Drainage pipe network control node intelligent identification method, device, equipment and product

Abstract

The invention relates to the technical field of real-time control of urban drainage systems, and discloses an intelligent identification method, device, equipment and product for control nodes of a drainage pipe network, which ensures that the flow direction of the drainage pipe network accords with actual hydraulic characteristics by acquiring a drainage process simulation data set of the drainage pipe network to be identified and utilizing model simulation and flow direction correction. Furthermore, each inspection well node in the target drainage pipe network is taken as a control node, and the slope value of the flow energy line of the drainage pipe network is calculated, so that the hydraulic characteristics of the upstream of the control node can be accurately reflected. Furthermore, through space capacity evaluation in an inspection well node regulation and control influence range and control node dynamic optimization selection, the relevance of control node selection can be ensured, and the calculation efficiency of key control node identification and the applicability of the key control node identification in a complex drainage scene are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of real-time control of urban drainage systems, and particularly relates to a drainage pipe network control node intelligent identification method, device, equipment and product. BACKGROUND

[0002] The traditional "mainly drainage" operation concept of urban drainage systems cannot fully utilize the water storage capacity of drainage pipe networks. How to dynamically activate the pipe network storage space through intelligent control means has become a problem to be solved for improving the resilience of urban drainage systems.

[0003] The selection of optimal control nodes of urban drainage systems involves double-layer optimization of node selection and scheme evaluation. The scheme evaluation based on physical process simulation is time-consuming and difficult to realize. The intuitive method is to use intelligent optimization algorithms such as genetic algorithms for outer control node optimization, and to combine mechanism models and rule control or model predictive control for real-time control method optimization of control node dynamic control strategy, to analyze the operation objective function under different rainfall conditions, so as to determine the optimal control node. The comprehensive time of inner and outer optimization in this form may take several months. Therefore, it is of great significance to develop an intelligent identification method of key control nodes of drainage pipe networks based on optimal utilization of storage space.

[0004] At present, the current research mainly develops an optimal control node selection method based on graph theory and static space evaluation: the method based on graph theory selects control nodes by defining indexes representing network topological structure characteristics such as degree, in-degree, and betweenness centrality, and sorting according to the size of the index value; the method based on static space evaluation determines the relationship between nodes and controllable pipe space by evaluating the range of drainage pipes that can be affected by each potential control node, and then selects control nodes according to the size of the controllable pipe space capacity. However, the existing methods cannot consider the correlation between control nodes, resulting in insufficient linkage of control nodes, and further leading to low calculation efficiency of control node identification. SUMMARY

[0005] Therefore, the present application provides a drainage pipe network control node intelligent identification method, device, equipment and product to solve the problem that the existing key control node intelligent identification method of drainage pipe networks cannot consider the correlation between control nodes, resulting in insufficient linkage of control nodes, and further leading to low calculation efficiency of control node identification.

[0006] In the first aspect, the present application provides a drainage pipe network control node intelligent identification method, which comprises: obtain a drainage process simulation data set of the to-be-identified drainage pipe network; based on the drainage process simulation data set, correct the flow direction of the to-be-identified drainage pipe network by using a preset drainage process simulation model, and obtain a target drainage pipe network after the flow direction is corrected; take each inspection well node in the target drainage pipe network as a control node, calculate the slope value of the flow energy line of the target drainage pipe network, calculate the pipe space capacity of the upstream pipe of each control node based on the ground elevation and the slope value of each control node, and make node decisions and determine the target control node by using a multi-state dynamic programming method based on the pipe space capacity of each control node and the total pipe space capacity of the upstream pipes of the plurality of control nodes.

[0007] The drainage pipe network control node intelligent identification method provided by the application solves the error problem that may exist in the traditional pipe network flow direction evaluation, ensures that the flow direction of the drainage pipe network conforms to the actual hydraulic characteristics, accurately reflects the hydraulic characteristics of the upstream of the control node by taking each inspection well node in the target drainage pipe network as a control node and calculating the slope value of the flow energy line of the drainage pipe network, accurately quantifies the adjustable upstream pipe storage space of each control node by calculating the pipe space capacity of the upstream pipe of each control node in combination with the ground elevation and the slope value of each control node, avoids the repetition or omission of capacity evaluation, converts the control node selection into a multi-stage optimal decision problem, ensures that the selected target control node has relevance by using a multi-state dynamic programming method, maximizes the use of the pipe network storage space, realizes minute-level rapid identification, is suitable for use in complex drainage scenarios such as normal and fault scenarios, and effectively improves the resilience of the urban drainage system. Therefore, by implementing the application, the spatial capacity evaluation within the influence range of the inspection well node and the dynamic optimization selection of the control node can ensure the relevance of the control node selection, improve the calculation efficiency of the key control node identification, and improve the applicability of the key control node identification in complex drainage scenarios.

[0008] In an optional embodiment, based on the drainage process simulation data set, the flow direction of the to-be-identified drainage pipe network is corrected by using a preset drainage process simulation model, and a target drainage pipe network after the flow direction is corrected is obtained, including: obtain a plurality of flow direction to-be-corrected pipes of the to-be-identified drainage pipe network; input the drainage process simulation data set into a preset drainage process simulation model to obtain a drainage process simulation result; correct the flow direction of the plurality of flow direction to-be-corrected pipes by using the drainage process simulation result, and obtain a target drainage pipe network after the flow direction is corrected.

[0009] The intelligent identification method of the control node of the drainage pipe network provided by the application can avoid the redundant operation of indiscriminately checking all pipes by screening the pipes with possible flow direction errors, and improve the pertinence and efficiency of flow direction correction. Further, the hydraulic state of the drainage pipe network in actual operation can be truly restored by using the drainage process simulation data set for simulation. Further, the flow direction correction is performed by using the drainage process simulation result, which solves the error problem that may exist in the traditional pipe network flow direction evaluation, and ensures that the flow direction of the drainage pipe network conforms to the actual hydraulic characteristics.

[0010] In an optional embodiment, the plurality of flow direction correction pipes of the drainage pipe network to be identified are obtained, including: The degree and indegree of each inspection well node in the drainage pipe network to be identified are calculated, and the plurality of flow direction correction pipes are determined according to the degree and indegree of each inspection well node.

