprehensive measures that can cover multiple potential fault points, or determine the order of actions based on the probability of failure and possible consequences. In this way, through the effective application of water supply and drainage trigger rule strategy data, not only the operational stability of the water supply and drainage system is improved, but also the system's response speed and service quality are greatly enhanced, ultimately realizing the intelligent management and maintenance of the smart water supply and drainage network.

[0030] Step S6: controlling the target water supply and drainage network based on the pre-control instruction sequence.

[0031] Specifically, controlling the target water supply and drainage network based on the pre-control instruction sequence refers to applying the pre-control instruction sequence generated in the previous step to the actual water supply and drainage system to achieve intelligent management and fault prevention of the network. For example, in the aforementioned urban water supply and drainage system application scenario, once the system generates a series of pre-control instructions including increasing the monitoring frequency, adjusting the construction plan, and dispatching technicians for on-site inspections, these instructions will be sent to the corresponding execution units, such as monitoring stations, construction management teams, and technical support departments. Through the specific execution of these instructions, the system can take measures in advance to reduce the risk of potential failures, such as timely discovering abnormal conditions by increasing the monitoring frequency, reducing physical damage to pipelines by adjusting the construction plan, and evaluating and repairing possible hidden dangers through professional inspections by technicians. In this way, it can not only effectively prevent the occurrence of faults, improve the operating efficiency and stability of the system, but also reduce service interruptions and economic losses caused by faults. The entire process forms a closed-loop management from monitoring, analysis, decision-making to execution, ensuring the safe and reliable operation of the smart water supply and drainage network.

[0032] In a specific embodiment, the Internet of Things is a distributed sensor network, and the target water supply and drainage network is monitored in real time through the preset Internet of Things to obtain water flow dynamic parameters, including: Real-time data collection of key nodes in the water supply and drainage network is carried out through a distributed sensor network to obtain original monitoring data; Performing multi-source data fusion processing on the original monitoring data to obtain fused monitoring data; Performing data denoising and feature extraction on the fused monitoring data to obtain a water flow feature vector; Detecting whether there are abnormal values ​​in the water flow characteristic vector, and if so, removing the abnormal values ​​in the water flow characteristic vector to obtain the water flow characteristic vector after removal; The eliminated water flow feature vector is predicted and supplemented to obtain water flow dynamic parameters; wherein the water flow dynamic parameters include water flow rate, water flow pressure and water quality parameters.

[0033] Specifically, the Internet of Things is a distributed sensor network. The process of real-time monitoring of the target water supply and drainage network through the preset Internet of Things to obtain the dynamic parameters of water flow is a complex and sophisticated data processing process. First, the key nodes of the water supply and drainage network are collected in real time through the distributed sensor network to obtain the original monitoring data. These sensors are widely distributed in various important locations of the water supply and drainage system, such as water sources, pumping stations, reservoirs, main pipeline nodes, etc., and can monitor various indicators of water flow around the clock, including but not limited to water flow, water flow pressure and water quality parameters. For example, in an urban water supply and drainage system, smart sensors are installed at the entrance of each community. These sensors automatically upload the latest water flow data to the central control system every few minutes, ensuring the real-time and comprehensiveness of the data. Next, the original monitoring data is subjected to multi-source data fusion processing to obtain the fused monitoring data. Due to the variety of sensors used in the water supply and drainage system, the data collected by different sensors may have problems such as inconsistent formats and asynchronous timestamps. Therefore, it is necessary to integrate data from different sources into a unified whole through data fusion technology. For example, when multiple sensors simultaneously report the pressure value of a certain pipeline node, the system will determine the true pressure value of the node through weighted average or other statistical methods, eliminate the possible errors of a single sensor, and improve the accuracy and reliability of the data. In addition, data fusion can also supplement the information blind spots that a single sensor cannot cover and enhance the perception ability of the system. Subsequently, the fused monitoring data is subjected to data denoising and feature extraction to obtain a water flow feature vector. This process aims to remove noise interference in the data and extract key information that can effectively characterize the characteristics of the water flow. For example, high-frequency noise is removed by a filter, low-frequency signals are retained, or characteristic components of different scales are separated by wavelet transform technology, so as to obtain a clearer and more stable water flow feature vector. These feature vectors usually contain important parameters such as the speed, direction, and pressure change rate of the water flow, which provide a basis for subsequent analysis and processing. Next, the water flow feature vector is detected to see if there are outliers. If so, the outliers in the water flow feature vector are removed to obtain the removed water flow feature vector. Outlier detection is an important link in ensuring data quality, because the presence of outliers may seriously affect the accuracy of subsequent analysis. For example, when the system detects that the water pressure at a certain pipeline node suddenly fluctuates significantly and exceeds the normal range, it will be marked as an outlier and removed from the data set. In order to more accurately identify outliers, various methods such as statistical methods (such as standard deviation method) and machine learning algorithms (such as isolation forest) can be used. Through this process, the system can effectively eliminate erroneous data caused by factors such as sensor failure and external interference, ensuring the accuracy of subsequent analysis. Finally, the water flow feature vector after elimination is predicted and supplemented to obtain the dynamic parameters of the water flow.In actual operation, due to various reasons, data at certain moments may be missing, which requires prediction and completion technology to restore the complete time series. For example, if a sensor fails to report data at a certain point in time due to a short power outage, the system can estimate the missing values ​​by analyzing the data trends of adjacent time points and using interpolation algorithms or time series prediction models to ensure the continuity and integrity of the data. The final water flow dynamic parameters include not only basic information such as water flow rate and water flow pressure, but may also include water quality parameters such as turbidity and pH value, providing detailed data support for a comprehensive understanding of the operating status of the water supply and drainage system. Through the above steps, the smart water supply and drainage network can realize all-round, multi-level real-time monitoring of the target water supply and drainage network, providing a solid data foundation for subsequent intelligent control and fault diagnosis. This process not only improves the automation and intelligence level of the system, but also provides strong technical support for ensuring the safe and stable operation of the urban water supply and drainage system.

