A method and device for optimizing selection parameters of a water pump water turbine

Abstract

The application relates to the technical field of pump-turbine optimal design, and discloses a pump-turbine type selection parameter optimization method and device, which comprises the following steps: obtaining the current key hydraulic parameters of a pump-turbine of a target power station, screening an optimal reference power station based on the current key hydraulic parameters of the pump-turbine, obtaining runner geometric parameters and movable guide vane geometric parameters of the optimal reference power station, establishing a multi-target optimization model based on the runner geometric parameters and the movable guide vane geometric parameters, performing multi-target optimization on the multi-target optimization model to obtain optimal comprehensive performance parameters of the pump-turbine, and performing iterative feedback correction on the optimal comprehensive performance parameters of the pump-turbine to obtain optimal type selection parameters of the pump-turbine. The application guarantees that the type selection parameters of the pump-turbine are optimal, and realizes stable operation of the power station.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pump-turbine optimization design, and particularly relates to a pump-turbine selection parameter optimization method and device. BACKGROUND

[0002] Compared with the energy storage unit in series connection of a water turbine and a water pump, the pump-turbine has a greatly reduced weight and a reduced cost, and thus is widely used. The pump-turbine selection process directly affects the equipment operation stability and economic benefits, and needs to avoid blind parameter application or rely on a single index decision.

[0003] In the pump-turbine selection process, the key parameters such as runner diameter, blade number and guide vane height are independently optimized in the related selection design, and the influence of the multi-variable cooperation on the wide load performance of the pump-turbine is not considered, which leads to poor parameter coupling of the pump-turbine selection design and cannot guarantee the stable operation of the power station. SUMMARY

[0004] Therefore, the present application provides a pump-turbine selection parameter optimization method and device to solve the problem of poor parameter coupling of the pump-turbine selection design.

[0005] In a first aspect, the present application provides a pump-turbine selection parameter optimization method, which comprises the following steps:

[0006] obtaining the current key hydraulic parameters of the target power station, and screening the optimal reference power station based on the current key hydraulic parameters of the pump-turbine;

[0007] obtaining the runner geometric parameters and the movable guide vane geometric parameters of the optimal reference power station, and establishing a multi-objective optimization model based on the runner geometric parameters and the movable guide vane geometric parameters;

[0008] performing multi-objective optimization on the multi-objective optimization model to obtain the optimal comprehensive performance parameters of the pump-turbine;

[0009] performing iterative feedback correction on the optimal comprehensive performance parameters of the pump-turbine to obtain the optimal selection parameters of the pump-turbine.

[0010] The pump-turbine selection parameter optimization method provided in the embodiment screens the optimal reference power station through the current key hydraulic parameters of the pump-turbine, establishes a multi-objective optimization model by using the runner geometric parameters and the movable guide vane geometric parameters of the optimal reference power station, avoids the problem of poor parameter coupling of the pump-turbine selection design caused by the single selection target, fully considers multiple hydraulic parameters in the pump-turbine selection process, and then performs multi-objective optimization on the multi-objective optimization model and performs iterative feedback correction on the optimal comprehensive performance parameters of the pump-turbine, so as to ensure the optimal selection parameters of the pump-turbine and realize the stable operation of the power station.

[0011] In an optional implementation, the optimal reference power station is screened based on the current pump-turbine key hydraulic parameter, including:

[0012] The pump-turbine key hydraulic historical parameters of other power stations are obtained, the current pump-turbine key hydraulic parameter is matched with the pump-turbine key hydraulic historical parameters of other power stations, the reference power station and the reference pump-turbine key hydraulic parameter are determined;

[0013] Based on the reference pump-turbine key hydraulic parameter, the optimal pump-turbine key hydraulic historical parameter is determined by using a weight algorithm, and the reference power station corresponding to the optimal pump-turbine key hydraulic historical parameter is taken as the optimal reference power station.

[0014] The optimization method for pump-turbine selection parameters provided in this embodiment screens the reference power station similar to the current pump-turbine key hydraulic parameter as the initial selection, and then determines the optimal pump-turbine key hydraulic historical parameter by using a weight algorithm, so as to accurately screen the optimal reference power station, take the pump-turbine key hydraulic historical parameter corresponding to the optimal reference power station as the pump-turbine key hydraulic parameter of the current power station, improve the calculation efficiency and accuracy of the pump-turbine selection parameters, and lay a foundation for subsequent optimization of the pump-turbine selection parameters.

[0015] In an optional implementation, a multi-objective optimization model is established based on the runner geometric parameter and the movable guide vane geometric parameter; wherein the expression of the objective function corresponding to the multi-objective optimization model is:

[0016]

[0017] wherein, efficiency, pressure fluctuation, S characteristic allowance, effective cavitation allowance, runner inlet setting angle, runner outlet setting angle, runner wrap angle, runner control point coordinate, movable guide vane inlet setting angle, movable guide vane outlet setting angle, movable guide vane control point coordinate.

