Urban-level power plant network monitoring method and system

Abstract

The application provides a city-level plant network monitoring method and system, wherein the method comprises the following steps: acquiring a system architecture of a drainage system, performing multi-stage pipeline division on sewage pipelines of the drainage system according to the system architecture, and obtaining a pipeline grading result; performing risk point identification and monitoring condition identification on the pipelines of the drainage system stage by stage according to the pipeline grading result, and generating a grading risk point identification result and a grading monitoring condition identification result; determining monitoring points of the drainage system and performing monitoring according to a drainage system monitoring strategy, the grading risk point identification result and the grading monitoring condition identification result, so as to obtain a grading monitoring system of the drainage system; acquiring real-time monitoring data of the monitoring points, and acquiring an operation state of the drainage system according to the real-time monitoring data; and the drainage system operation state is comprehensively and finely monitored, the perception ability of the operation state of the drainage system is effectively improved, and reliable data support is provided for pipeline network operation and maintenance management, optimal scheduling and system reconstruction.

Description

Technical Field

[0001] This application relates to the field of drainage system monitoring and diagnostic assessment technology, and in particular to a city-level plant network monitoring method and system. Background Technology

[0002] In recent years, while the urban sewage treatment system has been continuously improved, and despite significant improvements achieved through engineering measures such as strengthening pipeline infrastructure, upgrading sewage and stormwater separation, and rectifying mixed connections, the operational efficiency of the drainage system still faces severe challenges due to multiple factors: First, there are historical shortcomings in pipeline construction, with prominent issues such as unreasonable vertical design and reduced efficiency over long distances; second, inadequate construction supervision has led to widespread system problems such as mixed connections and large pipes being connected to small pipes; and third, severe infiltration of external water has resulted in dilution of sewage concentration and overloaded operation of the treatment system.

[0003] Against this backdrop, there is an urgent need to establish a comprehensive monitoring system covering the entire system. This system should collect real-time monitoring data on water level, flow rate, and water quality to construct a dynamic monitoring network covering the entire process from source to network to station to plant. This is not only a technical prerequisite for accurately diagnosing problems such as external water intrusion and incorrect connections, but also a crucial foundation for promoting integrated plant-network collaborative operation and maintenance. By driving management decisions through monitoring data, system operating efficiency can be effectively improved, ultimately achieving enhanced efficiency and sustainable development of the wastewater drainage system. Summary of the Invention

[0004] This application provides a city-level power plant and grid monitoring method and system to at least partially solve one of the technical problems in related technologies. The technical solution of this application is as follows:

[0005] In a first aspect, embodiments of this application propose a city-level power plant and grid monitoring method, including:

[0006] Obtain the system architecture of the drainage system, and divide the sewage pipes of the drainage system into multi-level pipes according to the system architecture to obtain the pipe classification result.

[0007] Based on the pipeline classification results, risk points and monitoring conditions are identified for the pipelines of the drainage system at each level, generating classification risk point identification results and classification monitoring condition identification results.

[0008] Based on the drainage system monitoring strategy, the results of the graded risk point identification, and the results of the graded monitoring condition identification, the monitoring points of the drainage system are determined and monitoring is carried out to obtain the graded monitoring system of the drainage system.

[0009] The system acquires real-time monitoring data from the monitoring points and obtains the operating status of the drainage system based on the real-time monitoring data.

[0010] The step of identifying risk points and monitoring conditions for the drainage system's pipelines according to the pipeline classification results, and generating classified risk point identification results and classified monitoring condition identification results, includes:

[0011] Based on the pipeline classification results, identify whether there are risk points and the types of risk points in each level of the drainage system, and obtain the classification risk point identification results.

[0012] Obtain the hydraulic model of the drainage network of the drainage system, simulate the operating state of the drainage system under different working conditions based on the hydraulic model of the drainage network, and identify the simulated water flow stability zone of each level of pipeline according to the operating state and the pipeline classification results.

[0013] Based on the actual water flow status of multiple key nodes of the drainage system, the observed water flow stability zone is obtained;

[0014] Based on the comparison results between the simulated stable water flow zone and the observed stable water flow zone, the results of the graded monitoring condition identification are obtained.

[0015] Secondly, embodiments of this application propose a city-level power plant and grid monitoring system, comprising:

[0016] The pipeline classification module is used to obtain the system architecture of the drainage system, and to divide the sewage pipelines of the drainage system into multiple levels according to the system architecture to obtain the pipeline classification result.

[0017] The pipeline identification module is used to identify risk points and monitoring conditions of the pipelines in the drainage system step by step according to the pipeline classification results, and generate classification risk point identification results and classification monitoring condition identification results.

[0018] The step of identifying risk points and monitoring conditions for the drainage system's pipelines according to the pipeline classification results, and generating graded risk point identification results and graded monitoring condition identification results, includes: identifying whether risk points exist and their types in each level of the drainage system's pipelines based on the pipeline classification results, thus obtaining graded risk point identification results; obtaining a drainage network hydraulic model of the drainage system; simulating the operating state of the drainage system under different working conditions based on the drainage network hydraulic model; identifying simulated stable flow zones for each level of pipelines based on the operating state and the pipeline classification results; obtaining observed stable flow zones based on the actual flow states of multiple key nodes in the drainage system; and obtaining graded monitoring condition identification results based on the comparison between the simulated stable flow zones and the observed stable flow zones.

[0019] The hierarchical monitoring module is used to determine the monitoring points of the drainage system and conduct monitoring based on the drainage system monitoring strategy, the hierarchical risk point identification results, and the hierarchical monitoring condition identification results, so as to obtain the hierarchical monitoring system of the drainage system.

[0020] The data processing module is used to acquire real-time monitoring data from the monitoring points and, based on the real-time monitoring data, to obtain the operating status of the drainage system.

[0021] This application has the following advantages and beneficial effects:

[0022] The city-level plant and network monitoring method and system provided in this application classifies drainage systems according to their architecture; differentiates pipeline classification for different types of drainage systems; identifies risk points and monitoring conditions at each pipeline level based on the pipeline classification; determines the monitoring points for each level of pipeline and conducts corresponding monitoring in conjunction with the drainage system monitoring strategy; and analyzes and predicts the operating status of the drainage system based on the monitoring data. This solution constructs a multi-level monitoring system based on the system architecture, achieving comprehensive and refined monitoring of the drainage system's operating status. Through a scientific monitoring network layout and multi-source data analysis methods, this solution effectively improves the perception capability and diagnostic accuracy of the drainage system's operating status, providing reliable data support and technical assurance for pipeline network operation and maintenance management, optimized scheduling, and system transformation.