[0011] The intelligent identification method of the control node of the drainage pipe network provided by the application can avoid the redundant operation of indiscriminately checking all pipes by screening the pipes with possible flow direction errors, and improve the pertinence and efficiency of flow direction correction. Further, the hydraulic state of the drainage pipe network in actual operation can be truly restored by using the drainage process simulation data set for simulation. Further, the flow direction correction is performed by using the drainage process simulation result, which solves the error problem that may exist in the traditional pipe network flow direction evaluation, and ensures that the flow direction of the drainage pipe network conforms to the actual hydraulic characteristics.

[0012] In an optional embodiment, the slope value of the flow energy line of the target drainage pipe network is calculated by taking each inspection well node in the target drainage pipe network as a control node, including: The first maximum flow value of the upstream pipe and the second maximum flow value of the downstream pipe of each control node are calculated by taking each inspection well node in the target drainage pipe network as a control node and using the Manning formula; the first maximum flow value and the second maximum flow value of each control node are iteratively updated based on a preset flow updating relationship until the updated second maximum flow value of each control node is greater than the updated first maximum flow value, and the target maximum flow value of the upstream pipe of each control node is obtained; and the slope value of the flow energy line of the target drainage pipe network is calculated by using the Manning formula based on the target maximum flow value.

[0013] The intelligent identification method of the control node of the drainage pipe network provided by the application can reflect the influence of the hydraulic characteristics of the pipe on the flow by calculating the maximum flow of the upstream and downstream pipes through the Manning formula. Further, the constraint relationship of the flow of the upstream and downstream of the control node is considered in the iterative updating process, which can ensure that the flow value conforms to the water flow distribution logic in the actual pipe network structure, avoid the distortion of the subsequent energy line slope caused by unreasonable flow calculation, and improve the accuracy of the flow data. Further, the slope of the flow energy line is calculated based on the target maximum flow value after the iteration and updating, which can accurately represent the inclined water surface line feature formed by the head difference of the upstream of the control node, and provide a reliable hydraulic slope basis for the calculation of the pipe space capacity of the subsequent pipe, ensuring that the capacity evaluation is consistent with the actual water flow state.

[0014] In an optional implementation, based on the ground elevation and the slope value of each control node, the pipe space capacity of the upstream pipe of each control node is calculated, including: The starting elevation of the flow energy line is calculated based on the ground elevation of each control node; based on the starting elevation and the slope value, the pipe space capacity of each upstream pipe in the flow energy line is calculated and superimposed until the preset superposition condition is met, to obtain the pipe space capacity of the upstream pipe of each control node.

[0015] The intelligent identification method of the control node of the drainage pipe network provided by the application can reflect the influence of the hydraulic characteristics of the pipe on the flow by calculating the maximum flow of the upstream and downstream pipes through the Manning formula. Further, the constraint relationship of the flow of the upstream and downstream of the control node is considered in the iterative updating process, which can ensure that the flow value conforms to the water flow distribution logic in the actual pipe network structure, avoid the distortion of the subsequent energy line slope caused by unreasonable flow calculation, and improve the accuracy of the flow data. Further, the slope of the flow energy line is calculated based on the target maximum flow value after the iteration and updating, which can accurately represent the inclined water surface line feature formed by the head difference of the upstream of the control node, and provide a reliable hydraulic slope basis for the calculation of the pipe space capacity of the subsequent pipe, ensuring that the capacity evaluation is consistent with the actual water flow state.

[0016] In an optional implementation, the total pipe space capacity of the upstream pipes of the plurality of control nodes is taken as an optimization target, and based on the pipe space capacity of each control node, a multi-state dynamic programming method is used for node decision and determination of the target control node, including: The total pipe space capacity of the upstream pipes of the plurality of control nodes is taken as an optimization target, and based on the pipe space capacity of each control node, a multi-state dynamic programming recursive equation is constructed; the multi-state dynamic programming recursive equation is solved by using the multi-state dynamic programming method, to obtain the target control node.

[0017] The application provides a sewer network control node intelligent identification method, which converts control node selection into a multi-stage optimal decision problem by constructing a multi-state dynamic programming recursive equation, and then efficiently solves the problem by a dynamic programming method, so that the selected target control node has relevance and can maximize the use of the pipe network storage space, and minute-level rapid identification is realized. Meanwhile, the relevance between different control nodes and the state change of the controlled pipe are considered, so that the pipe network space utilization degree can be effectively improved under normal and fault conditions.

[0018] In a second aspect, the application provides a sewer network control node intelligent identification device, which comprises: An acquisition module is configured to acquire a sewer process simulation data set of a to-be-identified sewer network; a correction module is configured to correct the flow direction of the to-be-identified sewer network by using a preset sewer process simulation model based on the sewer process simulation data set, so as to obtain a target sewer network after flow direction correction; a first calculation module is configured to take each inspection well node in the target sewer network as a control node and calculate the slope value of the flow energy line of the target sewer network; a second calculation module is configured to calculate the pipe space capacity of the upstream pipe of each control node based on the ground elevation and the slope value of each control node; and a decision determination module is configured to take the total pipe space capacity of the upstream pipes of the plurality of control nodes as an optimization target, use a multi-state dynamic programming method to make node decisions and determine a target control node based on the pipe space capacity of each control node.

[0019] In a third aspect, the application provides a computer device, which comprises a memory and a processor, the memory and the processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the sewer network control node intelligent identification method of the first aspect or any of the corresponding embodiments thereof.

[0020] In a fourth aspect, the application provides a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the sewer network control node intelligent identification method of the first aspect or any of the corresponding embodiments thereof.

[0021] In a fifth aspect, the application provides a computer program product, which comprises computer instructions, and the computer instructions are used to make a computer execute the sewer network control node intelligent identification method of the first aspect or any of the corresponding embodiments thereof. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0023] Figure 1 is a flowchart of a drainage pipe network control node intelligent identification method according to an embodiment of the present application; Figure 2 is a flowchart of another drainage pipe network control node intelligent identification method according to an embodiment of the present application; Figure 3 is a flowchart of still another drainage pipe network control node intelligent identification method according to an embodiment of the present application; Figure 4 is a schematic diagram of optimal control nodes and controlled pipe distribution according to an embodiment of the present application; Figure 5 is a flowchart of a drainage pipe network key control node intelligent identification method based on optimal utilization of storage and regulation space according to an embodiment of the present application; Figure 6 is a corresponding relationship diagram of maximum available drainage pipe network capacity under different control node quantities according to an embodiment of the present application; Figure 7 is a comparison diagram of drainage pipe network space utilization potential under different scenarios of a drainage pipe network key control node intelligent identification method based on optimal utilization of storage and regulation space (DPOCLPS), a graph theory-based method (TBC) and a static space evaluation-based method (CENTAUR_LOC) according to an embodiment of the present application; Figure 8 is a structural block diagram of a drainage pipe network control node intelligent identification device according to an embodiment of the present application; Figure 9 is a hardware structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0025] The embodiment of the present application provides a kind of drainage pipe network control node intelligent identification method, by the space capacity evaluation in the control of inspection well node and the dynamic optimization selection of node in the influence range are corrected, to reach the relevance of ensuring control node selection, improve the calculation efficiency of key control node identification and its applicability in complex drainage scene Effect.

