Cascade pump station group optimization operation scheme recommendation method based on knowledge graph and one-dimensional hydraulic model

Abstract

The invention discloses a cascade pump station group optimization operation scheme recommendation method based on a knowledge graph and a one-dimensional hydraulic model, and the method comprises the steps: constructing an operation scheme knowledge graph of each single pump station of a cascade pump station group; constructing a one-dimensional non-constant flow calculation model of the water delivery channel between the cascade pump station groups; constructing a pump station operation scheme query sub-graph, and according to the operation scheme knowledge graph, performing weighting and sorting on scheme entities corresponding to the pump station operation scheme query sub-graph to obtain a plurality of pump station optimized operation schemes so as to construct an optimized operation scheme library of each stage of pump station; constructing a cascade pump station group optimization operation scheme library, and calculating the flow and water level hydrograph of each section of the water delivery river channel under each scheme; and comparing and screening the schemes in the cascade pump station group optimization operation scheme library from multiple aspects to obtain an optimal cascade pump station group optimization operation scheme. According to the method, the cascade pump station group scheduling decision-making capability can be improved in an auxiliary manner, and the feasibility of the knowledge graph in cascade pump station group scheduling is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of optimized operation schemes for cascade pump station groups, and in particular to a method for recommending optimized operation schemes for cascade pump station groups based on a knowledge graph and a one-dimensional hydraulic model. Background Art

[0002] The optimized operation of cascade pump station groups is one of the important measures to ensure the safety of water supply systems and improve the benefits and service levels of water conservancy projects. The optimization of the operation plan of cascade pump station groups aims to improve the water supply efficiency of pump stations, reduce energy consumption and costs, and enhance system stability and reliability. At the same time, the plan can realize intelligent management, improve the overall operation effect and service level of the water supply system, and promote the sustainable use of water resources. Knowledge graph is an emerging research method that combines technologies and theories from multiple fields such as statistics, information science, semantic analysis and intelligent recognition. The one-dimensional hydraulic model is a mathematical model used to simulate the flow and hydraulic characteristics of water in one-dimensional space. In the recommendation of the optimized operation plan of cascade pump station groups, knowledge graphs and one-dimensional hydraulic models play an important role. In the recommendation of the optimized operation plan of cascade pump station groups, they can serve the system monitoring and data analysis, the establishment of optimization models, intelligent control and scheduling, fault detection and maintenance, risk warning and response, etc.

[0003] At present, the optimization scheduling method for cascade pump station groups is to use mathematical models such as linear programming and integer programming to establish a mathematical model of the pump station group scheduling problem). At the same time, based on experience and heuristic rules, a series of algorithms are designed to solve the optimization scheduling problem of the pump station group. The mathematical model of the water supply system is established using historical data and real-time data, and the control strategy is optimized in combination with the prediction model. Considering multiple target indicators, such as energy consumption, water supply stability, equipment life, etc., a multi-objective optimization model is established. Through the multi-objective optimization algorithm, a series of Pareto optimal solution sets are obtained for decision makers to choose the most appropriate solution. However, the existing scheduling model is too idealistic, does not conform to the actual situation, and has poor operability, resulting in low scheduling decision-making ability for cascade pump station groups.

[0004] The existing optimization operation and scheduling model for cascade pump station groups is a single-objective system with the objective function of "minimum operating cost within the scheduling cycle", without considering the effects of unit operation stability (such as pressure pulsation, vibration, spindle swing, etc.) and maintenance costs (number of unit starts and stops). The existing optimization operation and scheduling model for cascade pump station groups is designed according to the theoretical state of the pump station units during the engineering design phase, without considering the effects of actual parameter changes such as the units and the river channel during the operation of the pump station, resulting in the scheduling model losing its effective target and the optimization results seriously deviating from the optimal working conditions. The existing optimization operation and scheduling model for cascade pump station groups is too idealistic in theory, with too detailed time divisions, and the optimization results require frequent angle changes and frequent starts and stops, without considering actual operability, the impact on the stability of equipment units, and the investment in manpower and material maintenance costs. Summary of the invention

[0005] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0006] To this end, the present invention proposes a method for recommending optimized operation plans for cascade pump station groups based on a knowledge graph and a one-dimensional hydraulic model. In view of the problems existing in the above-mentioned prior art, such as single optimization target, over-idealization, poor operability, failure to consider changes in actual operating parameters, and failure to consider the impact of unit operating stability and maintenance costs, the collected historical operation plans of the pump stations are used to construct a knowledge graph of pump station operation plans, and the similarity matching method is used to find cases that are relatively similar to the current operating conditions, thereby generating the best operation plan that adapts to the actual situation.

[0007] Another object of the present invention is to propose a system for recommending optimal operation plans for cascade pump station groups based on knowledge graphs and one-dimensional hydraulic models.

[0008] To achieve the above-mentioned purpose, the present invention proposes, on one hand, a method for recommending an optimal operation plan for a cascade pump station group based on a knowledge graph and a one-dimensional hydraulic model, comprising:

[0009] The knowledge graph of operation plans of each single pumping station in the cascade pumping station group is constructed through the historical operation related information of the single pumping station;

[0010] Based on the river network generalization diagram between cascade pumping stations and Saint-Venant equations, a one-dimensional unsteady flow calculation model for the water conveyance channel between cascade pumping stations is constructed.