[0023] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0025] Figure 1 A flowchart illustrating a city-level power plant network monitoring method provided in an embodiment of this application;

[0026] Figure 2 This is a diagram of the hierarchical pipe structure of a zoned drainage system provided in an embodiment of this application;

[0027] Figure 3 This is a diagram illustrating the hierarchical pipe architecture of a multi-level coordinated drainage system provided in an embodiment of this application.

[0028] Figure 4 This is a structural example diagram of a large pipe connecting to a small pipe (risk point) provided in an embodiment of this application;

[0029] Figure 5 A structural example diagram of the reverse slope (risk point) provided in the embodiments of this application;

[0030] Figure 6 The diagram shows a structural example of a pipeline (risk point) with a burial depth of less than or equal to 1.5m, as provided in the embodiments of this application.

[0031] Figure 7 This is a diagram illustrating the hierarchical monitoring system architecture of a zoned drainage system provided in an embodiment of this application.

[0032] Figure 8 This is a diagram illustrating the hierarchical monitoring system architecture of a multi-level collaborative drainage system provided in this application embodiment;

[0033] Figure 9 Example diagram of the monitoring pipes and monitoring method of the zoned drainage system provided in the embodiments of this application;

[0034] Figure 10 This is an example diagram of the monitoring pipes and monitoring methods for a multi-stage coordinated drainage system provided in the embodiments of this application;

[0035] Figure 11 This is a block diagram of a city-level power plant network monitoring system provided in an embodiment of this application. Detailed Implementation

[0036] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0037] The city-level power plant network monitoring method and system of this application are described below with reference to the accompanying drawings.

[0038] Figure 1 This is a flowchart illustrating a city-level power plant network monitoring method provided in an embodiment of this application.

[0039] It should be noted that the executing entity of the city-level plant and network monitoring method in this application embodiment is the city-level plant and network monitoring system in this application embodiment. The city-level plant and network monitoring system can be configured in an electronic device so that the electronic device can perform the city-level plant and network monitoring function.

[0040] like Figure 1 As shown, this city-level power plant network monitoring method includes the following steps:

[0041] Step S101: Obtain the system architecture of the drainage system, and divide the sewage pipes of the drainage system into multi-level pipes according to the system architecture to obtain the pipe classification result.

[0042] In some embodiments, obtaining the system architecture of the drainage system and dividing the sewage pipes of the drainage system into multiple levels based on the system architecture to obtain the pipe classification result includes: obtaining the system architecture of the drainage system through the hydraulic transfer relationship between the sewage treatment plant, pumping station, drainage zone and drainage users of the drainage system; determining the system type of the drainage system based on the system architecture; and dividing the sewage pipes of the drainage system into multiple levels based on the system type to obtain the pipe classification result.

[0043] As one approach, basic data on the drainage system is collected, including but not limited to attributes and related vector data of pipe networks, pumping stations, and sewage treatment plants; current status monitoring data and operational status of the drainage system; and the hydraulic transfer paths between sewage treatment plants, pumping stations, drainage zones, and drainage users are identified to clarify the system architecture. As an example, by systematically analyzing the hydraulic transfer relationships between sewage treatment plants, pumping stations, drainage zones, and drainage users, the system architecture of the drainage system is clarified. Based on this architecture, the system type of the drainage system is determined. Based on the system type, the sewage pipes of the drainage system are divided into multi-level pipe classifications to obtain the pipe classification results.

[0044] As one implementation method, drainage systems include zoned drainage systems and multi-level coordinated drainage systems. Based on the system architecture, drainage systems are divided into two types: drainage systems where each wastewater treatment plant operates independently (referred to as "zoned drainage systems"), and complex drainage systems where multiple wastewater treatment plants cooperate and there are multi-level couplings upstream (referred to as "multi-level coordinated drainage systems"). For these two types, the sewage pipelines of the drainage system are divided into multi-level pipelines.

[0045] Differentiated multi-level pipeline classification strategies are adopted for different types of drainage systems. In some embodiments, the sewage pipelines of the drainage system are classified into multiple levels according to the system type, resulting in pipeline classification results, including: for zoned drainage systems, the main inlet pipeline of the sewage treatment plant is classified as a primary pipeline, the drainage zone outlet and pump station inlet / outlet pipelines are classified as secondary pipelines, the pipelines at the junction of branch main pipelines are classified as tertiary pipelines, and the drainage user outlet pipelines are classified as quaternary pipelines; for multi-level coordinated drainage systems, the main inlet pipeline of the sewage treatment plant and the inter-plant hydraulic transfer main pipeline are classified as primary pipelines, the secondary main pipelines connected to the primary pipelines and the pump station inlet / outlet pipelines are classified as secondary pipelines, and the upstream branch pipes of the secondary pipelines are classified as tertiary pipelines. As an example, the pipeline classification architecture of a certain zoned drainage system is as follows: Figure 2 As shown, the hierarchical pipe structure of a multi-level coordinated drainage system is as follows: Figure 3 As shown.

[0046] This embodiment implements a hierarchical pipeline classification system for drainage systems. Based on the pipeline classification, the functional positioning and upstream and downstream relationships of the pipelines are clarified, a clear monitoring network is constructed, and a systematic analysis framework is provided for subsequent accurate location of abnormal operating conditions.

[0047] Step S102: Based on the pipeline classification results, risk points and monitoring conditions are identified for each level of the drainage system pipelines, generating classification risk point identification results and classification monitoring condition identification results.

[0048] In some embodiments, the above-mentioned risk point identification and monitoring condition identification of the drainage system pipelines according to the pipeline classification results, generating graded risk point identification results and graded monitoring condition identification results, includes: identifying whether there are risk points and the types of risk points in each level of the drainage system pipelines according to the pipeline classification results, and obtaining graded risk point identification results; wherein, risk points include points where large pipes connect to small pipes, reverse slope points, pipelines with a burial depth of less than or equal to 1.5m (shallow burial points), low-lying points, and slope change points; obtaining the drainage network hydraulic model of the drainage system, simulating the operating state of the drainage system under different working conditions based on the drainage network hydraulic model, and identifying the simulated water flow stability zone of each level of pipeline according to the operating state and the pipeline classification results; obtaining the observed water flow stability zone according to the actual water flow state of multiple key nodes of the drainage system; and obtaining the graded monitoring condition identification results based on the comparison results of the simulated water flow stability zone and the observed water flow stability zone.

[0049] In some embodiments, risk points may include, but are not limited to: connecting a large pipe to a small pipe (e.g., Figure 4 ), reverse slope (such as) Figure 5 Pipelines with a burial depth of less than or equal to 1.5m (shallow burial points) (such as...) Figure 6 ), low-lying points, and slope change points (sudden decreases in slope). As an example, starting from the primary pipeline, we analyze the existence and types of risk points at each level of the pipeline from the end to the source.