[0026] According to the embodiment of the present application, a drainage pipe network control node intelligent identification method embodiment is provided, it should be noted that the steps shown in the flowchart of the drawing can be executed in a computer system, such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0027] A drainage pipe network control node intelligent identification method is provided in the present embodiment, which can be used in electronic devices, such as computers, mobile phones, tablet computers, etc. Figure 1 The flowchart of the drainage pipe network control node intelligent identification method according to the embodiment of the present application is shown as Figure 1 The flowchart includes the following steps: Step S101, obtaining the drainage process simulation data set of the drainage pipe network to be identified.

[0028] The drainage process simulation data set can include rainfall data, drainage pipe network data, flow or water level monitoring data, and control facility operation data, etc.

[0029] Further, rainfall data is used to reflect information of different precipitation conditions, which is an important input factor affecting the operation state of drainage pipe network; The drainage pipe network data can include the topological structure of the pipe network, the pipe parameters (such as pipe diameter, length, roughness, etc.), inspection well node information (such as elevation, position, etc.), etc.

[0030] Further, the flow or water level monitoring data can be obtained by monitoring equipment, which can include real-time flow, water level change data, etc.

[0031] Further, the control facility operation data can include the operating parameters and state information of pump stations, gates and other control facilities, which can affect the flow movement of the drainage pipe network.

[0032] Step S102, based on the drainage process simulation data set, the flow direction of the drainage pipe network to be identified is corrected by using a predetermined drainage process simulation model, and a target drainage pipe network after flow direction correction is obtained.

[0033] The preset drainage process simulation model is a mathematical model established and calibrated by hydrology and hydraulics principles by integrating rainfall data, pipe network parameters, monitoring records and facility operation information, used to simulate the operation process of the drainage pipe network under different conditions, and output the simulation results of real-time flow, water level change and overflow and other elements in the pipe network.

[0034] Specifically, by obtaining the drainage process simulation data set of the to-be-identified drainage pipe network and using model simulation, the simulation results of real-time flow, water level change and overflow and other elements in the to-be-identified drainage pipe network can be output.

[0035] Further, the flow direction is corrected in combination with the simulation results, solving the error problem that may exist in the traditional pipe network flow direction evaluation, and ensuring that the flow direction of the drainage pipe network conforms to the actual hydraulic characteristics.

[0036] Step S103, taking each inspection well node in the target drainage pipe network as a control node, the slope value of the flow energy line of the target drainage pipe network is calculated.

[0037] The flow energy line represents a tilted water surface line driven by the water head difference from the control node to the upstream under the condition that the control node is not completely closed.

[0038] Specifically, to avoid water accumulation at the control node in the facility failure scenario, the control facility is usually not completely closed. In this case, a tilted water surface line driven by the water head difference will be formed from the control node to the upstream, that is, the flow energy line. At this time, assuming that the water flow is in a stable state, the Manning formula can be used to calculate the slope value of the flow energy line, as shown in the following relationship (1): (1) In the formula, represents the maximum flow of the pipeline; represents the roughness coefficient; represents the cross-sectional area; represents the hydraulic radius; represents the slope.

[0039] Further, by calculating the slope value of the flow energy line of the drainage pipe network, the hydraulic characteristics of the upstream of the control node can be accurately reflected.

[0040] Step S104, based on the ground elevation and slope value of each control node, the pipe space capacity of the upstream pipeline of each control node is calculated.

[0041] The ground elevation of the control node represents the altitude of the ground surface of the inspection well node.

[0042] Further, the pipe space capacity of the upstream pipe of each control node represents the sum of the pipe spaces below the flow energy line in the extension direction of the upstream pipe starting from the control node.

[0043] Specifically, by calculating the pipe space capacity of the upstream pipe of each control node by combining the ground elevation and slope value of each control node, the upstream pipe storage space that can be controlled by each control node can be accurately quantified, and the repetition or omission of capacity evaluation can be avoided.

[0044] In step S105, the total pipe space capacity of the upstream pipes of the plurality of control nodes is taken as the optimization target, and the node decision and determination of the target control node are made by using the multi-state dynamic programming method based on the pipe space capacity of each control node.

[0045] The total pipe space capacity represents the sum of the pipe space capacities corresponding to the upstream pipes of the plurality of control nodes in the drainage pipe network.

[0046] Further, the multi-state dynamic programming method represents a solution method for considering the selection of the optimal control node as a multi-stage optimal decision problem.

[0047] Further, the target control node represents the key control node selected from the inspection well nodes of the drainage pipe network by the multi-state dynamic programming method, which can maximize the total storage space capacity of the upstream pipes.

[0048] Specifically, each selected control node is taken as a stage of decision, the controlled pipe number and the corresponding controlled space capacity are taken as the state of the system, the relevance between the control nodes is taken as the core, different rainfall conditions, conventional and fault complex drainage scenarios are comprehensively considered, and the multi-state dynamic programming method is used for decision-making and determination of the key control node that can maximize the total storage space capacity of the upstream pipes, i.e. the target control node.

[0049] Further, the selection of the control node is converted into a multi-stage optimal decision problem, and the multi-state dynamic programming method is used to ensure that the selected target control node has relevance and can maximize the utilization of the pipe network storage space, so that the minute-level rapid identification is realized, and the adaptability in conventional and fault complex drainage scenarios is strong, which effectively improves the resilience of the urban drainage system.