[0018] In an optional implementation, the multi-objective optimization model is subjected to multi-objective optimization to obtain the optimal comprehensive performance parameter of the pump-turbine, including:

[0019] The model accuracy of the multi-objective optimization model is verified.

[0020] If the model accuracy meets the accuracy condition, the NSGA-III algorithm with an elitist strategy is used to solve the multi-objective optimization model to obtain the optimal comprehensive performance parameters of the pump-turbine.

[0021] The optimization method for pump-turbine selection parameters provided in this embodiment verifies the model accuracy of the multi-objective optimization model, optimizes the multi-objective optimization model, and uses the NSGA-III algorithm with an elitist strategy to solve the multi-objective optimization model to ensure that high-quality solutions are retained, efficiently solve the multi-objective optimization problem, balance the convergence and diversity of solutions, ensure that the comprehensive performance parameters are optimal, and make the pump-turbine selection parameters fully consider multiple working conditions to realize multi-objective collaborative design.

[0022] In an optional implementation, the model accuracy verification of the multi-objective optimization model includes:

[0023] CFD simulation data and historical data of the pump-turbine are obtained, and a verification data set is established based on the CFD simulation data and the historical data;

[0024] The multi-objective optimization model is fitted based on the verification data set to obtain predicted performance parameters of the pump-turbine;

[0025] The predicted performance parameters of the pump-turbine are compared with the performance parameters in the verification data set to determine the model accuracy of the multi-objective optimization model;

[0026] The model accuracy of the multi-objective optimization model is compared with an accuracy condition to determine a model accuracy verification result.

[0027] The optimization method for pump-turbine selection parameters provided in this embodiment verifies the model accuracy of the multi-objective optimization model, ensures that the multi-objective optimization model is optimal, and makes the comprehensive performance parameters obtained by subsequently solving the multi-objective optimization model optimal, thereby ensuring the accuracy of the multi-objective optimization.

[0028] In an optional implementation, the optimal comprehensive performance parameters of the pump-turbine are iteratively and feedback corrected to obtain optimal selection parameters of the pump-turbine, including:

[0029] Model tests are performed on the optimal comprehensive performance parameters of the pump-turbine to obtain test parameters;

[0030] Data verification is performed on the test parameters, and the multi-objective optimization model is iteratively updated based on the data verification result until the multi-objective optimization model meets an iterative convergence condition, and then the iterative updating is stopped to obtain the optimal selection parameters of the pump-turbine.

[0031] This embodiment provides an optimization method for the selection parameters of a water pump turbine. By conducting model tests, data verification, and iterative updates on the optimal comprehensive performance parameters of the water pump turbine, the optimal selection parameters of the water pump turbine are ensured to better meet the operating requirements of the power station, thus guaranteeing the stable operation of the power station.

[0032] Secondly, the present invention provides an optimization device for the selection parameters of a water pump turbine, the device comprising:

[0033] The filtering module is used to obtain the current key hydraulic parameters of the pump-turbine of the target power station and filter the optimal reference power station based on the current key hydraulic parameters of the pump-turbine.

[0034] A module is established to obtain the runner geometry parameters and the movable guide vane geometry parameters of the optimal reference power station, and a multi-objective optimization model is established based on the runner geometry parameters and the movable guide vane geometry parameters;

[0035] The optimization module is used to perform multi-objective optimization on the multi-objective optimization model to obtain the optimal comprehensive performance parameters of the pump turbine.

[0036] The correction module is used to iteratively correct the optimal comprehensive performance parameters of the pump-turbine to obtain the optimal parameters of the pump-turbine.

[0037] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for optimizing the selection parameters of the water pump turbine described in the first aspect or any corresponding embodiment.

[0038] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for optimizing pump-turbine selection parameters described in the first aspect or any corresponding embodiment.

[0039] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the method for optimizing the selection parameters of a water pump and turbine as described in the first aspect or any corresponding embodiment. Attached Figure Description

[0040] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating a method for optimizing pump-turbine selection parameters according to an embodiment of the present invention.

[0042] Figure 2 This is a flowchart illustrating another method for optimizing pump-turbine selection parameters according to an embodiment of the present invention.

[0043] Figure 3 This is a flowchart illustrating another method for optimizing pump-turbine selection parameters according to an embodiment of the present invention;

[0044] Figure 4 This is a flowchart illustrating another method for optimizing pump-turbine selection parameters according to an embodiment of the present invention.

[0045] Figure 5 This is a flowchart illustrating a pump-turbine selection and design optimization method based on a historical runner database and multi-objective collaborative optimization according to an embodiment of the present invention.

[0046] Figure 6 This is a schematic diagram of the Pareto front solution set distribution according to an embodiment of the present invention;

[0047] Figure 7 This is a structural block diagram of a device for optimizing the selection parameters of a water pump and turbine according to an embodiment of the present invention;

[0048] Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] The following defects exist in the selection process of water pumps and turbines:

[0051] 1. Single operating condition dependence: Related selection methods (such as specific speed method and model comprehensive characteristic curve method) are only optimized for the rated operating point. When the load deviates from the design point, the efficiency drops significantly.