[0034] In a specific embodiment, the water flow dynamic parameters are subjected to time series cluster analysis to obtain water flow pattern categories, including: Performing time series segmentation on the water flow dynamic parameters to obtain data segments in multiple time windows; The data segments are similarly measured by a preset dynamic time warping algorithm to obtain a distance matrix; wherein the distance matrix includes rows, columns and elements, the rows represent data segments in different time windows, the columns represent different data segments, and the elements represent similarity measurement values ​​between two data segments; Performing cluster analysis on the distance matrix using a preset hierarchical clustering algorithm to generate a cluster tree; wherein the cluster tree is used to display the hierarchical relationship between the data segments; According to a preset cluster quantity threshold, a horizontal line of a specific height is intercepted from the cluster tree to obtain a plurality of clusters; wherein each of the clusters represents a type of water flow pattern; Extract features from the data segments in each cluster to obtain representative feature vectors; The representative feature vector is mapped to a predefined water flow pattern category to obtain a water flow pattern category; wherein the water flow pattern category includes a normal mode, an abnormal mode and a peak mode.

[0035] Specifically, the water flow dynamic parameters are subjected to time series clustering analysis to obtain the water flow pattern category. This process is the core step for identifying and classifying water flow patterns in the intelligent control method of the smart water supply and drainage network. First, the water flow dynamic parameters are segmented in time series to obtain data segments in multiple time windows. This means that the continuously collected water flow dynamic parameters are divided into multiple independent data segments at certain intervals, and each data segment represents the water flow state over a period of time. For example, in an urban water supply and drainage system, the system can segment the daily water flow data according to a time window per hour, so that the data of one day is divided into 24 data segments, each of which contains the changes in water flow, pressure and water quality parameters within that hour. Then, the data segments are measured for similarity by a preset dynamic time warping algorithm to obtain a distance matrix. The dynamic time warping (DTW) algorithm is an effective method for measuring the similarity between two time series, and is particularly suitable for processing time series data of different lengths or with time offsets. In this step, the system compares each data segment with all other data segments, calculates the similarity measure between them, and organizes these values ​​into a distance matrix in the form of a matrix. The rows of the distance matrix represent data segments in different time windows, the columns also represent different data segments, and each element in the matrix represents the similarity measure between two data segments. For example, through the DTW algorithm, the system can calculate the similarity between the data segment from 7 to 8 in the morning and the data segment from 5 to 6 in the afternoon. If the water use patterns of these two time periods are similar, then their corresponding values ​​in the distance matrix will be smaller. Next, the distance matrix is ​​clustered and analyzed by a preset hierarchical clustering algorithm to generate a cluster tree. The hierarchical clustering algorithm is a method of recursively merging data objects into larger and larger clusters until all objects are merged into the same cluster. In this process, a cluster tree (Dendrogram) is gradually constructed to show the hierarchical relationship between data segments. The cluster tree can not only intuitively reflect which data segments are closer to each other, but also control the final number of clusters by adjusting the height of the tree. For example, the bottom of the clustering tree shows each data fragment as an independent cluster, and as the height increases, similar clusters gradually merge to eventually form a large cluster. By observing the clustering tree, you can clearly see which time periods have higher similarity in water flow patterns and which time periods have more unique patterns. According to a preset cluster number threshold, a horizontal line of a specific height is intercepted from the clustering tree to obtain multiple clusters. The cluster number threshold here can be pre-set according to actual needs. For example, it is set to 3, which means that all data fragments are expected to be divided into 3 categories. By finding the corresponding height position on the clustering tree and drawing a horizontal line, the tree can be divided into multiple parts, each of which is a cluster.Each cluster represents a type of water flow pattern, such as normal mode, abnormal mode and peak mode. For example, by intercepting a horizontal line at a specific height, the system may divide the water use pattern in a day into three categories: normal mode during daytime working hours, peak mode during morning and evening peak hours, and low peak mode at night. Feature extraction is performed on the data fragments in each cluster to obtain a representative feature vector. This step is to further refine the characteristics of each type of water flow pattern. By analyzing the data fragments in each cluster, the main features that can represent this type of pattern are extracted. For example, for the cluster of peak mode, the system can calculate the average flow rate, maximum pressure change rate and other features of this type of data fragment to form a representative feature vector. These feature vectors can not only concisely describe the core attributes of each type of pattern, but also provide a basis for subsequent pattern recognition and classification. Finally, the representative feature vector is mapped to the predefined water flow pattern category to obtain the water flow pattern category. The predefined water flow pattern categories usually include normal mode, abnormal mode and peak mode, etc. The system will classify each cluster into the most matching pattern category according to its representative feature vector. For example, if the representative feature vector of a cluster shows that the water flow rate in this mode is much higher than the average level and the pressure fluctuation is large, then this mode is likely to be a peak mode. In this way, the system can automatically identify the water flow patterns in different time periods, providing important reference information for subsequent anomaly detection, fault diagnosis and optimization control. In summary, by performing time series clustering analysis on the dynamic parameters of water flow, the smart water supply and drainage network can efficiently identify and classify different water flow patterns, which not only improves the intelligence level of the system, but also provides strong technical support for achieving refined management and fault prevention. This process can not only help operation and maintenance personnel to detect abnormal situations in a timely manner, but also provide a scientific basis for optimizing resource allocation and improving service quality.