[0050] The drainage pipe network control node intelligent identification method provided by the embodiment solves the error problem that may exist in traditional pipe network flow direction evaluation, ensures that the drainage pipe network flow direction conforms to the actual hydraulic characteristics. Further, taking each inspection well node in the target drainage pipe network as a control node and calculating the slope value of the flow energy line of the drainage pipe network can accurately reflect the hydraulic characteristics of the upstream of the control node. Further, by combining the ground elevation of each control node and the slope value to calculate the pipe space capacity of the upstream pipe of each control node, the adjustable upstream pipe regulation and storage space of each control node can be accurately quantified, and the repetition or omission of capacity evaluation is avoided. Finally, the control node selection is converted into a multi-stage optimal decision problem, and the multi-state dynamic programming method is used to ensure that the selected target control node has relevance, can maximize the utilization of the pipe network regulation and storage space, realizes minute-level rapid identification, and is suitable for complex drainage scenes such as normal and fault, and effectively improves the resilience of the urban drainage system. Therefore, by implementing the present application, through the space capacity evaluation and control node dynamic optimization selection in the influence range of the inspection well node, the relevance of the control node selection can be ensured, and the calculation efficiency of the key control node identification and its applicability in complex drainage scenes are improved.

[0051] In the embodiment, a drainage pipe network control node intelligent identification method is provided, which can be used for electronic devices such as computers, mobile phones, tablet computers and the like. Figure 2 The flowchart of the drainage pipe network control node intelligent identification method according to the embodiment of the present application is shown in Figure 2 The flowchart of the drainage pipe network control node intelligent identification method according to the embodiment of the present application is shown in Step S201, obtaining a drainage process simulation data set of a drainage pipe network to be identified. For details, please refer to step S101 of the embodiment shown in Figure 1 The embodiment shown in

[0052] Step S202, based on the drainage process simulation data set, using a preset drainage process simulation model to correct the flow direction of the drainage pipe network to be identified, and obtaining a target drainage pipe network after flow direction correction.

[0053] Specifically, the above step S202 includes: Step S2021, obtaining a plurality of flow direction to be corrected pipes of the drainage pipe network to be identified.

[0054] Among them, the flow direction to be corrected pipe represents the connection pipe between the inspection well nodes with equal degree and in-degree in the drainage pipe network, which is selected by calculating the degree and in-degree of the inspection well node.

[0055] In some optional embodiments, the above step S2021 includes: Step a1, calculate the degree and in-degree of each inspection well node in the sewer network to be identified.

[0056] Step a2, determine the multiple flow directions of the pipe to be corrected according to the degree and in-degree of each inspection well node.

[0057] Specifically, an adjacency matrix is constructed to represent the topological relationship between the inspection well node and the sewer pipe As shown in the following relationship (2): (2) Wherein, represents the connection relationship between the inspection well node and , as shown in the following relationship (3): (3) In the formula, represents the set of sewer pipes; represents no connection, represents connection.

[0058] Further, according to the adjacency matrix , the degree and in-degree of each inspection well node in the sewer network to be identified can be calculated, as shown in the following relationships (4) and (5): (4) (5) In the formula, represents an indicator function, which is 1 when the end point of the edge is the node, otherwise 0.

[0059] Further, under the normal drainage logic, there is a specific matching relationship between the degree and the in-degree, when they are equal, the pipe flow direction may exist a situation that needs to be corrected, therefore, the connecting pipe of the inspection well node whose degree and in-degree are equal is screened out and taken as the flow direction of the pipe to be corrected.

[0060] Step S2022, input the drainage process simulation data set into the preset drainage process simulation model to obtain the drainage process simulation result.

[0061] Specifically, according to the description in the above step S102, the obtained drainage process simulation data set is input into the preset drainage process simulation model, which can output the drainage process simulation result containing real-time flow, water level change and overflow in the pipe network and other elements.

[0062] ​Step S2023, correcting the flow directions of the plurality of pipes with the initial flow directions to be corrected by using the simulation result of the drainage process, to obtain a target drainage pipe network with the flow directions corrected.

[0063] Specifically, the hydraulic head of the upstream and downstream nodes of the pipe with the initial flow direction to be corrected in the simulation period can be counted according to the obtained simulation result of the drainage process. The hydraulic head is used to reflect the total mechanical energy of the unit weight fluid.

[0064] Further, the point with the higher hydraulic head is taken as the upstream node, and the flow direction of the pipe is adjusted accordingly, so as to complete the flow direction correction of all the pipes with the initial flow direction to be corrected, and finally obtain the target drainage pipe network with the flow direction conforming to the actual hydraulic characteristics.

[0065] Step S203, taking each inspection well node in the target drainage pipe network as a control node, calculating the slope value of the flow energy line of the target drainage pipe network.

[0066] Specifically, the above step S203 includes: Step S2031, taking each inspection well node in the target drainage pipe network as a control node, calculating the first maximum flow value of the upstream pipe and the second maximum flow value of the downstream pipe of each control node by using the Manning formula.

[0067] Specifically, the initial slope of the drainage pipe network can be obtained in the drainage pipe network data.

[0068] Further, the initial slope of the drainage pipe network is substituted into the Manning formula shown in the above relationship (1) to calculate the first maximum flow value of the upstream pipe and the second maximum flow value of the downstream pipe of each control node.

[0069] Step S2032, based on the preset flow updating relationship, iteratively updating the first maximum flow value and the second maximum flow value of each control node until the updated second maximum flow value of each control node is greater than the updated first maximum flow value, to obtain the target maximum flow value of the upstream pipe of each control node.

[0070] Specifically, for each control node, the maximum flow of the upstream pipe, i.e. the first maximum flow value, can be iteratively updated according to the maximum flow of the upstream and downstream pipes, i.e. the first maximum flow value and the second maximum flow value, as shown in the following relationship (6): (6) In the formula: represents the updated maximum flow of the upstream pipe of the control node; represents the maximum flow of the upstream pipe of the control node, i.e. the first maximum flow value, calculated according to the above relationship (1); The maximum flow of the updated upstream pipeline of each control node can be calculated by using the above relationship (6) iteratively based on the second maximum flow value.

[0071] Further, the above updating process is repeatedly performed, and it is ensured that the maximum flow of the upstream pipeline is always less than or equal to the maximum flow of the downstream pipeline, i.e., when the second maximum flow value of each control node after updating is greater than the first maximum flow value after updating, the iterative updating is stopped, and the target maximum flow value of the upstream pipeline of each control node after updating is obtained.

[0072] Further, for the three special cases of pipeline connection with control facilities, pipeline merging, and pipeline branching, the maximum flow of the upstream pipeline of the control node can be updated by using the following relationships (7) to (9), respectively: (7) (8) (9) In the formula, the sum of the maximum flows of the upstream pipelines of the merging nodes is represented.