[0011] Based on the real-time operation related information of pump stations at all levels, a pump station operation plan query subgraph is constructed, and according to the operation plan knowledge graph, the plan entities corresponding to the pump station operation plan query subgraph are weighted and sorted to obtain multiple pump station optimization operation plans, so as to construct an optimization operation plan library for pump stations at all levels;

[0012] Based on the optimization operation solution library of each level of pumping stations, a cascade pumping station group optimization operation solution library is constructed, and the solutions in the cascade pumping station group optimization operation solution library are used as the upstream and downstream flow boundaries of the one-dimensional non-steady flow calculation model to respectively calculate the flow and water level process lines of each section of the water conveyance channel under each solution;

[0013] Based on the flow and water level process lines of each section of the water conveyance channel, the schemes in the cascade pump station group optimization operation scheme library are compared and screened from multiple aspects to obtain the optimal cascade pump station group optimization operation scheme.

[0014] The method for recommending an optimal operation plan for a cascade pump station group based on a knowledge graph and a one-dimensional hydraulic model in an embodiment of the present invention may also have the following additional technical features:

[0015] In one embodiment of the present invention, the multiple aspects include the head matching degree of the cascade pump station group, the optimized operation economy of the cascade pump station system, the water level fluctuation of the inter-stage water transfer channel, and the flood control, drainage, navigation and ecological water level requirements of the water transfer channel.

[0016] In one embodiment of the present invention, a knowledge graph of operation plans of each single pumping station in a cascade pumping station group is constructed based on historical operation related information of the single pumping station, including:

[0017] Decompose the cascade pump station group into multiple single pump stations, and obtain historical operation related information of each single pump station; wherein the historical operation related information includes basic information of the pump station and operation plan information;

[0018] Based on the basic information of the pumping station and the operation plan information, relevant concepts of the pumping station operation are obtained, the relevant concepts are split into multiple sub-concepts, and a single concept ontology model of the pumping station operation is constructed based on the ontology language;

[0019] Building a domain ontology model of pump station operation based on the single concept ontology model, integrating preset semantic rules into the domain ontology model to build a pattern layer of the pump station operation knowledge graph; and,

[0020] A pump station historical operation plan library is constructed based on the operation plan information, and knowledge is extracted from the plans in the pump station historical operation plan library to obtain triple data to construct a data layer of the pump station operation knowledge graph, so as to construct a pump station operation knowledge graph.

[0021] In one embodiment of the present invention, a one-dimensional unsteady flow calculation model of a water channel between cascade pumping station groups is constructed based on a generalized diagram of a river network between cascade pumping station groups and Saint-Venant equations, including:

[0022] Based on the basic data of the water supply channel between every two pumping stations in the cascade pumping station group and the water use status information of water users along the inter-stage water supply channel, a generalized river network map of the main and tributary rivers and water outlets is constructed;

[0023] A one-dimensional unsteady flow calculation model for an interstage water transfer channel is constructed based on the Saint-Venant equations and the generalized diagram of the river network.

[0024] In one embodiment of the present invention, a pump station operation plan query subgraph is constructed based on the real-time operation related information of pump stations at all levels, and the plan entities corresponding to the pump station operation plan query subgraph are weighted and sorted according to the operation plan knowledge graph to obtain multiple pump station optimization operation plans, so as to construct an optimization operation plan library for pump stations at all levels, including:

[0025] Constructing a pump station operation plan query subgraph based on the real-time operation related information of each single pump station in the cascade pump station group; wherein the real-time operation related information includes basic performance parameters of the water pump, scheduling objectives and operating conditions;

[0026] Retrieving a subgraph having a similar scheduling target in the operation plan knowledge graph based on the pump station operation plan query subgraph;

[0027] Calculating entity similarities and entity node weights in the subgraphs respectively, and calculating subgraph similarity based on the entity similarities and entity node weights;

[0028] Searching for operation plans corresponding to similar cases based on the subgraph similarity, and assigning the similarity corresponding to each historical case to each associated operation plan to obtain an alternative plan;

[0029] The recommendation degree of the alternative schemes is adjusted to obtain the recommended scheme priority, and multiple recommended schemes for pump stations at all levels are selected according to the sorting results of the scheme priorities to form an optimized operation scheme library for pump stations at all levels.

[0030] In one embodiment of the present invention, a cascade pump station group optimization operation solution library is constructed based on the optimization operation solution library of the pump stations at each level, and the solutions in the cascade pump station group optimization operation solution library are used as the upstream and downstream flow boundaries of the one-dimensional unsteady flow calculation model to calculate the flow and water level process lines of each section of the water conveyance channel under each solution, including:

[0031] The schemes in the optimization operation scheme library of pumping stations at all levels are combined to construct the optimization operation scheme library of cascade pumping station groups;

[0032] Inputting the upstream and downstream flow boundary conditions of the inter-stage water conveyance channel obtained based on the optimized operation scheme library of the cascade pump station group into the Saint-Venant equations, and constructing a nonlinear equation group of the river channel with a cross section according to the initial flow and initial water level of the river channel;

[0033] The nonlinear equations are solved by the chasing method, and the flow process lines and water level process lines of each section of the inter-stage water transfer channel under each scheme in the optimal operation scheme library of the cascade pump station group are obtained according to the solution results.

[0034] In one embodiment of the present invention, based on the flow rate and water level process line of each section of the water conveyance channel, the schemes in the cascade pump station group optimization operation scheme library are compared and screened from multiple aspects to obtain the optimal pump station group optimization operation scheme, including:

[0035] The water level fluctuations above and below the pump stations at each level under each operation scheme are calculated respectively, and the water level fluctuations above and below the pump stations under each operation scheme are analyzed and compared to obtain the head matching analysis results of the cascade pump station group;

[0036] The minimum unit water extraction cost of each pumping station under each operation scheme, using a fixed angle and constant speed operation, and the minimum unit water extraction cost under an optimized operation scheme are calculated to obtain the total savings of the cascade pumping station group, and the total savings under each operation scheme are analyzed and compared to obtain the results of the economic analysis of the optimized operation of the cascade pumping station system;

[0037] Calculate the water level fluctuation of the inter-stage water conveyance channel under each operation scheme for each pump station respectively, and compare and analyze the water level fluctuation under each operation scheme to obtain the analysis result of the water level fluctuation of the inter-stage water conveyance channel;

[0038] According to the non-steady flow simulation results of the water channel, analyze whether the water level and water level fluctuation of the river channel under each operation scheme can meet the requirements of flood control and drainage, navigation and ecological water level in each period, so as to obtain the analysis results of the water channel requirements;

[0039] The optimal operation plan for the cascade pump station group is obtained based on the head matching analysis results of the cascade pump station group, the economic analysis results of the optimized operation of the cascade pump station system, the water level fluctuation analysis results of the inter-stage water transfer channel and the water transfer channel requirement analysis results.