[0036] In a specific embodiment, the Bayesian network algorithm is used to perform a causal relationship analysis on the target water supply and drainage network based on the abnormal water flow pattern category to obtain a fault network causal relationship diagram of the target water supply and drainage network, including: Through the Bayesian network algorithm, the abnormal water flow pattern category is deeply analyzed to obtain the probability distribution diagram of abnormal water flow parameters; Based on the probability distribution diagram of abnormal water flow parameters, quantitatively evaluate the influence of each node in the target water supply and drainage network to obtain an influence matrix between nodes; wherein the influence matrix is ​​used to represent the strength of the causal relationship between each node; Using a preset identification algorithm, based on the inter-node influence matrix, path identification is performed on the target water supply and drainage network to obtain an influence path; wherein there are multiple influence paths; Performing time-series causal reasoning and analysis on each path in the impact path to obtain a path impact trend graph; wherein the path impact trend graph is the impact trend of each path over time; Identify the fault nodes and the fault factors corresponding to the fault nodes in the target water supply and drainage network based on the path influence trend graph and the abnormal water flow parameter probability distribution graph; The fault nodes and the fault factors corresponding to the fault factors are marked in the target water supply and drainage network to obtain a fault network causal relationship diagram of the target water supply and drainage network.

[0037] Specifically, the Bayesian network algorithm is used to perform a causal analysis on the target water supply and drainage network based on the abnormal water flow pattern category to obtain a fault network causal relationship diagram of the target water supply and drainage network. This process is one of the core steps for fault diagnosis and prevention in the intelligent control method of the smart water supply and drainage network. First, the abnormal water flow pattern category is deeply analyzed by the Bayesian network algorithm to obtain a probability distribution diagram of abnormal water flow parameters. Bayesian network is a graphical model based on probability theory that can effectively represent the dependency relationship between variables and infer the state of unknown variables through known evidence. In this step, the system will use the Bayesian network algorithm to perform a deep analysis on the abnormal water flow pattern category previously identified by time series clustering analysis, and calculate the probability of each abnormal pattern. For example, in an urban water supply and drainage system, if the system detects a sudden drop in water flow pressure in a certain area, the Bayesian network algorithm will calculate the probability distribution of this abnormal pattern caused by different reasons such as pipe rupture, valve failure or water pump failure based on historical data and current monitoring data. These probability values ​​constitute the probability distribution diagram of abnormal water flow parameters, which provides a basis for subsequent causal relationship analysis. Based on the probability distribution diagram of abnormal water flow parameters, the influence of each node in the target water supply and drainage network is quantitatively evaluated to obtain the influence matrix between nodes. The quantitative evaluation of the influence here aims to quantify the strength of the causal relationship between different nodes, that is, the degree of influence of the state change of one node on other nodes. The influence matrix is ​​a two-dimensional table, in which the rows and columns represent different nodes in the water supply and drainage network, and each element represents the strength of the causal relationship between two nodes. For example, assuming that the system detects a drop in the water flow pressure of node A, the degree of influence of this change on node B, node C, etc. is calculated through the Bayesian network algorithm, and these influence values ​​will be recorded in the influence matrix. In this way, the system can fully understand the interaction between each node and provide data support for subsequent path identification and causal reasoning. Using the preset identification algorithm, the target water supply and drainage network is identified based on the influence matrix between nodes to obtain the influence path. Path identification is to find possible propagation paths from abnormal nodes to other nodes by analyzing the influence matrix. These paths include not only directly connected nodes, but also indirectly connected paths through intermediate nodes. For example, if the impact matrix shows that changes in node A have a direct impact on node B, and changes in node B have an impact on node C, the system will identify an indirect path from A to C. Through path identification, the system can more comprehensively understand the propagation mechanism of abnormal patterns throughout the network, providing a basis for fault location and prevention. Perform temporal causal reasoning and analysis on each path in the impact path to obtain a path impact trend graph. The path impact trend graph shows the impact trend of each path over time, which can help the system understand how abnormal patterns gradually spread over time.For example, the system can analyze the path from node A to node C, record the degree of influence of the change of node A on node C at each time point, and draw these data into a chart. Through the path impact trend chart, the operation and maintenance personnel can intuitively see the development process of the abnormal mode and take timely measures to prevent the fault from further expanding. In addition, the path impact trend chart can also be used to evaluate the importance of different paths and provide a reference for resource allocation and priority sorting. Based on the path impact trend chart and the abnormal water flow parameter probability distribution chart, the faulty nodes in the target water supply and drainage network and the fault factors corresponding to the faulty nodes are identified. This process combines the path impact trend chart with the abnormal water flow parameter probability distribution chart, comprehensively analyzes the state changes of each node and the probability of occurrence of abnormal patterns, so as to accurately locate the faulty nodes and the fault factors behind them. For example, if the system finds that the change of node A has the greatest impact on the entire network, and the abnormal water flow parameter probability distribution chart shows that the probability of pipeline rupture at node A is the highest, then the system can identify node A as a faulty node and use pipeline rupture as its main fault factor. In this way, the system can not only quickly locate the fault location, but also provide specific fault causes, providing a clear direction for fault handling. Finally, the fault nodes and the fault factors corresponding to the fault factors are marked in the target water supply and drainage network to obtain the fault network causal relationship diagram of the target water supply and drainage network. The fault network causal relationship diagram is a visualization tool that graphically displays the location and influence range of the fault nodes and their fault factors in the entire water supply and drainage network. For example, on a map of a city's water supply and drainage system, the system can mark each fault node and its fault factor with different colors and symbols, such as using red circles to represent nodes with pipe ruptures and blue triangles to represent nodes with valve failures. Through the fault network causal relationship diagram, operation and maintenance personnel can understand the fault distribution of the entire network at a glance, quickly formulate emergency response plans, and improve the efficiency and accuracy of fault handling. In summary, through the Bayesian network algorithm to perform causal relationship analysis on abnormal water flow pattern categories, the smart water supply and drainage network can deeply analyze the occurrence mechanism of faults, accurately locate fault nodes and the fault factors behind them, and provide a scientific basis for fault prevention and handling. This process not only improves the intelligence level of the system, but also provides strong technical support for ensuring the safe and stable operation of urban water supply and drainage systems.