[0073] Further, the target maximum flow value of the upstream pipeline of each control node after updating can be obtained by iterative updating.

[0074] In step S2033, the slope value of the flow energy line of the target drainage pipeline network is calculated based on the target maximum flow value by using the Manning formula.

[0075] Specifically, the target maximum flow value of the upstream pipeline of the updated control node after updating is substituted into the Manning formula represented by the above relationship (1), and the slope value of the flow energy line of the target drainage pipeline network can be calculated.

[0076] In step S204, the pipeline space capacity of the upstream pipeline of each control node is calculated based on the ground elevation and the slope value of each control node. For details, please refer to step S104 of the embodiment shown in Figure 1 , which will not be repeated here.

[0077] In step S205, the total pipeline space capacity of the upstream pipelines of the plurality of control nodes is taken as an optimization target, and the target control node is determined by using the multi-state dynamic programming method based on the pipeline space capacity of each control node. For details, please refer to step S105 of the embodiment shown in Figure 1 , which will not be repeated here.

[0078] ​​The intelligent identification method for drainage network control nodes provided in this embodiment calculates the degree and in-degree of each manhole node in the identified drainage network, quantifying the connection relationship between the manhole node and surrounding pipes. Furthermore, based on the calculation results, multiple pipes with potentially ambiguous or erroneous flow directions can be precisely located for correction. This ensures that the initial selection of corrected pipes focuses on key pipes with abnormal topological characteristics, reducing unnecessary correction work and further improving the efficiency and accuracy of flow direction correction. Furthermore, simulations using a drainage process simulation dataset can realistically reproduce the hydraulic state of the drainage network in actual operation. Furthermore, using the drainage process simulation results for flow direction correction resolves potential errors in traditional pipe network flow direction assessment and ensures that the drainage network flow direction conforms to actual hydraulic characteristics. Furthermore, the maximum flow rate of upstream and downstream pipes is calculated using the Manning formula, reflecting the impact of pipe hydraulic characteristics on flow rate. Furthermore, by considering the constraints between upstream and downstream flow rates of control nodes during the iterative update process, the flow value can be ensured to conform to the water distribution logic of the actual pipe network structure, avoiding subsequent energy line slope distortion caused by irrational flow calculation, and improving the accuracy of flow data. Furthermore, by calculating the slope of the flow energy line based on the iteratively updated target maximum flow value, the inclined water surface line characteristics formed by the head difference upstream of the control node can be accurately characterized, providing a reliable hydraulic gradient basis for the subsequent calculation of the pipeline space capacity, ensuring that the capacity assessment is consistent with the actual water flow state.

[0079] In this embodiment, a method for intelligently identifying control nodes in a drainage network is provided, which can be used in electronic devices such as computers, mobile phones, tablet computers, etc. Figure 3 FIG. 1 is a flow chart of a method for intelligently identifying control nodes in a drainage network according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps: Step S301: Obtain a drainage process simulation dataset of the drainage network to be identified. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0080] Step S302: Based on the drainage process simulation data set, the preset drainage process simulation model is used to correct the flow direction of the drainage network to be identified, and a target drainage network with corrected flow direction is obtained. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0081] Step S303: Calculate the slope value of the flow energy line of the target drainage network by taking each inspection well node in the target drainage network as the control node. Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.

[0082] Step S304, based on the ground elevation and slope value of each control node, calculating the pipe space capacity of the upstream pipe of each control node.

[0083] Specifically, the above step S304 includes: Step S3041, calculating the starting elevation of the flow energy line based on the ground elevation of each control node.

[0084] Specifically, the starting elevation of the flow energy line can be the elevation of the ground elevation of each control node minus the safety super-elevation (set to 0.1m).

[0085] Step S3042, based on the starting elevation and slope value, calculating the pipe space capacity of each upstream pipe in the flow energy line and superimposing until the preset superposition condition is met, obtaining the pipe space capacity of the upstream pipe of each control node.

[0086] Specifically, according to the calculated starting elevation, combined with the slope value of the flow energy line calculated in the above step S203, the elevation of the kinetic energy line at the upstream inspection well node can be calculated.

[0087] Further, the pipe space capacity below the flow energy line can be calculated, that is, the controllable capacity of the current pipe section, as shown in the following relationship (10): (10) In the formula: represents the pipe space capacity below the flow energy line of pipe l; represents the water cross-section area.

[0088] Further, the controllable capacity of the upstream pipe is continuously superimposed until the stopping condition is reached, and the pipe space capacity of the upstream pipe of each control node is obtained.

[0089] The stopping condition can include: ① If the flow energy line elevation is less than the well bottom elevation of the inspection well node, the controllable capacity of the current pipe is calculated and the calculation is stopped; ② If the flow energy line elevation is greater than the well bottom elevation of the inspection well node, but less than the ground elevation of the inspection well, the controllable capacity of the current pipe is calculated and searched upstream; ③ If the flow energy line elevation is greater than the ground elevation of the inspection well, the ground elevation of the current inspection well node is taken as the flow energy line elevation, and the search continues upstream.

[0090] Further, the stopping condition can also include: ① There is no upstream inspection well node, that is, the current inspection well node is the starting node; ② The upstream node is a pump station, gate and other control nodes.

[0091] Step S305, based on the pipe space capacity of each control node, uses a multi-state dynamic programming method to make node decisions and determine the target control node with the total pipe space capacity of the upstream pipes of the plurality of control nodes as the optimization target.

[0092] Specifically, the above step S305 includes: Step S3051, based on the pipe space capacity of each control node, constructs a multi-state dynamic programming recursive equation with the total pipe space capacity of the upstream pipes of the plurality of control nodes as the optimization target.

[0093] Specifically, the selection of the optimal control node, i.e., the target control node, can be regarded as a multi-stage optimal decision problem, and each selected control node is a stage of decision making. The controlled pipe number and the corresponding controlled space capacity can be regarded as the state of the system.

[0094] Further, on this basis, a corresponding multi-state dynamic programming recursive equation can be constructed with the total pipe space capacity of the upstream pipes of the plurality of control nodes as the optimization target and in combination with the pipe space capacity of each control node, as shown in the following relationship equation (11): (11) In the formula: denotes the decision variable, i.e., the stage newly added control node; denotes the set of all controlled pipe numbers to stage ; denotes the set of all controlled pipe corresponding controlled space capacities to stage ; denotes the total space capacity of all controlled pipes to stage ; denotes the objective function of the dynamic programming sub-problem, which refers to the controllable pipe capacity increase brought by the stage newly added control node, as shown in the following relationship equation (12): (12) In the formula: denotes the stage pipe controllable pipe capacity increase; denotes the total number of pipes affected by the stage newly added control node; denotes the scenario evaluated by the objective function, which can include a regular scenario or a failure scenario.