[0050] This embodiment adopts a hierarchical analysis method from the end to the source. Starting from the sewage treatment plant, it investigates upstream along the drainage system's pipe network step by step to identify key risk points such as large pipes connecting to small pipes, reverse slopes, pipes with a burial depth of less than or equal to 1.5m (shallow burial points), low-lying points, and slope change points. Liquid level monitoring equipment is then deployed at these risk points to achieve real-time early warning.

[0051] This can be understood as identifying monitoring conditions to ensure the accuracy and stability of monitoring data. This involves identifying the pipe structure characteristics of key nodes such as before the sewage treatment plant, at the outlet of the drainage zone, and at the inlet and outlet of the pumping station. This allows for the selection of pipe sections with stable water flow and no backflow to install flow monitoring equipment, while avoiding areas with turbulent water flow such as vertical drops and confluences of rivers (pipelines). This ensures the accuracy and reliability of the monitoring data.

[0052] As an example, data such as pipe network data, topographic data, remote sensing data, rainfall data, and regional water collection data of the drainage system are collected and processed. The processed data is then imported into a hydraulic model to verify the pipe network topology, delineate catchment areas, and input model parameters to obtain the drainage pipe network hydraulic model. The drainage pipe network hydraulic model is calibrated using historical monitoring data (minutely rainfall data and actual measurements of liquid level and flow rate of the drainage system's facilities). Its reliability is verified (by comparing simulated values ​​with monitored values ​​and verifying the NSE coefficient using formulas, etc.). Finally, the operating conditions of the pipe network under different operating conditions (i.e., different...) are simulated. Based on the flow velocity distribution of the pipe sections and the operational status and pipe classification results, the simulated stable and turbulent flow zones of each level of pipe are identified. On-site surveys record the flow direction, turbulent areas, and backflow phenomena at key nodes of the drainage system, such as before the sewage treatment plant and at the pump station inlet and outlet, eliminating interference areas such as vertical drops, sharp bends, and confluence points, and determining the locations of downslope pipe sections and areas with stable flow conditions. Based on the simulated stable flow zones of each level of pipe identified by the drainage network hydraulic model, combined with the locations of stable flow conditions monitored on-site, the classification monitoring conditions for each level of pipe in the drainage system are determined, and the final monitoring points are determined accordingly. For example, if the drainage network hydraulic model identifies a stable flow zone 300m downstream of the manifold before the sewage treatment plant, and on-site verification confirms no eddies in this section, with monitoring data showing 93% consistency with the model simulation, then the monitoring points for this section are determined. Through hydraulic model pre-screening and on-site verification, more than 50% of invalid monitoring points can be reduced, improving data stability.

[0053] As an example, the method for delineating catchment areas includes: dividing hydrological paths through a hydrological analysis module of spatial analysis, further forming preliminary catchment zones through watershed division, and then refining the catchment areas by combining the topological relationships of drainage facilities to achieve the delineation of catchment areas.

[0054] As an example, the input parameters for a drainage network hydraulic model include: basic physical parameters, hydrological and surface characteristic parameters, and parameters affecting runoff time. Basic physical parameters include area and width; hydrological and surface characteristic parameters include impermeability and water storage capacity in impermeable areas; parameters affecting runoff time include Manning coefficient in impermeable areas and Manning coefficient in permeable areas. Using the drainage network hydraulic model, software such as SWMM and InfoWorks, combined with the network topology and monitoring data, simulates water flow and water quality.

[0055] This embodiment obtains the results of graded risk point identification and graded monitoring condition identification by combining on-site surveys with hydraulic model simulation of drainage pipe networks, so as to determine the monitoring points.

[0056] Step S103: Based on the drainage system monitoring strategy, the results of the identification of graded risk points, and the results of the identification of graded monitoring conditions, determine the monitoring points of the drainage system and conduct monitoring to obtain the graded monitoring system of the drainage system.

[0057] The determination of monitoring points at each level, based on the drainage system monitoring strategy, is based on routine monitoring needs or source diagnosis needs.

[0058] In some embodiments, determining the monitoring points and conducting monitoring of the drainage system based on the drainage system monitoring strategy, the results of the graded risk point identification, and the results of the graded monitoring condition identification includes: setting up a four-level monitoring architecture for the zoned drainage system according to the drainage system monitoring strategy. The four-level monitoring architecture includes level one to level four monitoring. Level one monitoring includes water quality and quantity monitoring of the main pipeline entering the sewage treatment plant; level two monitoring includes water quality and quantity monitoring of the drainage zone outlet and the inlet and outlet pipelines of the pumping station; level three monitoring includes water quality and quantity monitoring of the pipelines at the junction of branch and main pipelines; and level four monitoring includes water quality and quantity monitoring of the outlet pipelines of drainage users. Also, setting up a three-level monitoring architecture for a multi-level coordinated drainage system according to the drainage system monitoring strategy includes... The monitoring system is divided into three levels. Level 1 monitoring includes water quality and quantity monitoring of the main pipelines entering the wastewater treatment plant and the inter-plant hydraulic transfer trunk lines. Level 2 monitoring includes water quality and quantity monitoring of secondary trunk lines connected to Level 1 pipelines, liquid level monitoring of the pump station forebay, and water quality and quantity monitoring at the pump station outlet. Level 3 monitoring includes water quality and quantity monitoring of the upstream branches of Level 2 pipelines. Based on the results of the tiered monitoring condition identification and the four-level monitoring framework, the monitoring points for the zoned drainage system are determined and monitored. Based on the results of the tiered monitoring condition identification and the three-level monitoring framework, the monitoring points for the multi-level coordinated drainage system are determined and monitored. Based on the results of the tiered risk point identification, the liquid level monitoring points for risk points in each level of the drainage system are determined and monitored.

[0059] In this embodiment, for a zoned drainage system, the drainage system monitoring strategy adopts a four-level monitoring architecture, corresponding to the four levels of pipelines in the zoned drainage system: level one pipeline monitors water quality and quantity, level two pipelines monitor water quality and quantity, level three pipelines monitor water quality and quantity, and level four pipelines monitor water quality and quantity. As an example, the hierarchical monitoring system of a certain zoned drainage system is as follows: Figure 7 As shown, the primary monitoring mainly involves monitoring the water quality and quantity of the main pipelines entering the wastewater treatment plant to understand the inflow situation at the end and obtain long-term operational patterns. Secondary monitoring includes monitoring the water quality and quantity at the drainage zone outlets and pump station inlets and outlets to understand the inflow situation in key areas and the operational status of key facilities. Tertiary monitoring involves monitoring the water quality and quantity of pipelines at the junctions of branch and main pipes. Quaternary monitoring involves monitoring the water quality and quantity of pipelines at the outlets of drainage users. Through this four-level monitoring framework, the water transfer relationships between pipelines at each level can be understood. Water quality and quantity balance analysis methods can be used to trace back from the end (wastewater treatment plant) to the source (drainage user), comparing the deviation between monitoring data and theoretical values, gradually narrowing down the scope of problem investigation, accurately identifying abnormal areas, and providing a scientific basis for subsequent pipeline network renovation, repair, and optimized operation and maintenance. In addition, liquid level monitoring is conducted at risk points in each level of pipeline to achieve real-time early warning of pipeline operational risks.