[0038] In a specific embodiment, the fault network causal relationship diagram is input into a preset association rule mining algorithm to extract rule strategies to obtain water supply and drainage trigger rule strategy data, including: Identifying and classifying the fault nodes and the fault factors corresponding to the fault nodes in the fault network causal relationship diagram to obtain a fault factor classification diagram; Performing association rule mining based on the fault factor classification diagram to obtain preliminary association rules; Performing strength and confidence analysis on the preliminary association rules to obtain screened association rules; Performing graph mining analysis on the fault network causal relationship graph based on the filtered association rules to obtain a causal relationship association graph; Based on the causal relationship diagram, trigger rule strategy extraction is performed on the fault node to obtain water supply and drainage trigger rule strategy data.

[0039] Specifically, the fault network causal relationship diagram is input into the preset association rule mining algorithm to extract the rule strategy and obtain the water supply and drainage triggering rule strategy data. This process is a key step in the intelligent control method of the smart water supply and drainage network for optimizing fault handling and preventive measures. First, the fault nodes in the fault network causal relationship diagram and the fault factors corresponding to the fault nodes are identified and classified to obtain a fault factor classification diagram. The purpose of this step is to identify each fault node and its fault factor in detail in the fault network causal relationship diagram, and classify them according to the nature and type of the fault factor. For example, in an urban water supply and drainage system, if the fault network causal relationship diagram shows that pipeline rupture and valve failure in a certain area are the main fault factors, the system will classify these fault factors, such as classifying pipeline rupture as "physical damage" and valve failure as "mechanical failure". In this way, the system can more clearly understand the distribution of different types of fault factors, providing a basis for subsequent association rule mining. Association rule mining is performed based on the fault factor classification diagram to obtain preliminary association rules. Association rule mining is a data mining technology used to discover frequent item sets in a data set and the association relationship between them. In this step, the system will use the association rule mining algorithm to analyze the association relationship between different fault factors in the fault factor classification diagram and generate a series of preliminary association rules. For example, the system may find an association rule such as "When the service life of the pipeline in a certain area exceeds 20 years and the groundwater level rises by more than 2 meters in the last month, the risk of pipeline rupture in the area increases significantly." These preliminary association rules reveal the potential connection between different fault factors and provide clues for further analysis. The preliminary association rules are analyzed for strength and confidence to obtain the selected association rules. In the process of association rule mining, the number of preliminary association rules generated may be large, and the practical significance and credibility of some rules may not be high. Therefore, it is necessary to further screen these preliminary association rules to ensure that the final rules have high practical value. Strength analysis mainly evaluates the support and confidence of association rules. The support indicates the frequency of the rule in the data set, and the confidence indicates the reliability of the rule. For example, the system may set a minimum support threshold (such as 0.1) and a minimum confidence threshold (such as 0.8). Only association rules that meet both conditions will be retained. Through this screening, the system can eliminate those rules that appear accidentally or have low credibility, and retain the truly meaningful rules. Based on the screened association rules, the fault network causal relationship graph is subjected to graph mining analysis to obtain a causal relationship association graph. Graph mining analysis is an analysis technology specifically used to process graph structure data, aiming to discover patterns and structures in the graph. In this step, the system will apply the screened association rules to the fault network causal relationship graph to further analyze the causal relationship between the fault nodes.For example, the system can find complex multi-level causal relationships between certain fault nodes through graph mining analysis, such as "pipeline rupture" may lead to "water flow pressure drop", and "water flow pressure drop" may cause "water pump overload". Through this analysis, the system can generate a detailed causal relationship association diagram to show the interaction and impact path between each fault node. Based on the causal relationship association diagram, the trigger rule strategy of the fault node is extracted to obtain the water supply and drainage trigger rule strategy data. This process is to convert the information in the causal relationship association diagram into specific trigger rules and strategies to guide actual fault handling and preventive measures. For example, the system can generate the following trigger rules based on the causal relationship association diagram: "When the service life of the pipeline in a certain area exceeds 20 years and the groundwater level rises by more than 2 meters in the last month, the system should immediately increase the monitoring frequency of the area and notify the maintenance personnel to conduct on-site inspections." These trigger rules can not only help operation and maintenance personnel to discover potential fault risks in a timely manner, but also guide them to take effective preventive measures to avoid the occurrence of faults. In this way, the system can achieve closed-loop management from fault detection to fault prevention, and improve the operating efficiency and safety of the water supply and drainage system. In summary, by inputting the fault network causal relationship diagram into the preset association rule mining algorithm for rule strategy extraction, the smart water supply and drainage network can generate a series of specific trigger rules and strategies, providing a scientific basis for fault handling and prevention. This process not only improves the intelligence level of the system, but also provides strong technical support for ensuring the safe and stable operation of the urban water supply and drainage system. Through this multi-level and multi-angle analysis and optimization, the system can more effectively respond to various complex fault situations and improve the overall management level and service quality.