[0097] Further, can be determined by the following relationship equations (13) to (17): (13) (14) (15) (16) (17) Where: Representation stage Added control nodes to control pipelines within their affected range Number.

[0099] Furthermore, if the condition is met (i.e. the newly added controlled pipeline is not in the set of current controlled pipelines), then the pipeline The increase in the controllable space capacity is the stage Added control node to pipeline Controllable space capacity; Furthermore, if the conditions are met at the same time and (That is, the newly added controlled pipeline is within the set of currently controlled pipelines, and the newly added control node has a certain effect on the pipeline. The controllable space capacity is smaller than the pipes in the current controlled pipe set. Controllable space capacity), then the pipeline The increase in controllable space capacity is 0; Furthermore, if the conditions are met at the same time and (That is, the newly added controlled pipeline is within the set of currently controlled pipelines, and the newly added control node has a certain effect on the pipeline. The controllable space capacity is greater than the pipe in the current controlled pipe set Controllable space capacity), then the pipeline The increase in controllable space capacity is the increase in the number of new control nodes on the pipeline The controllable space capacity and the pipes in the current controlled pipe set Interpolation in controllable spatial capacity.

[0100] Step S3052: Solve the multi-state dynamic programming recursive equation using a multi-state dynamic programming method to obtain the target control node.

[0101] Specifically, to determine the initial state, you can start from the basic state where no control node is selected (or the first control node is selected) and set the initial (empty set or a set containing a small number of initial pipe numbers), (corresponding to the initial capacity set), (initial total capacity), etc.

[0102] Further, starting from the initial stage, the decision-making calculation is performed for each stage in turn according to the multi-state dynamic programming recursive equation. Specifically, for each possible new control node , its corresponding and are calculated, and the state of the system (the total capacity , ) and the total pipeline space capacity are constantly updated.

[0103] Further, when all possible control node selection stages are traversed (or a preset termination condition is reached, such as all nodes being considered, meeting a specific capacity requirement, etc.), the values obtained at the end of each stage are compared, and the control node selection sequence that maximizes the total pipeline space capacity is selected. The control node (or node combination) determined in the last stage corresponding to the target control node is the optimal control node that can maximize the total pipeline space capacity.

[0104] In some optional embodiments, the optimal control node and the controlled pipeline distribution are as shown in Figure 4 .

[0105] The drainage pipe network control node intelligent identification method provided in this embodiment accurately quantifies the upstream pipeline space capacity that can be controlled by each control node by calculating the upstream pipeline space capacity based on the ground elevation and slope value of the control node and superimposing it to meet the preset condition, ensures the completeness and accuracy of the capacity calculation, clearly defines the calculation boundary of the pipeline space capacity, avoids repetition or omission in capacity evaluation, and provides a scientific quantitative basis for the optimal selection of control nodes. Further, by constructing a multi-state dynamic programming recursive equation, the selection of control nodes is converted into a multi-stage optimal decision-making problem, which is then efficiently solved by a dynamic programming method, ensuring that the target control node has relevance and can maximize the use of pipe network storage space, achieving minute-level rapid identification. At the same time, the relevance between different control nodes and the state changes of the controlled pipelines are considered, which can effectively improve the utilization of pipe network space in both normal and fault scenarios.

[0106] In an example, a drainage pipe network key control node intelligent identification method based on optimal utilization of storage space is provided, which can ensure the linkage of control node selection and improve the calculation efficiency of key control node identification and its applicability in complex drainage scenarios. As shown in Figure 5 , the method specifically includes the following steps: Step 1: Establish a drainage process simulation model to correct the flow direction of the drainage pipe network.

[0107] Firstly, the basic data for establishing the simulation model of the drainage process should include rainfall data, drainage pipe network data, flow or water level monitoring data, and control facility operation data, etc. The model construction process includes integrating rainfall data, pipe network parameters, monitoring records, and facility operation information, establishing a mathematical model based on hydrology and hydraulics principles, and calibrating and verifying. The input is the above basic data, and the output is the simulation results of real-time flow, water level change, and overflow in the pipe network.

[0108] Secondly, the degree and indegree indexes of each inspection well node are calculated using the above formulas (2) to (5), and the connecting pipe of the inspection well node with equal degree and indegree is found as the flow direction of the pipe to be corrected.

[0109] Finally, the drainage process model constructed in the foregoing is run, and the hydraulic head of the upstream and downstream nodes of the flow direction pipe to be corrected in the simulation period is counted, and the point with higher hydraulic head is taken as the upstream node, and the pipe flow direction is corrected accordingly.

[0110] Step 2: Each inspection well node is regarded as a potential control node, and the flow energy line thereof is calculated. To avoid water accumulation at the control node in the facility failure scenario, the control facility is usually not completely closed. In this case, a tilted water surface line driven by the water head difference is formed from the control node to the upstream, which is called the flow energy line. Assuming that the water flow is in a stable state, the Manning formula can be used to calculate the water head of the upstream node of the control node, and the specific calculation expression is shown in the above formula (1).

[0111] Firstly, the maximum flow of the upstream pipe of each inspection well node is calculated based on the above equation.

[0112] Secondly, for each inspection well node, the maximum flow of the upstream pipe thereof is iteratively updated according to the maximum flows of the upstream and downstream pipes thereof, as shown in the above formula (6).

[0113] Further, for the three special cases of pipe connection with control facility, pipe merging, and pipe branching, the maximum flow of the upstream pipe of the inspection well node is updated using the following formulas (7) to (9).

[0114] Finally, the slope J of the flow energy line is calculated by substituting the updated pipe maximum flow into the above formula (1). .

[0115] Step 3: The pipe space capacity in the controllable range of each inspection well node is calculated. The starting elevation of the flow energy line is the elevation of the inspection well ground elevation minus the safety super-elevation (set as 0.1 m), and the slope J of the flow energy line is obtained in Step 2. The pipe space capacity below the flow energy line is calculated, which is the controllable capacity of the current pipe section, and the specific calculation formula is shown in the above formula (10).