[0040] To achieve the above-mentioned purpose, the present invention proposes, on the other hand, a system for recommending optimal operation plans for cascade pump station groups based on a knowledge graph and a one-dimensional hydraulic model, comprising:

[0041] The pump station operation knowledge graph construction module is used to construct the operation plan knowledge graph of each single pump station in the cascade pump station group based on the historical operation related information of the single pump station;

[0042] The module for constructing the non-steady flow model of the inter-stage water channel is used to construct the one-dimensional non-steady flow calculation model of the water channel between the cascade pumping station groups based on the generalized diagram of the river network between the cascade pumping station groups and the Saint-Venant equations;

[0043] The pump station optimization operation plan recommendation module based on the knowledge graph is used to construct a pump station operation plan query subgraph based on the real-time operation related information of pump stations at all levels, and weight and sort the plan entities corresponding to the pump station operation plan query subgraph according to the operation plan knowledge graph to obtain multiple pump station optimization operation plans, so as to construct an optimization operation plan library for pump stations at all levels;

[0044] The non-steady flow simulation calculation module of the inter-stage water conveyance channel is used to construct an optimal operation solution library for the cascade pump station group based on the optimal operation solution library for the pump stations at each level, and use the solutions in the optimal operation solution library for the cascade pump station group as the upstream and downstream flow boundaries of the one-dimensional non-steady flow calculation model to respectively calculate the flow and water level process lines of each section of the water conveyance channel under each solution;

[0045] The module for comprehensively comparing and selecting the optimal operation schemes of the cascade pump station groups is used to compare and select the schemes in the optimal operation scheme library of the cascade pump station groups from multiple aspects based on the flow and water level process lines of each section of the water conveyance river, so as to obtain the optimal optimal operation scheme of the cascade pump station groups.

[0046] The method and system for recommending optimized operation plans for cascade pump station groups based on knowledge graph and one-dimensional hydraulic model in the embodiment of the present invention integrates a one-dimensional hydraulic model to ensure the head matching and water level requirements between pump stations at each level in view of the operation and scheduling characteristics of cascade pump stations. The knowledge graph technology is also used to recommend the best operation plan from the historical operation plans of the pump stations, avoiding the shortcomings of existing scheduling models such as being too idealistic, not in line with actual conditions, and having poor operability, thereby achieving effective matching of plans.

[0047] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0049] Figure 1 is a flow chart of a method for recommending an optimal operation plan for a cascade pump station group based on a knowledge graph and a one-dimensional hydraulic model according to an embodiment of the present invention;

[0050] Figure 2 It is an architecture diagram of a method for recommending an optimal operation plan for a cascade pump station group based on a knowledge graph and a one-dimensional hydraulic model according to an embodiment of the present invention;

[0051] Figure 3 It is a structural diagram of a system for recommending optimal operation plans for cascade pump station groups based on a knowledge graph and a one-dimensional hydraulic model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0053] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0054] The following describes a method and system for recommending an optimal operation plan for a cascade pump station group based on a knowledge graph and a one-dimensional hydraulic model according to an embodiment of the present invention with reference to the accompanying drawings.

[0055] Figure 2 The schematic diagram of the method for recommending the optimal operation scheme of a cascade pump station group based on a knowledge graph and a one-dimensional hydraulic model according to an embodiment of the present invention is shown in the figure. The cascade pump station group is decomposed into multiple single pump stations, and the knowledge graph of the operation scheme of each single pump station is constructed through the existing basic information related to the operation of each single pump station. The river network between the cascade pump station groups is generalized, and based on the Saint-Venant equations, the characteristic parameters of the river channel and the water users along the line are combined to preliminarily construct a one-dimensional non-steady flow calculation model for the water supply channel between the cascade pump station groups. According to the basic information, scheduling objectives, and operating conditions of the pump stations at all levels, a pump station operation scheme query subgraph is formed, and the scheme entities corresponding to the subgraph are weighted and sorted based on the similarity matching method, and multiple pump station optimization operation schemes are recommended to construct the optimization operation scheme library for each pump station. The optimization operation schemes of the pump stations at all levels are combined to construct the optimization operation scheme library for the cascade pump station group, and the schemes in the library are used as the upstream and downstream flow boundaries of the one-dimensional non-steady flow calculation model, and the flow and water level process lines of each section of the water supply channel under each scheme are calculated respectively. The schemes in the cascade pump station group optimization operation scheme library are comprehensively compared from the aspects of head matching, optimized operation economy, water level fluctuation of inter-stage water delivery channel, flood control and drainage, navigation, and ecological water level requirements, and the optimal pump station group optimization operation scheme is given. Figure 2 shown.

[0056] Figure 1 It is a flow chart of a method for recommending an optimal operation plan for a cascade pump station group based on a knowledge graph and a one-dimensional hydraulic model according to an embodiment of the present invention.

[0057] like Figure 1 As shown, the method includes but is not limited to the following steps:

[0058] S1, construct the knowledge graph of the operation plan of each single pumping station in the cascade pumping station group through the historical operation related information of the single pumping station.