[0040] In a specific embodiment, the pre-control instruction generation for the target water supply and drainage network is performed by using the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence, including: Parsing the water supply and drainage trigger rule strategy data to obtain a strategy parsing result; Based on the strategy analysis results, the target water supply and drainage network is simulated in the operating state scenario to obtain water flow dynamic simulation data; Performing status evaluation on each node in the target water supply and drainage network based on the water flow dynamic simulation data to obtain a node status evaluation report; Based on the logic strategy matching algorithm, a control strategy matching analysis is performed on the node status assessment report to obtain a strategy matching result; Based on the strategy matching result, pre-control instructions are generated for the faulty nodes in the target water supply and drainage network to obtain a preliminary pre-control instruction sequence; Based on the preliminary pre-control instruction sequence, a response prediction analysis is performed on the target water supply and drainage network to obtain response prediction data; The pre-control instruction is optimized and adjusted based on the response prediction data to obtain a pre-control instruction sequence.

[0041] Specifically, the process of generating pre-control instructions for the target water supply and drainage network through the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence is an important step in realizing fault prevention and optimization management in the intelligent control method of the smart water supply and drainage network. First, the water supply and drainage trigger rule strategy data is parsed to obtain the strategy parsing result. The purpose of this step is to interpret the trigger rules and strategy data extracted from the association rule mining algorithm in detail and convert them into specific instructions that the system can understand and execute. For example, in an urban water supply and drainage system, if there is a rule in the trigger rule strategy data that "when the service life of the pipeline in a certain area exceeds 20 years and the groundwater level rises by more than 2 meters in the last month, the system should immediately increase the monitoring frequency of the area and notify the maintenance personnel to conduct on-site inspections", the system needs to parse this rule into a specific value of the increase in monitoring frequency and a specific way to notify the maintenance personnel. Based on the strategy parsing results, the operating state scenario of the target water supply and drainage network is simulated to obtain water flow dynamic simulation data. The operating state scenario simulation is to predict the operating state of the water supply and drainage network in different scenarios through simulation technology. The system will simulate the dynamic changes of water flow after the implementation of different control measures according to the parsed strategy results. For example, the system can simulate the changes in the water flow pressure, flow rate and water quality parameters in the area when the monitoring frequency is increased and the maintenance personnel are notified to conduct on-site inspections. Through this simulation, the system can understand the effects of different control measures in advance and provide a basis for the subsequent generation of control instructions. Based on the water flow dynamic simulation data, the state of each node in the target water supply and drainage network is evaluated to obtain a node state evaluation report. The state evaluation is a detailed analysis of the simulation results to evaluate the operating status of each node under different scenarios. The system will generate a state evaluation report for each node based on the simulation data, which includes the changes in the parameters such as the water flow pressure, flow rate, water quality, etc. of the node, and the impact of these changes on the entire network. For example, the system can evaluate whether the water flow pressure of a key node can be effectively controlled when the monitoring frequency is increased, or whether the leakage of the pipeline has improved after the maintenance personnel conduct an on-site inspection. Based on the logical strategy matching algorithm, the control strategy matching analysis is performed on the node state evaluation report to obtain a strategy matching result. The logical strategy matching algorithm is an algorithm for matching the evaluation result with a predefined control strategy. The system will analyze whether the current operating state meets the requirements of the predefined control strategy based on the node state evaluation report. For example, if the assessment report shows that the water flow pressure at a certain node is still beyond the safe range, the system will match the corresponding control strategy, such as increasing the power of the water pump or closing certain branches, to further reduce the pressure at the node. Based on the strategy matching results, pre-control instructions are generated for the faulty nodes in the target water supply and drainage network to obtain a preliminary pre-control instruction sequence.Pre-control instruction generation is to convert the matched control strategy into specific control instructions, which will be sent to the corresponding execution unit. For example, if the strategy matching result shows that the pump power needs to be increased, the system will generate a control instruction to instruct the pump controller to increase the power to a predetermined value. These preliminary pre-control instruction sequences will be used to guide the actual control operation to ensure that the state of the faulty node is effectively controlled. Based on the preliminary pre-control instruction sequence, the response situation of the target water supply and drainage network is predicted and analyzed to obtain response prediction data. Response prediction analysis is to predict the actual effect after the implementation of the preliminary pre-control instruction through simulation technology. The system will simulate again based on the preliminary pre-control instruction sequence to evaluate the response of the network after the implementation of these instructions. For example, the system can predict the water flow pressure distribution and flow changes of the entire network after the pump power is increased, as well as the impact of these changes on other nodes. Through this prediction, the system can evaluate the effectiveness and feasibility of the preliminary pre-control instruction. Based on the response prediction data, the pre-control instruction is optimized and adjusted to obtain a pre-control instruction sequence. Optimization adjustment is to further optimize the preliminary pre-control instruction according to the response prediction data to ensure that the final generated pre-control instruction can achieve the best control effect. For example, if the response prediction data shows that after increasing the pump power, the water flow pressure at a certain node is still too high, the system can adjust the increased power value, or combine other control measures, such as closing certain branches, to further optimize the control effect. Through multiple iterations and optimizations, the system finally generates a set of optimal pre-control instruction sequences, which will be sent to the corresponding execution units to achieve intelligent control of the target water supply and drainage network. In summary, by generating pre-control instructions for the target water supply and drainage network based on the water supply and drainage trigger rule strategy data, the smart water supply and drainage network can achieve full-process intelligent management from fault detection, strategy analysis, simulation evaluation to control instruction generation. This process not only improves the response speed and control accuracy of the system, but also provides strong technical support for ensuring the safe and stable operation of the urban water supply and drainage system. Through this multi-level and multi-angle analysis and optimization, the system can more effectively respond to various complex fault conditions and improve the overall management level and service quality.