[0116] Further, the controllable capacity of the upstream pipeline is continuously superimposed until the stop condition is reached. The basis for judging the superposition or stop of the calculation of the controllable capacity of the pipeline is as follows: ① If the flow energy line elevation is less than the bottom elevation of the inspection well node, the current controllable capacity of the pipeline is calculated and the calculation is stopped; ② If the flow energy line elevation is greater than the bottom elevation of the inspection well node but less than the ground elevation of the inspection well, the current controllable capacity of the pipeline is calculated and searched upstream; ③ If the flow energy line elevation is greater than the ground elevation of the inspection well node, the ground elevation of the current inspection well node is taken as the flow energy line elevation, and the search is continued upstream.

[0117] In addition, the stop condition also includes the following cases: ① There is no upstream inspection well node, i.e., the current inspection well node is the starting node; ② The upstream node is a control node such as a pump station or a gate.

[0118] Step 4, selecting the optimal control node based on the multi-state dynamic programming method. The selection of the optimal control node is regarded as a multi-stage optimal decision problem, and each selected control node is a stage of decision, and the controlled pipeline number and the corresponding controlled space capacity can be regarded as the state of the system. Therefore, the multi-stage optimal decision problem can be solved by using the multi-state dynamic programming method. The multi-state dynamic programming recursive equation of the control node selection problem is constructed, as shown in the above relationship (11).

[0119] The key control node intelligent identification method for optimal utilization of drainage pipe network based on storage space provided in the present example can ensure the relevance of the selection of control nodes through the evaluation of the space capacity within the control range of the inspection well node and the dynamic optimization selection of the control node, and improve the calculation efficiency of the identification of key control nodes and the applicability in complex drainage scenarios.

[0120] In some optional embodiments, as shown in Figure 6 , the corresponding relationship between the maximum available drainage pipe network capacity under different control node numbers is provided.

[0121] Further, Figure 6 The different curves correspond to different analysis cases. According to the analysis results, under the premise that no overflow occurs, the recommended number of control nodes for the A rainwater storage tank area is 7, and the maximum available pipe network space is 1384m 3 ; the recommended number of control nodes for the A combined storage tank area is 7, and the maximum available pipe network space is 2974m 3 ; and the recommended number of control nodes for B is 3, and the maximum available pipe network space is 4781m 3 .

[0122] Further, as shown in Figure 7 the comparison of the drainage network key control node intelligent identification method based on optimal utilization of storage space (DPOCLPS) provided in the present example and the graph-based method (TBC) and the static space evaluation-based method (CENTAUR_LOC) in different scenarios on the space utilization potential of the drainage network.

[0123] Among them, Figure 7 The horizontal coordinate represents different control scenarios. Further, the conventional scenario means that all devices do not fail, and the failure scenario corresponds to the failure of the control facility at any point.

[0124] Further, according to Figure 7 It can be seen that the drainage network key control node intelligent identification method based on optimal utilization of storage space provided in the present example can effectively improve the utilization degree of the network space in the conventional scenario and the failure scenario compared with the existing method.

[0125] In the present embodiment, a drainage network control node intelligent identification device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and is conceived.

[0126] The present embodiment provides a drainage network control node intelligent identification device, as shown in Figure 8 The device comprises: An acquisition module 801 is configured to acquire drainage process simulation data sets of a drainage network to be identified.

[0127] A correction module 802 is configured to correct the flow direction of the drainage network to be identified by using a preset drainage process simulation model based on the drainage process simulation data sets, to obtain a target drainage network after flow direction correction.

[0128] A first calculation module 803 is configured to take each inspection well node in the target drainage network as a control node, and calculate the slope value of the flow energy line of the target flow direction to be corrected pipeline.

[0129] A second calculation module 804 is configured to calculate the pipeline space capacity of the upstream pipeline of each control node based on the ground elevation and the slope value of each control node.

[0130] A decision determination module 805 is configured to take the total pipeline space capacity of the upstream pipeline of a plurality of control nodes as an optimization target, and use a multi-state dynamic programming method to make node decisions and determine the target control node based on the pipeline space capacity of each control node.

[0131] In some optional embodiments, the correction module 802 includes: An acquisition sub-module, configured to acquire a plurality of flow directions of the to-be-identified sewer network.

[0132] An input sub-module, configured to input the sewer process simulation data set into a preset sewer process simulation model to obtain a sewer process simulation result.

[0133] A correction sub-module, configured to correct the flow directions of the plurality of flow directions of the to-be-identified sewer network by using the sewer process simulation result to obtain a target sewer network with corrected flow directions.

[0134] In some optional embodiments, the acquisition sub-module includes: A calculation unit, configured to calculate the degree and indegree of each inspection well node in the to-be-identified sewer network.

[0135] A determination unit, configured to determine the plurality of flow directions of the to-be-identified sewer network according to the degree and indegree of each inspection well node.

[0136] In some optional embodiments, the first calculation module 803 includes: A first calculation sub-module, configured to take each inspection well node in the target sewer network as a control node, and calculate a first maximum flow value of an upstream pipe and a second maximum flow value of a downstream pipe of each control node by using the Manning formula.

[0137] An iterative updating sub-module, configured to iteratively update the first maximum flow value and the second maximum flow value of each control node based on a preset flow updating relationship until the updated second maximum flow value of each control node is greater than the updated first maximum flow value, to obtain a target maximum flow value of the upstream pipe of each control node.

[0138] A second calculation sub-module, configured to calculate a slope value of a flow energy line of the target sewer network by using the Manning formula based on the target maximum flow value.

[0139] In some optional embodiments, the second calculation module 804 includes: A third calculation sub-module, configured to calculate a starting elevation of the flow energy line based on the ground elevation of each control node.

[0140] A superposition calculation sub-module, configured to calculate and superimpose the pipe space capacity of each upstream pipe in the flow energy line based on the starting elevation and the slope value until a preset superposition condition is met, to obtain the pipe space capacity of the upstream pipe of each control node.

[0141] In some optional embodiments, the decision determination module 805 includes: The constructing submodule is configured to construct a multi-state dynamic programming recursive equation based on the pipe space capacity of each control node, with the total pipe space capacity of the upstream pipe of the plurality of control nodes as an optimization target.

[0142] The solving submodule is configured to solve the multi-state dynamic programming recursive equation by using a multi-state dynamic programming method to obtain the target control node.

[0143] Further function descriptions of the above modules and units are the same as those of the corresponding embodiments, and will not be described here.

[0144] The drainage pipe network control node intelligent identification device in the embodiment is in the form of a functional unit, and the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory executing one or more software or fixed programs, and / or other devices capable of providing the above functions.