[0060] In this embodiment, for a multi-level coordinated drainage system, the drainage system monitoring strategy adopts a three-level monitoring architecture. As an example, the hierarchical monitoring system of a certain multi-level coordinated drainage system is as follows: Figure 8 As shown, for multi-level collaborative drainage systems with complex pipe network layers, the monitoring point layout needs to balance data accuracy and operation and maintenance intensity. The first level of monitoring is to monitor the water quality and quantity of the main pipelines entering the sewage treatment plant and the hydraulic transfer trunk lines between plants, to control the operating status of the core water transmission trunk lines of the system. The second level of monitoring is to monitor the water quality and quantity of the secondary trunk lines connected to the first level pipelines, and at the same time, to set up liquid level monitoring in the forebay of the pumping station and to monitor the water quality and quantity at the pumping station outlet, so as to achieve overall control of the operating status of key nodes. The third level of monitoring is to focus on the upstream branches of the second level pipelines, to understand the water transfer patterns in the core area through water quality and quantity monitoring, and to provide data support for troubleshooting.

[0061] The drainage system monitoring strategy in this embodiment also includes monitoring the liquid level at risk points of pipelines at all levels, so as to realize real-time early warning of pipeline operation risks.

[0062] Furthermore, to meet the needs of routine monitoring and precise source tracing analysis of the drainage system, and considering both monitoring efficiency and economic deployment, a "fixed + rotating" monitoring and maintenance management approach is adopted. For example... Figure 9 and Figure 10As shown, fixed monitoring is employed at key locations such as the main inlet pipelines of primary and secondary sewage treatment plants and the inlets and outlets of pumping stations to ensure the continuity and availability of basic data and support the overall system operation status assessment. For risk points, the locations of monitoring points can be dynamically adjusted according to the actual operating conditions of the drainage system. For widely distributed and complexly owned source wastewater users, rotating monitoring can be adopted, and portable monitoring equipment can be used to improve monitoring flexibility. This dynamic optimization strategy can improve resource utilization while ensuring monitoring coverage.

[0063] In some embodiments, rainfall data is obtained by monitoring the system boundary of the drainage system according to the rainwater zone corresponding to the drainage system; wherein, the system boundary refers to the spatial boundary of the drainage system.

[0064] This embodiment incorporates system boundary monitoring to account for the spatiotemporal variations in rainfall. Rain gauges are deployed evenly at key locations within the drainage system, installed in unobstructed areas. Combined with flow and level monitoring data, this provides essential rainfall data for analyzing the drainage system's operational status during rainy weather. For example, if rainfall differs significantly between areas A and B, they are divided into two rainwater zones. Rainfall monitoring is then conducted separately for each zone to analyze the drainage system's operational status during rainy weather.

[0065] In some embodiments, liquid level or video monitoring is performed at the outlet of the drainage system to obtain outlet monitoring data; based on the outlet monitoring data, abnormal outflow phenomena during the dry season are identified.

[0066] Therefore, based on the identified abnormal outflow phenomena during the dry season, the causes of abnormal outflow phenomena in the drainage system during the dry season can be investigated and addressed.

[0067] In some embodiments, liquid level monitoring is performed on river sections related to the drainage system to obtain river monitoring data; based on the river monitoring data and the elevation of the drainage pipes along the river, infiltration and inflow analysis results of the drainage system are obtained.

[0068] In other words, by monitoring the liquid level at relevant river sections of the drainage system and combining it with the elevation of the drainage pipes along the river, data support is provided for the infiltration and inflow analysis of the drainage system.

[0069] This embodiment deploys flow meters and online water quality monitoring equipment along the stable flow sections of the wastewater treatment plant's main inlet pipeline, pump station inlets and outlets, and drainage zone outlets, forming a multi-parameter collaborative monitoring network. This allows for real-time monitoring of inflow patterns, supporting operational diagnosis and pollution source tracing of the drainage system. Liquid level monitoring of the fore-pump pool enables dynamic optimization of pump station operation strategies and improved system efficiency through the linkage analysis of fore-pump pool level, pipeline fullness, and wastewater treatment plant inflow. Furthermore, rainfall, water level, and video monitoring equipment are installed at system boundaries, including liquid level and video monitoring at discharge outlets, water level monitoring at river cross-sections, and rainfall meters at key nodes. This constructs an integrated "plant-network-river" monitoring system, providing data support for identifying combined sewer overflows and treating external water infiltration.

[0070] Step S104: Obtain real-time monitoring data from the monitoring points, and obtain the operating status of the drainage system based on the real-time monitoring data.

[0071] In some embodiments, real-time monitoring data collected by monitoring devices at monitoring points is acquired at a certain data acquisition frequency. Based on the real-time monitoring data, the operating status of the drainage system is analyzed and predicted to obtain the operating status analysis and prediction results.

[0072] In some embodiments, the above-mentioned acquisition of the operating status of the drainage system based on real-time monitoring data includes: obtaining the network risk warning analysis result of the drainage system based on the monitoring data corresponding to the risk points in the real-time monitoring data and the risk warning thresholds corresponding to each risk point; identifying flow and water level anomalies based on real-time monitoring data and anomaly judgment thresholds, and obtaining the rainwater and sewage mixing identification result based on the flow and water level anomalies; obtaining the index values ​​of the system operation efficiency evaluation index system based on real-time monitoring data, and obtaining the system operation efficiency evaluation result based on the index values.

[0073] This embodiment analyzes and predicts the operating status of the drainage system, including risk warning of the drainage system's pipe network operation risk based on real-time monitoring data, identification of rainwater and sewage mixing, and evaluation of system operation efficiency. In the event of poor system operation efficiency evaluation results, the pump station operation strategy can be optimized to improve system operation efficiency.

[0074] In some embodiments, the method further includes: obtaining a monitoring data sequence based on real-time monitoring data; and obtaining a pipeline network operation status prediction result based on the monitoring data sequence and a trained pipeline network operation status prediction model.