[0042] In a specific embodiment, the control strategy matching analysis is performed on the node status assessment report based on the logic strategy matching algorithm to obtain a strategy matching result, including: By using a logic strategy matching algorithm, a logic state analysis is performed on the faulty nodes of the water supply and drainage network based on the node state evaluation report to obtain a logic state analysis report; Generate operation scenario logic rules for the target water supply and drainage network based on the logic status analysis report to obtain a logic rule set; Performing state logic reasoning analysis on the fault node using the logic rule set to obtain a logic reasoning result; The control strategy is logically matched based on the logical reasoning result to obtain a strategy matching result.

[0043] Specifically, the control strategy matching analysis is performed on the node status assessment report based on the logic strategy matching algorithm to obtain the strategy matching result. This process is one of the key steps in the intelligent control method of the smart water supply and drainage network for optimizing fault handling and preventive measures. First, the faulty nodes of the water supply and drainage network are logically analyzed based on the node status assessment report through the logic strategy matching algorithm to obtain a logic status analysis report. The purpose of this step is to logically process the information in the node status assessment report and extract the current state of the faulty node and its possible development trend. For example, in an urban water supply and drainage system, if the node status assessment report shows that the water flow pressure of a key node continues to increase and the flow rate increases abnormally, the system will convert these state information into logical descriptions through the logic strategy matching algorithm, such as "the water flow pressure of node A exceeds the threshold value X, and the flow rate exceeds the threshold value Y". These logical descriptions will be recorded in the logic status analysis report, providing a basis for subsequent logic rule generation and reasoning analysis. Based on the logic status analysis report, the target water supply and drainage network is operated. The scenario logic rule generation is to generate a set of logic rules applicable to the current operation scenario based on the information in the logic status analysis report. These logic rules describe the control measures that should be taken under specific conditions. For example, the system can generate the following logic rules based on the logic state analysis report: "If the water flow pressure of node A exceeds threshold X, and the flow exceeds threshold Y, the power of the upstream water pump of node A needs to be increased"; "If the water quality parameter of node B is lower than threshold Z, the backup filter device needs to be started". These logic rules not only cover the current fault state, but also take into account possible chain reactions, providing detailed guidance for the intelligent control of the system. The state logic reasoning analysis of the faulty node is performed through the logic rule set to obtain the logic reasoning result. The state logic reasoning analysis is to use the generated logic rule set to perform logic reasoning on the current state of the faulty node and predict the effects of different control measures. For example, the system can use the logic rule set to reason about the current state of node A and deduce how the water flow pressure and flow of node A will change after increasing the power of the upstream water pump. This reasoning analysis can not only verify the effectiveness of the control measures, but also discover potential risk points. For example, if the reasoning result shows that increasing the water pump power will cause the pressure of other nodes to exceed the safe range, the system can adjust the control strategy in time to avoid new faults. The control strategy is logically matched based on the logic reasoning result to obtain the strategy matching result. Logical matching is to compare the results of reasoning analysis with the predefined control strategy and select the most appropriate control measure. For example, if the logical reasoning results show that increasing the power of the water pump is the most effective measure, the system will match this measure with the predefined control strategy to confirm its feasibility and optimality.If there are multiple control strategies to choose from, the system will select the optimal control strategy based on the comprehensive evaluation of the logical reasoning results. For example, the system may choose a strategy that can effectively reduce the water flow pressure of node A and minimize the impact on other nodes. In this way, the system can ensure that the generated control instructions can not only solve the problem, but also maximize the operation status of the entire water supply and drainage network. In summary, through the logical strategy matching algorithm, the control strategy matching analysis of the node status assessment report is carried out, and the smart water supply and drainage network can realize the full process intelligent management from the logical description of the fault state, the logical rule generation of the operation scenario, the state logic reasoning analysis to the logical matching of the control strategy. This process not only improves the response speed and control accuracy of the system, but also provides strong technical support for ensuring the safe and stable operation of the urban water supply and drainage system. Through this multi-level and multi-angle analysis and optimization, the system can more effectively respond to various complex fault conditions and improve the overall management level and service quality. For example, in actual applications, when the system detects that the water flow pressure in a certain area is abnormally increased, through the above steps, the system can quickly generate and implement the optimal control strategy to restore the normal water supply in the area in time and avoid greater losses.