[0059] Specifically, step S1 includes the following steps:

[0060] S11, the present invention is mainly applied to a cascade pump station group with multiple single pump stations connected in series. The cascade pump station group is decomposed into multiple single pump stations, and the basic information (unit quantity, unit model, design flow, design head, rated power, etc.) and operation plan information (such as target water lifting volume, initial head, unit blade placement angle, flow, efficiency, power, etc. in each time period) of each single pump station are collected. According to the collected basic information and operation plan information, the relevant concepts of pump station operation are sorted out and summarized, including: the overall hydraulic characteristics of the pump station group, the independent operation characteristics of a single pump station, the concept of joint operation planning, the concept of stability and safety, and the concept of economy.

[0061] S12, split the related concepts of pump station operation into sub-concepts such as scheduling objectives, initial working conditions, and operation plans. For each sub-concept, use the class (Class) and subclass (Subclass) in the ontology language OWL to establish the conceptual superior-subordinate relationship, use data types (Datatypes) and data properties (Data Properties) to complete the description of the concept attributes, and use object properties (Object Properties) to complete the description of the internal relationship of the concept, and build a single concept ontology model of pump station operation.

[0062] S13, using each pump station ontology as a bridge, connects each single concept ontology of pump station operation to complete the construction of the domain ontology model of pump station operation. The single ontology model can be associated with the object property (class-object property-class) expression method. Object properties can effectively express the semantic relationship within a single concept and between multiple concepts, and realize the description of the interaction relationship between concepts and instances in the domain. By analyzing the interaction relationship between concepts, semantically related concepts are selected and the role direction of object properties is determined, thereby establishing accurate semantic associations between concepts:

[0063] T0=(HeadEntity,ObjectProperties,TailEntity)

[0064] Among them, T0 is a triple constructed by object properties, HeadEntity is the head entity of the triple, ObjectProperties is the attribute object of the triple, and TailEntity is the tail entity of the triple.

[0065] S14, analyze and extract the experience knowledge of experts and pump station operation and control personnel and the operation rules in the relevant specifications of the pump station, express them using if-then conditional statements, and convert them into SWRL rules. Finally, the constructed SWRL semantic rules are verified using the protégé reasoning module, and after being correct, they are integrated into the ontology model to expand and enrich the knowledge graph model layer of the pump station operation.

[0066] S15, based on the operation plan information collected in step S11, build a historical operation plan library for the pump station, use the BiLSTM+CRF neural network to extract knowledge from the historical plans, and obtain triple data to build the data layer of the pump station operation knowledge graph, and use the R2RML mapping method to convert the structured data into RDF format, so as to store the triple data in the knowledge graph.

[0067] S16, using a method based on entity attribute similarity calculation to identify ambiguous entities in the knowledge graph, merging entities whose judgment results point to the same object, realizing knowledge fusion and improving knowledge quality. The formula for calculating the phase velocity of entity attributes is:

[0068]

[0069] Among them, e i ,e j are the attributes of the entity to be evaluated; m and n are the number of attributes of the entity to be evaluated; lev is the edit distance calculation formula, which is used to calculate the text similarity of entity attributes. When the sum of the similarities of two entity attributes is greater than the set threshold, the two entities are considered to be the same, otherwise they are considered to be different entities.

[0070] S17, select Neo4j graph database as the storage and visualization tool of the knowledge graph, and based on the RDF triple format obtained in step S15, construct the mapping rules between RDF and the graph structure (Node, Relation, Node, Property) in Neo4j to realize the storage mapping of the knowledge graph.

[0071] S2, based on the river network generalization diagram between cascade pumping station groups and the Saint-Venant equations, a one-dimensional unsteady flow calculation model for the water transfer channel between cascade pumping station groups is constructed.

[0072] Specifically, step S2 includes the following steps:

[0073] S21, generalize the water channels between every two pumping stations in the cascade pumping station group. Collect basic information on the water channels (channel length, bottom width, riverbed elevation, slope, cross-section shape, roughness, etc.), clarify the water use of water users along the inter-level water channels (agricultural water users, industrial water users, lock water users, etc.), and construct a generalized river network with clear main and tributary rivers and water outlets.

[0074] S22, based on the Saint-Venant equations and the river network generalization diagram obtained in step S21, a one-dimensional unsteady flow calculation model of the inter-stage water transfer channel is preliminarily constructed. The Saint-Venant equations are used to describe the water flow movement in the river network:

[0075]

[0076] Among them, Z is the water level, Q is the flow rate, B is the water surface width, A is the cross-sectional area of ​​the water flow, R is the hydraulic radius, C is the Xie Cai coefficient, q is the lateral inflow per unit length of the river, and t and s are the time and space coordinates respectively.

[0077] S23, Preissmann's four-point implicit difference format is used to discretize the Saint-Venant equations. The discretization format is as follows:

[0078]

[0079] Among them, n is the divided calculation period, j is the divided calculation section, C j , D j 、E j 、F j , G j ,φ j It is a function of water level Z and flow rate Q (including initial value of iteration):

[0080]

[0081] Where Δx j is the interval between the divided river sections, Δt is the calculation time step, θ is the weight of the Preissmann implicit format, α is the kinetic energy correction coefficient, u is the cross-sectional flow velocity, and g is the gravitational acceleration.

[0082] Therefore, for a river channel with L sections, 2(L-1) nonlinear equations about Z and Q can be formed.