[0145] The embodiment of the present application also provides a computer device having the above Figure 8 drainage pipe network control node intelligent identification device.

[0146] Please refer to Figure 9 , Figure 9 is a structural schematic diagram of a computer device provided by an optional embodiment of the present application, as shown in Figure 9 The computer device includes one or more processors 10, a memory 20, and an interface for connecting components, including a high-speed interface and a low-speed interface. The components are communicatively connected with each other by using different buses, and can be installed on a common mainboard or in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in the memory or graphics information of the memory to display a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used together with multiple memories if needed. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 9 The processor 10 is taken as an example in the embodiment.

[0147] The processor 10 can be a central processor, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic gate array, a general array logic, or any combination thereof.

[0148] The memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform the methods illustrated by the above embodiments.

[0149] The memory 20 can include a program region and a data region. The program region can store an operating system and application programs required by at least one function. The data region can store data created according to use of the computer device, and the like. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory such as at least one of a magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some alternative embodiments, the memory 20 can optionally include a memory disposed remotely with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0150] The memory 20 can include a volatile memory such as a random access memory, and can further include a non-volatile memory such as a flash memory, a hard disk, or a solid state disk, and can further include a combination of the above-mentioned kinds of memories.

[0151] The computer device further includes a communication interface 30 for communication of the computer device with other devices or communication networks.

[0152] The embodiments of the present application also provide a computer readable storage medium, and the above-mentioned methods according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded to a local storage medium through network downloading of computer code, so that the methods described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, and the like. Further, the storage medium can further include a combination of the above-mentioned kinds of memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods illustrated by the above embodiments are implemented.

[0153] Part of the present application can be applied as a computer program product, for example, computer program instructions, when executed by a computer, through the operation of the computer, can invoke or provide the method and / or technical solutions according to the present application. Those skilled in the art should understand that the form of computer program instructions in computer readable medium includes but is not limited to source files, executable files, installation package files and the like, and accordingly, the way of computer program instructions executed by computer includes but is not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Here, the computer readable medium can be any available computer readable storage medium or communication medium accessible to the computer.

[0154] Although the embodiments of the present application are described in conjunction with the drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A method for intelligently identifying control nodes in a drainage network, characterized in that: The method comprises: Obtain a drainage process simulation data set of the drainage network to be identified; Based on the drainage process simulation data set, a preset drainage process simulation model is used to correct the flow direction of the drainage network to be identified, so as to obtain a target drainage network after flow direction correction; Taking each inspection well node in the target drainage network as a control node, calculating the slope value of the flow energy line of the target drainage network; Calculating the pipeline space capacity of the upstream pipeline of each control node based on the ground elevation of each control node and the slope value; Taking the total pipeline space capacity of the upstream pipelines of multiple control nodes as the optimization target, based on the pipeline space capacity of each control node, a multi-state dynamic programming method is used to make node decisions and determine the target control node.

2. The method according to claim 1, characterized in that Based on the drainage process simulation data set, a preset drainage process simulation model is used to correct the flow direction of the drainage network to be identified to obtain a target drainage network after flow direction correction, including: Acquire multiple pipes whose flow directions are to be corrected of the drainage pipe network to be identified; Inputting the drainage process simulation data set into the preset drainage process simulation model to obtain a drainage process simulation result; The flow directions of the plurality of pipes to be corrected are corrected using the drainage process simulation results to obtain a target drainage pipe network after the flow directions are corrected.

3. The method according to claim 2, characterized in that Acquiring multiple pipes whose flow directions are to be corrected in the drainage network to be identified, including: Calculating the degree and in-degree of each inspection well node in the drainage network to be identified; The plurality of pipelines to be corrected in their flow directions are determined according to the degree and in-degree of each inspection well node.

4. The method according to claim 1, wherein Taking each inspection well node in the target drainage network as a control node, calculating the slope value of the flow energy line of the target drainage network, including: Taking each inspection well node in the target drainage network as a control node, using the Manning formula, calculate the first maximum flow value of the upstream pipeline and the second maximum flow value of the downstream pipeline of each control node; Iteratively updating the first maximum flow value and the second maximum flow value of each control node based on a preset flow update relationship until the updated second maximum flow value of each control node is greater than the updated first maximum flow value, thereby obtaining a target maximum flow value of the upstream pipeline of each control node; Based on the target maximum flow value, the slope value of the flow energy line of the target drainage network is calculated using the Manning formula.

5. The method according to claim 1, characterized in that Calculating the pipeline space capacity of the upstream pipeline of each control node based on the ground elevation of each control node and the slope value, including: Calculating the starting elevation of the flow energy line based on the ground elevation of each control node; Based on the starting elevation and the slope value, the pipeline space capacity of each upstream pipeline in the flow energy line is calculated and superimposed until a preset superposition condition is met, thereby obtaining the pipeline space capacity of the upstream pipeline of each control node.

6. The method according to claim 1, characterized in that Taking the total pipeline space capacity of the upstream pipelines of multiple control nodes as the optimization target, based on the pipeline space capacity of each control node, a multi-state dynamic programming method is used to make node decisions and determine the target control node, including: Taking the total pipeline space capacity of the upstream pipelines of the multiple control nodes as the optimization target, and constructing a multi-state dynamic programming recursive equation based on the pipeline space capacity of each control node; The multi-state dynamic programming recursive equation is solved using the multi-state dynamic programming method to obtain the target control node.

7. A drainage network control node intelligent identification device, characterized in that: The device comprises: An acquisition module, used for acquiring a drainage process simulation data set of the drainage network to be identified; a correction module, configured to correct the flow direction of the drainage network to be identified based on the drainage process simulation data set and using a preset drainage process simulation model to obtain a target drainage network after flow direction correction; A first calculation module is configured to calculate the slope value of the flow energy line of the target drainage network by taking each inspection well node in the target drainage network as a control node; A second calculation module is configured to calculate the pipeline space capacity of the upstream pipeline of each control node based on the ground elevation of each control node and the slope value; The decision determination module is used to take the total pipeline space capacity of the upstream pipelines of multiple control nodes as the optimization target, and based on the pipeline space capacity of each control node, use a multi-state dynamic programming method to make node decisions and determine the target control node.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the drainage network control node intelligent identification method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the drainage network control node intelligent identification method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for intelligently identifying control nodes of a drainage network according to any one of claims 1 to 6.

Images