[0075] In this embodiment, as monitoring and operational data accumulate, a mathematical model is trained using the accumulated monitoring data to obtain a pipeline network operation status prediction model. This model is then combined with new real-time monitoring data to analyze and predict the overall operation status of the drainage system pipeline network in both time and space.

[0076] In some embodiments, in order to improve the accuracy of the prediction model, the location of monitoring points can be dynamically optimized, and the configuration of monitoring points can be added or adjusted in a timely manner, ultimately providing data support for pipeline operation and maintenance, optimized scheduling, planning and renovation and other measures.

[0077] In some embodiments, a mathematical model is trained using historical monitoring data to obtain a pipeline network operation status prediction model. The mathematical model includes a coupled model of a mechanistic model and a neural network model. The mechanistic model includes a hydraulic model and a water quality model. The neural network model includes one of the following: a long short-term memory network model, a graph neural network model, a tree model, and an autoregressive moving average model. The method for constructing the coupled model includes: establishing a mechanistic model based on the physical mechanisms of the drainage system; training the neural network model using historical monitoring data; achieving bidirectional coupling between the mechanistic model and the neural network model through parameter transfer, data assimilation, or joint solution methods, wherein the mechanistic model provides mechanistic constraints to ensure the physical rationality of the neural network model, while the neural network model assists in correcting parameter errors in the mechanistic model or supplementing unresolved processes; using iterative calibration to balance the weights of the mechanistic model and the neural network model; ultimately forming a coupled model that combines physical interpretability and data-driven accuracy; and verifying and optimizing the trained coupled model for specific scenarios to achieve synergistic enhancement of mechanistic and data aspects.

[0078] The parameter transfer methods include: transferring intermediate physical quantities (including but not limited to pipeline flow rate, velocity, liquid level, and slope) calculated by the mechanism model as input features to the neural network model; and transferring the correction quantities output by the neural network model (including but not limited to model parameter correction values ​​and state variable increments) in reverse to update the internal parameters or boundary conditions of the mechanism model, forming a bidirectional data flow;

[0079] Data assimilation methods include: using ensemble Kalman filtering or particle filtering algorithms to use the predicted state obtained by the neural network model based on historical monitoring data as the observation update term, assimilating and correcting the simulated state of the mechanism model, and feeding the corrected state back to the neural network model to optimize its prediction for the next moment;

[0080] The joint solution method includes: combining the equations of the mechanistic model with the algebraic relations constructed by the neural network model to construct a coupled equation system, and iteratively solving the coupled equation system at each time step. Here, the equations of the mechanistic model provide physical constraints, and the algebraic relations of the neural network model are used to approximate or correct unmodeled dynamic parameters.

[0081] This embodiment constructs a hydraulic model and a pipeline operation status prediction model based on pipeline network data and monitoring data, which can realize real-time diagnosis and prediction of system operation status, and provide intelligent support for operation and maintenance decision-making.

[0082] The city-level plant and network monitoring method of this application classifies drainage systems according to their architecture; it performs differentiated pipeline classification for different types of drainage systems; based on the pipeline classification, it identifies risk points and monitoring conditions at each level, determines the monitoring points for each level of pipeline and conducts corresponding monitoring in conjunction with the drainage system monitoring strategy, and analyzes and predicts the operating status of the drainage system based on the monitoring data; this solution constructs a multi-level monitoring system of "end-process-source" through the hydraulic transfer path between sewage treatment plants, pumping stations, drainage zones, and drainage users, realizing dynamic monitoring of the entire process from sewage treatment plants to drainage users, and achieving comprehensive and refined monitoring of the operating status of the drainage system; this solution establishes differentiated monitoring schemes according to the type of drainage system, which can be adapted to different system types such as zoned and multi-level collaborative systems, significantly reducing operation and maintenance costs while ensuring the reliability of monitoring data; this solution effectively improves the perception capability and diagnostic accuracy of the operating status of the drainage system through scientific monitoring network layout and multi-source data analysis methods, providing reliable data support and technical guarantee for pipeline network operation and maintenance management, optimization scheduling, and system transformation; this solution... This plan implements hydraulic transfer paths between wastewater treatment plants, pumping stations, drainage zones, and drainage users, and conducts tiered monitoring according to the "end-process-source" sequence to understand the operational status of the drainage system. Through data accumulation, a network operation status prediction model is established to predict the spatiotemporal operation status of the drainage system, providing data support for drainage system renovation, operation and maintenance, and scheduling strategies. This plan, combined with hydraulic models and intelligent algorithm analysis, can not only provide real-time early warning of network anomalies and accurate source tracing, but also provide a scientific basis for network renovation and optimized scheduling. By clearly defining system boundaries and combining flow and level monitoring data, this plan provides necessary rainfall data for analyzing the operational status of the drainage system during rainy weather. This plan adopts a dual analysis method of "reverse grading + risk identification," and considers the feasibility of monitoring locations to ensure the scientific validity and effectiveness of monitoring point deployment. Furthermore, through the organic integration of multi-dimensional monitoring data such as level, flow, and water quality, a complete operational status assessment system for the drainage system can be established. Based on the collaborative analysis of mechanistic models and neural network models, this plan achieves in-depth mining and prediction of system operation patterns.

[0083] To achieve the above embodiments, this application also proposes a city-level power plant network monitoring system. Figure 11 This is a schematic diagram of the structure of a city-level power plant network monitoring system provided in an embodiment of this application. Figure 11 As shown, the city-level plant network monitoring system may include: a pipeline classification module 210, a pipeline identification module 220, a classification monitoring module 230, and a data processing module 240.

[0084] Among them, the pipeline classification module 210 is used to obtain the system architecture of the drainage system, and to divide the sewage pipelines of the drainage system into multiple levels according to the system architecture to obtain the pipeline classification result.

[0085] The pipeline identification module 220 is used to identify risk points and monitoring conditions of pipelines in the drainage system step by step according to the pipeline classification results, and generate classification risk point identification results and classification monitoring condition identification results.

[0086] Specifically, based on the pipeline classification results, risk points and monitoring conditions are identified for each level of the drainage system's pipelines, generating graded risk point identification results and graded monitoring condition identification results. This includes: identifying the existence and types of risk points in each level of the drainage system's pipelines based on the pipeline classification results; obtaining a hydraulic model of the drainage network; simulating the operating state of the drainage system under different working conditions based on the hydraulic model; identifying the simulated stable flow zones for each level of pipeline based on the operating state and pipeline classification results; obtaining the observed stable flow zones based on the actual flow states of multiple key nodes in the drainage system; and obtaining the graded monitoring condition identification results based on the comparison between the simulated and observed stable flow zones.

[0087] The graded monitoring module 230 is used to determine the monitoring points of the drainage system and conduct monitoring based on the drainage system monitoring strategy, the graded risk point identification results and the graded monitoring condition identification results, so as to obtain the graded monitoring system of the drainage system.