[0044] The above describes the intelligent control method of the intelligent water supply and drainage network in the embodiment of the present invention. The following describes the intelligent control system of the intelligent water supply and drainage network in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, an intelligent control system for a smart water supply and drainage network includes: The monitoring module 21 is used to monitor the target water supply and drainage network in real time through a preset Internet of Things to obtain water flow dynamic parameters; A first analysis module 22 is used to perform a time series cluster analysis on the water flow dynamic parameters to obtain a water flow pattern category; The second analysis module 23 is used for, if the water flow pattern category is abnormal, performing a causal relationship analysis on the target water supply and drainage network based on the abnormal water flow pattern category through a Bayesian network algorithm to obtain a fault network causal relationship diagram of the target water supply and drainage network; wherein the abnormal water flow pattern category has multiple categories; The extraction module 24 inputs the fault network causal relationship diagram into a preset association rule mining algorithm to extract rule strategies and obtain water supply and drainage trigger rule strategy data; A generating module 25, configured to generate a pre-control instruction for the target water supply and drainage network according to the water supply and drainage trigger rule strategy data, and obtain a pre-control instruction sequence; The control module 26 is used to control the target water supply and drainage network based on a pre-control instruction sequence.

[0045] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0046] Reference Figure 3 The present invention also provides a computer device in an embodiment, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0047] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0048] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0049] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0050] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0051] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent control method for a smart water supply and drainage network, characterized in that: The following steps are involved: Through the preset Internet of Things, the target water supply and drainage network is monitored in real time to obtain the dynamic parameters of water flow; Performing time series cluster analysis on the water flow dynamic parameters to obtain water flow pattern categories; If the water flow pattern category is abnormal, a causal relationship analysis is performed on the target water supply and drainage network based on the water flow dynamic parameters corresponding to the abnormal water flow pattern category through a Bayesian network algorithm to obtain a fault network causal relationship diagram of the target water supply and drainage network; Input the fault network causal relationship diagram into a preset association rule mining algorithm to extract rule strategies and obtain water supply and drainage trigger rule strategy data; Generate pre-control instructions for the target water supply and drainage network through the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence; The target water supply and drainage network is controlled based on the pre-control instruction sequence.

2. The intelligent control method of the smart water supply and drainage network according to claim 1 is characterized in that: The Internet of Things is a distributed sensor network. The preset Internet of Things is used to monitor the target water supply and drainage network in real time to obtain water flow dynamic parameters, including: Real-time data collection of key nodes in the water supply and drainage network is carried out through a distributed sensor network to obtain original monitoring data; Performing multi-source data fusion processing on the original monitoring data to obtain fused monitoring data; Performing data denoising and feature extraction on the fused monitoring data to obtain a water flow feature vector; Detecting whether there are abnormal values ​​in the water flow characteristic vector, and if so, removing the abnormal values ​​in the water flow characteristic vector to obtain the water flow characteristic vector after removal; The eliminated water flow feature vector is predicted and supplemented to obtain water flow dynamic parameters; wherein the water flow dynamic parameters include water flow rate, water flow pressure and water quality parameters.

3. The intelligent control method of the smart water supply and drainage network according to claim 1 is characterized in that: The water flow pattern categories are obtained by performing time series cluster analysis on the water flow dynamic parameters, including: Performing time series segmentation on the water flow dynamic parameters to obtain data segments in multiple time windows; The data segments are similarly measured by a preset dynamic time warping algorithm to obtain a distance matrix; wherein the distance matrix includes rows, columns and elements, the rows represent data segments in different time windows, the columns represent different data segments, and the elements represent similarity measurement values ​​between two data segments; Performing cluster analysis on the distance matrix by using a preset hierarchical clustering algorithm to generate a cluster tree; wherein the cluster tree is used to display the hierarchical relationship between the data segments; According to a preset cluster quantity threshold, a horizontal line of a specific height is intercepted from the cluster tree to obtain a plurality of clusters; wherein each of the clusters represents a type of water flow pattern; Extract features from the data segments in each cluster to obtain representative feature vectors; The representative feature vector is mapped to a predefined water flow pattern category to obtain a water flow pattern category; wherein the water flow pattern category includes a normal mode, an abnormal mode and a peak mode.