[0083] S24, for the confluence of rivers and the sections where water users are located along the river, the model needs to be processed with internal boundaries. For the confluence of rivers, assuming that rivers A and B converge at point P and then merge into river C, according to the water balance and water level continuity at point P, there should be:

[0084]

[0085] For the sections where water users are located along the line, they can be treated as the inner boundary of the concentrated lateral inflow and outflow. Assume that there is a concentrated inflow Q at the jth section. 集 According to the water balance and water level continuity of the jth section, we should have:

[0086]

[0087] S3, construct a pump station operation plan query subgraph based on the real-time operation related information of each level of pump stations, and weight and sort the plan entities corresponding to the pump station operation plan query subgraph according to the operation plan knowledge graph to obtain multiple pump station optimized operation plans, so as to construct an optimized operation plan library for each level of pump stations.

[0088] Specifically, step S3 includes the following steps:

[0089] S31, for each single pump station in the cascade pump station group, a pump station operation plan query subgraph is formed according to its basic information (basic performance parameters of the water pump), scheduling target (target water lifting volume of each level of pump station), operating conditions (initial head, water lifting load), etc.

[0090] S32, retrieve a subgraph with similar scheduling objectives in the pump station operation knowledge graph composed of historical scheduling operation cases.

[0091] S33, respectively calculating the entity similarity and entity node weight in the subgraph, and then calculating the subgraph similarity based on the entity similarity and node weight. The calculation formula of entity similarity is:

[0092]

[0093] Among them, Sim i Indicates the query subgraph i-th entity A i Entity B that belongs to the same entity class in a historical operation plan subgraph i If one of the two subgraphs lacks this type of entity, then Sim i =0. Represents the entity vectors of the same entity class in two subgraphs. ij 、b ij They represent the values ​​of the same attributes in the entities of the same entity class in the two subgraphs, where n and j represent the total number of attributes contained in the entity and the jth attribute, respectively. i ,B i ) represents the similarity weights between attribute sequences of entities with different degrees of missing values, which is used to solve the problem that the engineering entities in the literature reports may have some missing attribute values, which affects the similarity calculation. i , B i When the attributes of are empty, J(A i ,B i )=1.

[0094] The calculation formula for node weight and subgraph similarity is:

[0095]

[0096] Among them, α i Indicates the query subgraph i-th entity A i Node weight. Even if the scheduling target is the same, the final operation plan will be very different due to the changes in the basic performance parameters of the pump and the different operating conditions. In the case subgraph, the higher the frequency of the relationship between a certain type of entity pointing to the scheduling target "Target", the greater the relationship between the entity and the realization of the scheduling target.i represents the frequency of the "Target" relationship of the ith entity class of the case subgraph, and m represents the number of entity classes related to the scheduling target. S represents the similarity between the query subgraph and a historical operation scheme subgraph. k represents the number of entity types in the pump station operation knowledge graph structure that are related to the scheduling target and describe the pump station operation characteristics.

[0097] S34, recommending pump station operation plans based on the subgraph similarity calculated in step S33. Finding the operation plans corresponding to similar cases based on the triple query, assigning the similarity corresponding to each historical case to each operation plan associated with it, and performing an initial recommendation Q on each operation plan. k Calculation:

[0098]

[0099] Among them, Q k Represents the initial recommendation degree of the kth solution. represents the recommendation value of the kth solution. If the kth solution exists in the ith historical case subgraph, the similarity between the subgraph and the query subgraph is used as the recommendation value of the solution. If it does not exist, Press Q k Sort the values ​​from high to low to select multiple options as alternatives.

[0100] S35, adjust the recommendation degree of the alternative solution obtained in step S34 to obtain the final recommendation degree. Since the alternative solution is the result of searching among all similar cases, it cannot fully reflect the priority of the solution among all alternative solutions. Therefore, it is necessary to find the case subgraph associated with the alternative solution and adjust the recommendation priority. The adjustment formula is:

[0101]

[0102] Among them, S i is the similarity of the i-th subgraph, φ(k) represents the set of case subgraphs that contain the k-th solution, and W k Indicates the priority of the recommended solution.

[0103] For each level of pumping station, according to W k The results are sorted from high to low and multiple recommended solutions are selected to form an optimized operation solution library for each pumping station.

[0104] S4, constructing an optimal operation scheme library for cascade pump station groups based on the optimal operation scheme library for each level of pump stations, and using the schemes in the optimal operation scheme library for cascade pump station groups as the upstream and downstream flow boundaries of the one-dimensional non-steady flow calculation model to respectively calculate the flow and water level process lines of each section of the water conveyance channel under each scheme.

[0105] Specifically, step S4 includes the following steps:

[0106] S41, combines the plans in the optimization operation plan library of pump stations at all levels to construct the optimization operation plan library of the cascade pump station group, that is, the various time periods corresponding to the water lifting load and water lifting head, the number of started units of each pump station, the blade angle of the started water pump and the unit speed, flow rate, water lifting volume, and the corresponding operation cost of the pump station group.

[0107] S42, according to the optimized operation plan of the cascade pump station group in step S41, the upstream and downstream flow boundary conditions of the inter-stage water transfer channel can be obtained, and substituted into the Saint-Venant equations in discrete format in step S23. Combined with the initial flow and initial water level of the river channel, 2L nonlinear equations about Z and Q can be formed for a river channel with L sections.

[0108] S43, using the chasing method to solve the nonlinear equations obtained in step S42. For the case where the flow boundary conditions are known, As parameter variables, the difference equations in step S23 can be written as the following pursuit equations:

[0109]

[0110] The catch-up coefficient is:

[0111]

[0112] The specific solution is: Known, will As a parameter variable, proceed from the upstream boundary to the downstream boundary and find and Downstream Boundary Known, by and The recursive relationship can be obtained Then substitute back from the downstream boundary to the upstream boundary to calculate the water level Z and flow Q of each section in each time period.

[0113] In this way, the flow process line and water level process line of each section of the inter-level water transfer channel under each scheme in the scheme library can be obtained.