[0088] The data processing module 240 is used to acquire real-time monitoring data from the monitoring points and, based on the real-time monitoring data, to obtain the operating status of the drainage system.

[0089] Furthermore, in one possible implementation of this application embodiment, the pipeline classification module 210 is specifically used for:

[0090] The system architecture of the drainage system is obtained by analyzing the hydraulic transfer relationships between the sewage treatment plants, pumping stations, drainage zones, and drainage users.

[0091] Based on the system architecture, the system type of the drainage system is determined. Based on the system type, the sewage pipes of the drainage system are divided into multiple levels to obtain the pipe classification results.

[0092] Furthermore, in one possible implementation of this application embodiment, the drainage system type includes a zoned drainage system and a multi-level coordinated drainage system. The pipe classification module 210, when performing multi-level pipe division of the sewage pipes of the drainage system according to the system type to obtain the pipe classification result, is specifically used for:

[0093] For zoned drainage systems, the main inlet pipes of the sewage treatment plant are classified as primary pipes, the drainage zone outlets and pump station inlet and outlet pipes are classified as secondary pipes, and the pipes at the junction of branch pipes and main pipes are classified as tertiary pipes. The drainage outlet pipes of drainage users are classified as quaternary pipes.

[0094] For a multi-level coordinated drainage system, the main inlet pipe of the sewage treatment plant and the inter-plant hydraulic transfer main pipe are classified as primary pipes, the secondary main pipes connected to the primary pipes and the inlet and outlet pipes of the pumping stations are classified as secondary pipes, and the upstream branch pipes of the secondary pipes are classified as tertiary pipes.

[0095] Furthermore, in one possible implementation of this application embodiment, the pipe identification module 220 is specifically used for:

[0096] Based on the pipeline classification results, identify whether there are risk points and the types of risk points in each level of the drainage system, and obtain the classification risk point identification results; among them, risk points include the connection point between large and small pipes, reverse slope points, pipes with a burial depth of less than or equal to 1.5m, low-lying points, and slope change points.

[0097] Obtain the hydraulic model of the drainage network of the drainage system, simulate the operating state of the drainage system under different working conditions based on the hydraulic model of the drainage network, and identify the simulated water flow stability zone of each level of pipeline according to the operating state and pipeline classification results.

[0098] Based on the actual water flow status of multiple key nodes in the drainage system, the stable zone of the observed water flow is obtained;

[0099] Based on the comparison between the simulated stable water flow zone and the observed stable water flow zone, the results of the graded monitoring condition identification are obtained.

[0100] Furthermore, in one possible implementation of this application embodiment, the hierarchical monitoring module 230 is specifically used for:

[0101] According to the drainage system monitoring strategy, a four-level monitoring architecture is set up for the zoned drainage system. The four-level monitoring architecture includes level one to level four monitoring. Level one monitoring includes water quality and quantity monitoring of the main pipelines entering the sewage treatment plant; level two monitoring includes water quality and quantity monitoring of the drainage zone outlets and pump station inlet and outlet pipelines; level three monitoring includes water quality and quantity monitoring of the pipelines at the junction of branch and main pipelines; and level four monitoring includes water quality and quantity monitoring of the drainage user outlet pipelines.

[0102] According to the drainage system monitoring strategy, a three-level monitoring architecture is set up for the multi-level coordinated drainage system. The three-level monitoring architecture includes primary monitoring to tertiary monitoring. Primary monitoring includes water quality and quantity monitoring of the main pipelines entering the sewage treatment plant and the hydraulic transfer trunk lines between plants. Secondary monitoring includes water quality and quantity monitoring of the secondary trunk lines connected to the primary pipelines, liquid level monitoring of the pump station forebay, and water quality and quantity monitoring at the pump station outlet. Tertiary monitoring includes water quality and quantity monitoring of the upstream branch lines of the secondary pipelines.

[0103] Based on the results of the hierarchical monitoring condition identification and the four-level monitoring architecture, the monitoring points of the zoned drainage system were determined and monitoring was carried out.

[0104] Based on the results of the hierarchical monitoring condition identification and the three-level monitoring architecture, the monitoring points of the multi-level collaborative drainage system were determined and monitoring was carried out.

[0105] Based on the results of the risk point identification at different levels, the liquid level monitoring points for risk points in the drainage system at each level are determined and monitored.

[0106] Furthermore, in one possible implementation of this application embodiment, the hierarchical monitoring module 230 is also used for:

[0107] Based on the rainwater zones corresponding to the drainage system, rainfall data is obtained by monitoring the system boundary of the drainage system; where the system boundary refers to the spatial boundary of the drainage system.

[0108] Liquid level or video monitoring is performed at the outlets of the drainage system to obtain outlet monitoring data; based on the outlet monitoring data, abnormal outflow phenomena during the dry season are identified.

[0109] Liquid level monitoring was conducted on river sections related to the drainage system to obtain river monitoring data. Based on the river monitoring data and the elevation of the drainage pipes along the river, the infiltration and inflow analysis results of the drainage system were obtained.

[0110] Furthermore, in one possible implementation of this application embodiment, the data processing module 240 is specifically used for:

[0111] Based on the monitoring data corresponding to the risk points in the real-time monitoring data and the risk warning thresholds corresponding to each risk point, the risk warning analysis results of the drainage system's pipe network are obtained.

[0112] Based on real-time monitoring data and anomaly judgment thresholds, abnormal flow and water level points are identified, and the results of rainwater and sewage mixing identification are obtained based on these abnormal flow and water level points.

[0113] Based on real-time monitoring data, the index values ​​of the system operation efficiency evaluation index system are obtained, and the system operation efficiency evaluation results are obtained based on the index values.

[0114] Furthermore, in one possible implementation of this application embodiment, the data processing module 240 is further configured to:

[0115] Based on real-time monitoring data, a monitoring data sequence is obtained;

[0116] Based on the monitoring data sequence and the trained pipeline network operation status prediction model, the pipeline network operation status prediction results are obtained.

[0117] Furthermore, in one possible implementation of this application embodiment, the data processing module 240 is further configured to:

[0118] A mathematical model is trained using historical monitoring data to obtain a predictive model for the pipeline network's operational status. This mathematical model includes a coupled model of a mechanistic model and a neural network model. The mechanistic model comprises a hydraulic model and a water quality model, while the neural network model includes one of the following: a long short-term memory network model, a graph neural network model, a tree model, or an autoregressive moving average model. The construction method of the coupled model includes: establishing a mechanistic model based on the physical mechanisms of the drainage system; training the neural network model using historical monitoring data; achieving bidirectional coupling between the mechanistic model and the neural network model through parameter transfer, data assimilation, or joint solution methods. The mechanistic model provides mechanistic constraints to ensure the physical rationality of the neural network model, while the neural network model assists in correcting parameter errors in the mechanistic model or supplementing unresolved processes; and iterative calibration is used to balance the weights of the mechanistic model and the neural network model.