4. The intelligent control method of the smart water supply and drainage network according to claim 1 is characterized in that: The Bayesian network algorithm is used to perform a causal relationship analysis on the target water supply and drainage network based on the water flow dynamic parameters corresponding to the abnormal water flow pattern category to obtain a fault network causal relationship diagram of the target water supply and drainage network, including: By using the Bayesian network algorithm, the water flow dynamic parameters corresponding to the abnormal water flow pattern category are deeply analyzed to obtain a probability distribution diagram of abnormal water flow parameters; Based on the probability distribution diagram of abnormal water flow parameters, quantitatively evaluate the influence of each node in the target water supply and drainage network to obtain an influence matrix between nodes; wherein the influence matrix is ​​used to represent the strength of the causal relationship between each node; Using a preset identification algorithm, based on the inter-node influence matrix, path identification is performed on the target water supply and drainage network to obtain an influence path; wherein there are multiple influence paths; Performing time-series causal reasoning and analysis on each path in the impact path to obtain a path impact trend graph; wherein the path impact trend graph is the impact trend of each path over time; Identify the fault nodes and the fault factors corresponding to the fault nodes in the target water supply and drainage network based on the path influence trend graph and the abnormal water flow parameter probability distribution graph; The fault nodes and the fault factors corresponding to the fault factors are marked in the target water supply and drainage network to obtain a fault network causal relationship diagram of the target water supply and drainage network.

5. The intelligent control method of the smart water supply and drainage network according to claim 4 is characterized in that: The fault network causal relationship diagram is input into a preset association rule mining algorithm to extract rule strategies to obtain water supply and drainage trigger rule strategy data, including: Identifying and classifying the fault nodes and the fault factors corresponding to the fault nodes in the fault network causal relationship diagram to obtain a fault factor classification diagram; Performing association rule mining based on the fault factor classification diagram to obtain preliminary association rules; Performing strength and confidence analysis on the preliminary association rules to obtain screened association rules; Performing graph mining analysis on the fault network causal relationship graph based on the filtered association rules to obtain a causal relationship association graph; Based on the causal relationship diagram, trigger rule strategy extraction is performed on the fault node to obtain water supply and drainage trigger rule strategy data.

6. The intelligent control method of the smart water supply and drainage network according to claim 1 is characterized in that: The generating of pre-control instructions for the target water supply and drainage network by using the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence includes: Parsing the water supply and drainage trigger rule strategy data to obtain a strategy parsing result; Based on the strategy analysis results, the target water supply and drainage network is simulated in the operating state scenario to obtain water flow dynamic simulation data; Performing status evaluation on each node in the target water supply and drainage network based on the water flow dynamic simulation data to obtain a node status evaluation report; Based on the logic strategy matching algorithm, a control strategy matching analysis is performed on the node status assessment report to obtain a strategy matching result; Based on the strategy matching result, pre-control instructions are generated for the faulty nodes in the target water supply and drainage network to obtain a preliminary pre-control instruction sequence; Based on the preliminary pre-control instruction sequence, a response prediction analysis is performed on the target water supply and drainage network to obtain response prediction data; The pre-control instruction is optimized and adjusted based on the response prediction data to obtain a pre-control instruction sequence.

7. The intelligent control method of the smart water supply and drainage network according to claim 6 is characterized in that: The control strategy matching analysis is performed on the node status assessment report based on the logic strategy matching algorithm to obtain a strategy matching result, including: By using a logic strategy matching algorithm, a logic state analysis is performed on the faulty nodes of the water supply and drainage network based on the node state evaluation report to obtain a logic state analysis report; Generate operation scenario logic rules for the target water supply and drainage network based on the logic status analysis report to obtain a logic rule set; Performing state logic reasoning analysis on the fault node using the logic rule set to obtain a logic reasoning result; The control strategy is logically matched based on the logical reasoning result to obtain a strategy matching result.

8. An intelligent control system for a smart water supply and drainage network, characterized in that: include: The monitoring module is used to monitor the target water supply and drainage network in real time through the preset Internet of Things to obtain the dynamic parameters of water flow; A first analysis module is used to perform time series cluster analysis on the water flow dynamic parameters to obtain water flow pattern categories; The second analysis module is used for, if the water flow pattern category is abnormal, performing a causal relationship analysis on the target water supply and drainage network based on the abnormal water flow pattern category through a Bayesian network algorithm to obtain a fault network causal relationship diagram of the target water supply and drainage network; wherein there are multiple abnormal water flow pattern categories; An extraction module, used for inputting the fault network causal relationship diagram into a preset association rule mining algorithm to extract rule strategies and obtain water supply and drainage trigger rule strategy data; A generation module, used to generate pre-control instructions for the target water supply and drainage network according to the water supply and drainage trigger rule strategy data to obtain a pre-control instruction sequence; A control module is used to control the target water supply and drainage network based on a pre-control instruction sequence.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images