[0114] S5, based on the flow and water level process lines of each section of the water conveyance channel, compare and screen the solutions in the cascade pump station group optimization operation solution library from multiple aspects to obtain the optimal cascade pump station group optimization operation solution.

[0115] Specifically, step S5 includes the following steps:

[0116] S51, based on the optimized operation scheme library of the cascade pump station group obtained in step S4, and the flow process lines and water level process lines of each section of the inter-stage water transfer channel under each scheme, each scheme is calculated and analyzed from four aspects: head matching degree, optimized operation economy, water level fluctuation of the inter-stage water transfer channel, flood control and drainage, navigation, and ecological water level requirements:

[0117] 1) Analysis of head matching of cascade pumping stations: Calculate the water level fluctuation above and below the pumping stations under each operation scheme respectively, and compare the scheme with smaller water level fluctuation above and below the pumping station, which will have a higher matching degree with the established head during the optimized operation process.

[0118] 2) Analysis of the economic efficiency of optimized operation of cascade pumping station system: Calculate the minimum unit water lifting cost of each pumping station under each operation scheme, using fixed-angle constant speed operation and the minimum unit water lifting cost under the optimized operation scheme, and obtain the total savings of the cascade pumping station group. Compare which scheme has the smaller total savings, and the optimized operation economy of the pumping station system under this scheme is higher.

[0119] 3) Analysis of water level fluctuations in inter-stage water transfer channels: Calculate the water level fluctuations in the inter-stage water transfer channels for each pump station under each operation scheme, and compare which scheme has the smaller water level fluctuation. The water level changes in the water transfer channels under this scheme will be relatively more stable.

[0120] 4) Analysis of flood control, drainage, navigation and ecological water level requirements of water conveyance channels: Based on the non-steady flow simulation results of water conveyance channels, analyze whether the water level and water level fluctuation of the channel under each operation scheme can meet the requirements of flood control, drainage, navigation and ecological water level in each period. For the optimization scheme that meets the requirements, the scheme with the smallest water level fluctuation can be selected.

[0121] S52, comprehensively comparing and selecting the four aspects in step S51, and providing the best solution for optimizing the operation of the cascade pump station group.

[0122] According to the method for recommending optimized operation plans for cascade pump station groups based on knowledge graphs and one-dimensional hydraulic models according to an embodiment of the present invention, the collected historical operation plans of pump stations are used to construct a knowledge graph of pump station operation plans, and the cases that are relatively similar to the current working conditions are found through the similarity matching method, so as to generate the best operation plan that adapts to the actual situation, and integrate the one-dimensional hydraulic model to ensure the head matching degree and water level requirements between pump stations at all levels according to the operation and scheduling characteristics of cascade pump stations. The knowledge graph technology is also used to recommend the best operation plan from the historical operation plans of the pump stations, avoiding the shortcomings of the existing scheduling model that is too idealistic, inconsistent with the actual situation, and poor operability, which can assist in improving the scheduling decision-making ability of the cascade pump station group and enhance the feasibility of the knowledge graph in the scheduling of the cascade pump station group.

[0123] In order to implement the above embodiment, Figure 3 As shown, this embodiment also provides a cascade pump station group optimization operation plan recommendation system 10 based on knowledge graph and one-dimensional hydraulic model, the system 10 includes a pump station operation knowledge graph construction module 100, an inter-stage water channel non-constant flow model construction module 200, a pump station optimization operation plan recommendation module 300 based on knowledge graph, an inter-stage water channel non-constant flow simulation calculation module 400 and a cascade pump station group optimization operation plan comprehensive comparison module 500;

[0124] A pump station operation knowledge graph construction module 100 is used to construct an operation plan knowledge graph of each single pump station in a cascade pump station group based on historical operation related information of the single pump station;

[0125] The inter-stage water channel non-steady flow model construction module 200 is used to construct a one-dimensional non-steady flow calculation model of the water channel between the cascade pumping station groups based on the river network generalization diagram between the cascade pumping station groups and the Saint-Venant equations;

[0126] The pump station optimization operation plan recommendation module 300 based on the knowledge graph is used to construct a pump station operation plan query subgraph based on the real-time operation related information of the pump stations at all levels, and weight and sort the plan entities corresponding to the pump station operation plan query subgraph according to the operation plan knowledge graph to obtain multiple pump station optimization operation plans, so as to construct an optimization operation plan library for pump stations at all levels;

[0127] The non-steady flow simulation calculation module 400 of the inter-stage water channel is used to construct an optimal operation solution library for the cascade pump station group based on the optimal operation solution library for the pump stations at each level, and use the solutions in the optimal operation solution library for the cascade pump station group as the upstream and downstream flow boundaries of the one-dimensional non-steady flow calculation model to respectively calculate the flow and water level process lines of each section of the water channel under each solution;

[0128] The cascade pump station group optimization operation plan comprehensive comparison module 500 is used to compare and screen the plans in the cascade pump station group optimization operation plan library from multiple aspects based on the flow and water level process lines of each section of the water conveyance river, so as to obtain the optimal cascade pump station group optimization operation plan.

[0129] Furthermore, the pump station operation knowledge graph construction module 100 is also used for:

[0130] Decompose the cascade pump station group into multiple single pump stations, and obtain historical operation related information of each single pump station; wherein the historical operation related information includes basic information of the pump station and operation plan information;

[0131] Based on the basic information of the pumping station and the operation plan information, relevant concepts of the pumping station operation are obtained, the relevant concepts are split into multiple sub-concepts, and a single concept ontology model of the pumping station operation is constructed based on the ontology language;

[0132] Building a domain ontology model of pump station operation based on the single concept ontology model, integrating preset semantic rules into the domain ontology model to build a pattern layer of the pump station operation knowledge graph; and,

[0133] A pump station historical operation plan library is constructed based on the operation plan information, and knowledge is extracted from the plans in the pump station historical operation plan library to obtain triple data to construct a data layer of the pump station operation knowledge graph, so as to construct a pump station operation knowledge graph.