[0119] The parameter passing methods include: passing the intermediate physical quantities calculated by the mechanism model as input features to the neural network model; and passing the correction quantities output by the neural network model in reverse to update the internal parameters or boundary conditions of the mechanism model, forming a bidirectional data flow;

[0120] Data assimilation methods include: using ensemble Kalman filtering or particle filtering algorithms to use the predicted state obtained by the neural network model based on historical monitoring data as the observation update term, assimilating and correcting the simulated state of the mechanism model, and feeding the corrected state back to the neural network model to optimize its prediction for the next moment;

[0121] The joint solution method includes: combining the equations of the mechanistic model with the algebraic relations constructed by the neural network model to construct a coupled equation system, and iteratively solving the coupled equation system at each time step. Here, the equations of the mechanistic model provide physical constraints, and the algebraic relations of the neural network model are used to approximate or correct unmodeled dynamic parameters.

[0122] It should be noted that the foregoing explanation of the city-level power plant network monitoring method embodiment also applies to the city-level power plant network monitoring system of this embodiment, and will not be repeated here.

[0123] In the foregoing descriptions of the embodiments, the terms "some embodiments," "examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0124] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0125] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A city-level power plant and grid monitoring method, characterized in that, Includes the following steps: Obtain the system architecture of the drainage system, and divide the sewage pipes of the drainage system into multi-level pipes according to the system architecture to obtain the pipe classification result. Based on the pipeline classification results, risk points and monitoring conditions are identified for the pipelines of the drainage system at each level, generating classification risk point identification results and classification monitoring condition identification results. Based on the drainage system monitoring strategy, the results of the graded risk point identification, and the results of the graded monitoring condition identification, the monitoring points of the drainage system are determined and monitoring is carried out to obtain the graded monitoring system of the drainage system. The system acquires real-time monitoring data from the monitoring points and obtains the operating status of the drainage system based on the real-time monitoring data. The step of identifying risk points and monitoring conditions for the drainage system's pipelines according to the pipeline classification results, and generating classified risk point identification results and classified monitoring condition identification results, includes: Based on the pipeline classification results, identify whether there are risk points and the types of risk points in each level of the drainage system, and obtain the classification risk point identification results. Obtain the hydraulic model of the drainage network of the drainage system, simulate the operating state of the drainage system under different working conditions based on the hydraulic model of the drainage network, and identify the simulated water flow stability zone of each level of pipeline according to the operating state and the pipeline classification results. Based on the actual water flow status of multiple key nodes of the drainage system, the observed water flow stability zone is obtained; Based on the comparison results between the simulated stable water flow zone and the observed stable water flow zone, the results of the graded monitoring condition identification are obtained; The method further includes: obtaining a monitoring data sequence based on the real-time monitoring data; obtaining a pipeline network operation status prediction result based on the monitoring data sequence and a trained pipeline network operation status prediction model; the method for obtaining the pipeline network operation status prediction model includes: A mathematical model is trained using historical monitoring data to obtain a pipeline network operation status prediction model. The mathematical model includes a coupled model of a mechanistic model and a neural network model. The mechanistic model includes a hydraulic model and a water quality model. The neural network model includes one of the following: a long short-term memory network model, a graph neural network model, a tree model, and an autoregressive moving average model. The construction method of the coupled model includes: establishing a mechanistic model based on the physical mechanism of the drainage system; training the neural network model using historical monitoring data; achieving bidirectional coupling between the mechanistic model and the neural network model through parameter transfer, data assimilation, or joint solution methods. The mechanistic model provides mechanistic constraints to ensure the physical rationality of the neural network model, while the neural network model assists in correcting parameter errors in the mechanistic model or supplementing unresolved processes; and iteratively calibrating and balancing the weights of the mechanistic model and the neural network model. The parameter transmission method includes: transmitting the intermediate physical quantities calculated by the mechanism model as input features to the neural network model; and transmitting the correction quantities output by the neural network model in reverse to update the internal parameters or boundary conditions of the mechanism model, forming a bidirectional data flow; The data assimilation method includes: using ensemble Kalman filtering or particle filtering algorithms to use the predicted state obtained by the neural network model based on historical monitoring data as the observation update term, assimilating and correcting the simulated state of the mechanism model, and feeding back the corrected state to the neural network model to optimize its prediction at the next moment; The joint solution method includes: combining the equations of the mechanistic model with the algebraic relations constructed by the neural network model to construct a coupled equation set, and iteratively solving the coupled equation set at each time step, wherein the equations of the mechanistic model provide physical constraints, and the algebraic relations of the neural network model are used to approximate or correct unmodeled dynamic parameters.

2. The city-level power plant network monitoring method according to claim 1, characterized in that, The system architecture of the drainage system is obtained, and the sewage pipes of the drainage system are divided into multiple levels according to the system architecture to obtain the pipe classification results, including: The system architecture of the drainage system is obtained by considering the hydraulic transfer relationships between the wastewater treatment plant, pumping station, drainage zones, and drainage users. Based on the system architecture, the system type of the drainage system is determined. Based on the system type, the sewage pipes of the drainage system are divided into multiple levels to obtain the pipe classification results.

3. The city-level power plant network monitoring method according to claim 2, characterized in that, The drainage system types include zoned drainage systems and multi-level coordinated drainage systems. Based on the system type, the sewage pipes of the drainage system are divided into multi-level pipe classifications to obtain pipe classification results, including: For the aforementioned zoned drainage system, the main inlet pipe of the sewage treatment plant is classified as a primary pipe, the drainage zone outlet and pump station inlet and outlet pipes are classified as secondary pipes, the pipes at the junction of branch pipes and main pipes are classified as tertiary pipes, and the drainage outlet pipes of drainage users are classified as quaternary pipes. For the aforementioned multi-level coordinated drainage system, the main inlet pipe of the sewage treatment plant and the inter-plant hydraulic transfer main pipe are classified as primary pipes, the secondary main pipes connected to the primary pipes and the inlet and outlet pipes of the pumping stations are classified as secondary pipes, and the upstream branch pipes of the secondary pipes are classified as tertiary pipes.

4. The city-level power plant network monitoring method according to claim 1, characterized in that, The risk points include the connection point between the large pipe and the small pipe, the reverse slope point, the pipe with a burial depth of less than or equal to 1.5m, the low-lying point, and the slope change point.