[0134] Furthermore, the above-mentioned inter-stage water channel non-steady flow model construction module 200 is also used for:

[0135] Based on the basic data of the water supply channel between every two pumping stations in the cascade pumping station group and the water use status information of water users along the inter-stage water supply channel, a generalized river network map of the main and tributary rivers and water outlets is constructed;

[0136] A one-dimensional unsteady flow calculation model for an interstage water transfer channel is constructed based on the Saint-Venant equations and the generalized diagram of the river network.

[0137] According to the embodiment of the present invention, the system for recommending optimized operation plans for cascade pump station groups based on knowledge graphs and one-dimensional hydraulic models uses the collected historical operation plans of pump stations to construct a knowledge graph of pump station operation plans, and uses a similarity matching method to find cases that are relatively similar to the current working conditions, thereby generating the best operation plan that adapts to the actual situation, and integrating a one-dimensional hydraulic model to ensure the head matching degree and water level requirements between pump stations at all levels in view of the operation and scheduling characteristics of cascade pump stations. The knowledge graph technology is also used to recommend the best operation plan from the historical operation plans of the pump stations, avoiding the shortcomings of the existing scheduling model that is too idealistic, inconsistent with the actual situation, and poor operability, which can assist in improving the scheduling decision-making ability of the cascade pump station group and enhance the feasibility of the knowledge graph in the scheduling of the cascade pump station group.

[0138] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0139] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

Claims

1. A method for recommending optimal operation plans for cascade pumping station groups based on knowledge graph and one-dimensional hydraulic model, characterized in that: The following steps are involved: The knowledge graph of operation plans of each single pumping station in the cascade pumping station group is constructed through the historical operation related information of the single pumping station; Based on the river network generalization diagram between cascade pumping stations and Saint-Venant equations, a one-dimensional unsteady flow calculation model for the water conveyance channel between cascade pumping stations is constructed. Based on the real-time operation related information of pump stations at all levels, a pump station operation plan query subgraph is constructed, and according to the operation plan knowledge graph, the plan entities corresponding to the pump station operation plan query subgraph are weighted and sorted to obtain multiple pump station optimization operation plans, so as to construct an optimization operation plan library for pump stations at all levels; Based on the optimization operation solution library of each level of pumping stations, a cascade pumping station group optimization operation solution library is constructed, and the solutions in the cascade pumping station group optimization operation solution library are used as the upstream and downstream flow boundaries of the one-dimensional non-steady flow calculation model to respectively calculate the flow and water level process lines of each section of the water conveyance channel under each solution; Based on the flow and water level process lines of each section of the water conveyance channel, the schemes in the cascade pump station group optimization operation scheme library are compared and screened from multiple aspects to obtain the optimal cascade pump station group optimization operation scheme.

2. The method according to claim 1, characterized in that The multiple aspects include the head matching degree of the cascade pump station group, the optimized operation economy of the cascade pump station system, the water level fluctuation of the inter-stage water transfer channel, and the flood control, drainage, navigation and ecological water level requirements of the water transfer channel.

3. The method according to claim 1, characterized in that The knowledge graph of the operation plan of each single pumping station in the cascade pumping station group is constructed through the historical operation related information of the single pumping station, including: Decompose the cascade pump station group into multiple single pump stations, and obtain historical operation related information of each single pump station; wherein the historical operation related information includes basic information of the pump station and operation plan information; Based on the basic information of the pumping station and the operation plan information, relevant concepts of the pumping station operation are obtained, the relevant concepts are split into multiple sub-concepts, and a single concept ontology model of the pumping station operation is constructed based on the ontology language; Building a domain ontology model of pump station operation based on the single concept ontology model, integrating preset semantic rules into the domain ontology model to build a pattern layer of the pump station operation knowledge graph; and, A pump station historical operation plan library is constructed based on the operation plan information, and knowledge is extracted from the plans in the pump station historical operation plan library to obtain triple data to construct a data layer of the pump station operation knowledge graph, so as to construct a pump station operation knowledge graph.

4. The method according to claim 3, characterized in that: Based on the river network generalization diagram between cascade pumping stations and the Saint-Venant equations, a one-dimensional unsteady flow calculation model for the water transfer channel between cascade pumping stations is constructed, including: Based on the basic data of the water supply channel between every two pumping stations in the cascade pumping station group and the water use status information of water users along the inter-stage water supply channel, a generalized river network map of the main and tributary rivers and water outlets is constructed; A one-dimensional unsteady flow calculation model for an interstage water transfer channel is constructed based on the Saint-Venant equations and the generalized diagram of the river network.

5. The method according to claim 4, characterized in that Based on the real-time operation related information of pump stations at all levels, a pump station operation plan query subgraph is constructed, and according to the operation plan knowledge graph, the plan entities corresponding to the pump station operation plan query subgraph are weighted and sorted to obtain multiple pump station optimization operation plans, so as to construct an optimization operation plan library for pump stations at all levels, including: Constructing a pump station operation plan query subgraph based on the real-time operation related information of each single pump station in the cascade pump station group; wherein the real-time operation related information includes basic performance parameters of the water pump, scheduling objectives and operating conditions; Retrieving a subgraph having a similar scheduling target in the operation plan knowledge graph based on the pump station operation plan query subgraph; Calculating entity similarities and entity node weights in the subgraphs respectively, and calculating subgraph similarity based on the entity similarities and entity node weights; Searching for operation plans corresponding to similar cases based on the subgraph similarity, and assigning the similarity corresponding to each historical case to each associated operation plan to obtain an alternative plan; The recommendation degree of the alternative schemes is adjusted to obtain the recommended scheme priority, and multiple recommended schemes for pump stations at all levels are selected according to the sorting results of the scheme priorities to form an optimized operation scheme library for pump stations at all levels.

6. The method according to claim 5, characterized in that Based on the optimization operation solution library of each level of pumping stations, a cascade pumping station group optimization operation solution library is constructed, and the solutions in the cascade pumping station group optimization operation solution library are used as the upstream and downstream flow boundaries of the one-dimensional unsteady flow calculation model to respectively calculate the flow and water level process lines of each section of the water conveyance channel under each solution, including: The schemes in the optimization operation scheme library of pumping stations at all levels are combined to construct the optimization operation scheme library of cascade pumping station groups; Inputting the upstream and downstream flow boundary conditions of the inter-stage water conveyance channel obtained based on the optimized operation scheme library of the cascade pump station group into the Saint-Venant equations, and constructing a nonlinear equation group of the river channel with a cross section according to the initial flow and initial water level of the river channel; The nonlinear equations are solved by the chasing method, and the flow process lines and water level process lines of each section of the inter-stage water transfer channel under each scheme in the optimal operation scheme library of the cascade pump station group are obtained according to the solution results.

7. The method according to claim 2, characterized in that Based on the flow and water level process lines of each section of the water conveyance channel, the schemes in the cascade pump station group optimization operation scheme library are compared and screened from multiple aspects to obtain the optimal pump station group optimization operation scheme, including: The water level fluctuations above and below the pump stations at each level under each operation scheme are calculated respectively, and the water level fluctuations above and below the pump stations under each operation scheme are analyzed and compared to obtain the head matching analysis results of the cascade pump station group; The minimum unit water extraction cost of each pumping station under each operation scheme, using a fixed angle and constant speed operation, and the minimum unit water extraction cost under an optimized operation scheme are calculated to obtain the total savings of the cascade pumping station group, and the total savings under each operation scheme are analyzed and compared to obtain the results of the economic analysis of the optimized operation of the cascade pumping station system; Calculate the water level fluctuation of the inter-stage water conveyance channel under each operation scheme for each pump station respectively, and compare and analyze the water level fluctuation under each operation scheme to obtain the analysis result of the water level fluctuation of the inter-stage water conveyance channel; According to the non-steady flow simulation results of the water channel, analyze whether the water level and water level fluctuation of the river channel under each operation scheme can meet the requirements of flood control and drainage, navigation and ecological water level in each period, so as to obtain the analysis results of the water channel requirements; The optimal operation plan for the cascade pump station group is obtained based on the head matching analysis results of the cascade pump station group, the economic analysis results of the optimized operation of the cascade pump station system, the water level fluctuation analysis results of the inter-stage water transfer channel and the water transfer channel requirement analysis results.

8. A system for recommending optimal operation plans for cascade pumping stations based on knowledge graph and one-dimensional hydraulic model, characterized in that: The following steps are involved: The pump station operation knowledge graph construction module is used to construct the operation plan knowledge graph of each single pump station in the cascade pump station group based on the historical operation related information of the single pump station; The module for constructing the non-steady flow model of the inter-stage water channel is used to construct the one-dimensional non-steady flow calculation model of the water channel between the cascade pumping station groups based on the generalized diagram of the river network between the cascade pumping station groups and the Saint-Venant equations; The pump station optimization operation plan recommendation module based on the knowledge graph is used to construct a pump station operation plan query subgraph based on the real-time operation related information of pump stations at all levels, and weight and sort the plan entities corresponding to the pump station operation plan query subgraph according to the operation plan knowledge graph to obtain multiple pump station optimization operation plans, so as to construct an optimization operation plan library for pump stations at all levels; The non-steady flow simulation calculation module of the inter-stage water conveyance channel is used to construct an optimal operation solution library for the cascade pump station group based on the optimal operation solution library for the pump stations at each level, and use the solutions in the optimal operation solution library for the cascade pump station group as the upstream and downstream flow boundaries of the one-dimensional non-steady flow calculation model to respectively calculate the flow and water level process lines of each section of the water conveyance channel under each solution; The module for comprehensively comparing and selecting the optimal operation schemes of the cascade pump station groups is used to compare and select the schemes in the optimal operation scheme library of the cascade pump station groups from multiple aspects based on the flow and water level process lines of each section of the water conveyance river, so as to obtain the optimal optimal operation scheme of the cascade pump station groups.

9. The system according to claim 8, characterized in that The pump station operation knowledge graph construction module is also used for: Decompose the cascade pump station group into multiple single pump stations, and obtain historical operation related information of each single pump station; wherein the historical operation related information includes basic information of the pump station and operation plan information; Based on the basic information of the pumping station and the operation plan information, relevant concepts of the pumping station operation are obtained, the relevant concepts are split into multiple sub-concepts, and a single concept ontology model of the pumping station operation is constructed based on the ontology language; Building a domain ontology model of pump station operation based on the single concept ontology model, integrating preset semantic rules into the domain ontology model to build a pattern layer of the pump station operation knowledge graph; and, A pump station historical operation plan library is constructed based on the operation plan information, and knowledge is extracted from the plans in the pump station historical operation plan library to obtain triple data to construct a data layer of the pump station operation knowledge graph, so as to construct a pump station operation knowledge graph.

10. The system according to claim 9, characterized in that The interstage water channel non-steady flow model building module is also used for: Based on the basic data of the water supply channel between every two pumping stations in the cascade pumping station group and the water use status information of water users along the inter-stage water supply channel, a generalized river network map of the main and tributary rivers and water outlets is constructed; A one-dimensional unsteady flow calculation model for an interstage water transfer channel is constructed based on the Saint-Venant equations and the generalized diagram of the river network.

Images