5. A city-level power plant network monitoring method according to claim 3, characterized in that, The step of determining the monitoring points for the drainage system and conducting monitoring based on the drainage system monitoring strategy, the results of the graded risk point identification, and the results of the graded monitoring condition identification includes: According to the drainage system monitoring strategy, a four-level monitoring architecture is set up for the zoned drainage system. The four-level monitoring architecture includes level one monitoring to level four monitoring. Level one monitoring includes water quality and quantity monitoring of the main pipeline entering the sewage treatment plant. Level two monitoring includes water quality and quantity monitoring of the drainage zone outlet and pump station inlet and outlet pipelines. Level three monitoring includes water quality and quantity monitoring of the pipelines at the junction of branch and main pipelines. Level four monitoring includes water quality and quantity monitoring of the drainage user outlet pipelines. According to the drainage system monitoring strategy, a three-level monitoring architecture is set up for the multi-level collaborative drainage system. The three-level monitoring architecture includes primary monitoring to tertiary monitoring. Primary monitoring includes water quality and quantity monitoring of the main pipeline entering the sewage treatment plant and the inter-plant hydraulic transfer trunk pipeline. Secondary monitoring includes water quality and quantity monitoring of the secondary trunk pipeline connected to the primary pipeline, liquid level monitoring of the pump station forebay, and water quality and quantity monitoring at the pump station outlet. Tertiary monitoring includes water quality and quantity monitoring of the upstream branch pipes of the secondary pipeline. Based on the results of the hierarchical monitoring condition identification and the four-level monitoring architecture, the monitoring points of the zoned drainage system are determined and monitoring is carried out. Based on the results of the hierarchical monitoring condition identification and the three-level monitoring architecture, the monitoring points of the multi-level collaborative drainage system are determined and monitored. Based on the results of the risk point identification, the liquid level monitoring points of the risk points in each level of the drainage system are determined and monitored.

6. The city-level power plant network monitoring method according to claim 1, characterized in that, The method further includes: Based on the rainwater zone corresponding to the drainage system, rainfall data is obtained by monitoring the system boundary of the drainage system; wherein, the system boundary refers to the spatial boundary of the drainage system. Liquid level or video monitoring is performed at the outlet of the drainage system to obtain outlet monitoring data; based on the outlet monitoring data, abnormal outflow phenomena during the dry season are identified. Liquid level monitoring is performed on the river cross-sections related to the drainage system to obtain river monitoring data; based on the river monitoring data and the elevation of the drainage pipes along the river of the drainage system, the infiltration and inflow analysis results of the drainage system are obtained.

7. The city-level power plant network monitoring method according to claim 1, characterized in that, The step of obtaining the operating status of the drainage system based on the real-time monitoring data includes: Based on the monitoring data corresponding to the risk points in the real-time monitoring data and the risk warning thresholds corresponding to each risk point, the network risk warning analysis results of the drainage system are obtained. Based on the real-time monitoring data and anomaly judgment threshold, abnormal flow and water level points are identified, and the results of rainwater and sewage mixing identification are obtained based on the abnormal flow and water level points. Based on the real-time monitoring data, the index values ​​of the system operation efficiency evaluation index system are obtained, and based on the index values, the system operation efficiency evaluation results are obtained.

8. A city-level power plant network monitoring system, characterized in that, include: The pipeline classification module is used to obtain the system architecture of the drainage system, and to divide the sewage pipelines of the drainage system into multiple levels according to the system architecture to obtain the pipeline classification result. The pipeline identification module is used to identify risk points and monitoring conditions of the pipelines in the drainage system step by step according to the pipeline classification results, and generate classification risk point identification results and classification monitoring condition identification results. The step of identifying risk points and monitoring conditions for the drainage system's pipelines according to the pipeline classification results, and generating graded risk point identification results and graded monitoring condition identification results, includes: identifying whether risk points exist and their types in each level of the drainage system's pipelines based on the pipeline classification results, thus obtaining graded risk point identification results; obtaining a drainage network hydraulic model of the drainage system; simulating the operating state of the drainage system under different working conditions based on the drainage network hydraulic model; identifying simulated stable flow zones for each level of pipelines based on the operating state and the pipeline classification results; obtaining observed stable flow zones based on the actual flow states of multiple key nodes in the drainage system; and obtaining graded monitoring condition identification results based on the comparison between the simulated stable flow zones and the observed stable flow zones. The hierarchical monitoring module is used to determine the monitoring points of the drainage system and conduct monitoring based on the drainage system monitoring strategy, the hierarchical risk point identification results, and the hierarchical monitoring condition identification results, so as to obtain the hierarchical monitoring system of the drainage system. The data processing module is used to acquire real-time monitoring data from the monitoring points and, based on the real-time monitoring data, to obtain the operating status of the drainage system. It is also used to: obtain a monitoring data sequence based on the real-time monitoring data; and obtain a pipeline operating status prediction result based on the monitoring data sequence and a trained pipeline operating status prediction model. The method for acquiring the pipeline operating status prediction model includes: training a mathematical model using historical monitoring data to obtain the pipeline operating status prediction model. The mathematical model includes a coupled model of a mechanistic model and a neural network model. The mechanistic model includes a hydraulic model and a water quality model. The model includes one of the following: Long Short-Term Memory Network (LSTM) model, Graph Neural Network (GNN) model, Tree model, and Autoregressive Moving Average (AMA) model. The method for constructing the coupled model includes: establishing a mechanistic model based on the physical mechanism of the drainage system; training the neural network model using historical monitoring data; achieving bidirectional coupling between the mechanistic model and the neural network model through parameter transfer, data assimilation, or joint solution, wherein the mechanistic model provides mechanistic constraints to ensure the physical rationality of the neural network model, while the neural network model assists in correcting parameter errors in the mechanistic model or supplementing unresolved processes; and using iterative calibration to balance the weights of the mechanistic model and the neural network model. The parameter transmission method includes: transmitting the intermediate physical quantities calculated by the mechanism model as input features to the neural network model; and transmitting the correction quantities output by the neural network model in reverse to update the internal parameters or boundary conditions of the mechanism model, forming a bidirectional data flow; The data assimilation method includes: using ensemble Kalman filtering or particle filtering algorithms to use the predicted state obtained by the neural network model based on historical monitoring data as the observation update term, assimilating and correcting the simulated state of the mechanism model, and feeding back the corrected state to the neural network model to optimize its prediction at the next moment; The joint solution method includes: combining the equations of the mechanistic model with the algebraic relations constructed by the neural network model to construct a coupled equation set, and iteratively solving the coupled equation set at each time step, wherein the equations of the mechanistic model provide physical constraints, and the algebraic relations of the neural network model are used to approximate or correct unmodeled dynamic parameters.

Images