[0052] 2. Poor parameter coupling: Key parameters such as runner diameter, number of blades, and guide vane height are optimized independently without considering the impact of multi-variable synergy on wide load performance.

[0053] The embodiment of the present application provides a water pump water turbine type selection parameter optimization method, which is suitable for pumped storage unit design needing to consider wide load efficiency and pressure pulsation suppression, and realizes multi-objective collaborative design through integrated parameterized modeling, multi-working condition coupling optimization and dynamic adaptability evaluation system, that is, through historical data matching, parameterized modeling and experimental iteration correction, so that the problems of efficiency attenuation, cavitation deterioration and pressure pulsation exceeding the standard in the range of 30%-100% wide load in the related type selection method are solved.

[0054] The embodiment of the present application provides a water pump water turbine type selection parameter optimization method, and it should be noted that the execution subject of the water pump water turbine type selection parameter optimization method provided by the embodiment of the present application can be a water pump water turbine type selection parameter optimization device, and the water pump water turbine type selection parameter optimization device can be realized as part or all of an electronic device in the form of software, hardware or a combination of software and hardware, wherein the electronic device can be a server or a terminal, wherein the server in the embodiment of the present application can be a server, or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application can be a smart phone, a personal computer, a tablet computer, a wearable device, a smart robot and other smart hardware devices. In the following method embodiment, the execution subject is taken as an example to be explained.

[0055] According to the embodiment of the present application, a water pump water turbine type selection parameter optimization method is provided, and it should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a group 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 that here.

[0056] In the embodiment, a water pump water turbine type selection parameter optimization method is provided, which can be used in the above-mentioned electronic device, Figure 1 is a flowchart of a water pump water turbine type selection parameter optimization method according to the embodiment of the present application, as Figure 1 shown, the flowchart includes the following steps:

[0057] In step S101, the current key hydraulic parameters of the water pump water turbine of the target power station are obtained, and the optimal reference power station is selected based on the current key hydraulic parameters of the water pump water turbine.

[0058] Specifically, the current key hydraulic parameters of the water pump water turbine include the maximum water head of the water turbine H TM_max , the minimum water head of the water turbine H TM_min , the rated water head of the water turbine H TM_n , the maximum lift of the water pump H PM_max, the minimum head of the water pump H PM_min , the single machine capacity P and the rotating speed N .

[0059] In step S102, the runner geometric parameters and the movable guide vane geometric parameters of the optimal reference power station are obtained, and a multi-objective optimization model is established based on the runner geometric parameters and the movable guide vane geometric parameters.

[0060] Specifically, the runner geometric parameters of the optimal power station include a runner inlet setting angle, a runner outlet setting angle and a runner wrap angle, and a five-order Bezier curve is used to control a pressure surface and a suction surface curve of a runner airfoil, so as to obtain runner control point coordinates; the movable guide vane geometric parameters include a movable guide vane inlet setting angle and a movable guide vane outlet setting angle, and a three-order Bezier curve is used to control a movable guide vane airfoil, so as to obtain movable guide vane control point coordinates.

[0061] Further, an expression of a target function corresponding to the multi-objective optimization model is as follows:

[0062]

[0063] wherein, efficiency, pressure fluctuation, S characteristic margin, effective cavitation margin, runner inlet setting angle, runner outlet setting angle, runner wrap angle, runner control point coordinates, runner flow direction position, runner airfoil thickness, movable guide vane inlet setting angle, movable guide vane outlet setting angle, movable guide vane control point coordinates, movable guide vane flow direction position, movable guide vane airfoil thickness, 、 、 and represent functions corresponding to a Kriging proxy model.

[0064] Further, constraint conditions are set according to given design requirements, including weighted efficiency, pressure fluctuation of different water head sections, S characteristic margin and cavitation and other hydraulic performance constraints.

[0065] In step S103, multi-objective optimization is performed on the multi-objective optimization model, so as to obtain optimal comprehensive performance parameters of the pump-turbine.

[0066] Step S104, the optimal comprehensive performance parameters of the pump-turbine are iteratively corrected to obtain the optimal selection parameters of the pump-turbine.

[0067] Specifically, the pump-turbine is selected by using the optimal selection parameters of the pump-turbine, the selected pump-turbine is applied to the power station, the water flow energy is converted into electric energy, and the pumping function is realized by reverse operation.

[0068] The method for optimizing the selection parameters of the pump-turbine provided in the embodiment selects the optimal reference power station by using the current key hydraulic parameters of the pump-turbine, establishes a multi-objective optimization model by using the runner geometric parameters and the movable guide vane geometric parameters of the optimal reference power station, avoids the poor parameter coupling of the selection design of the pump-turbine caused by the single selection target, makes the selection process of the pump-turbine fully consider multiple hydraulic parameters, and then optimizes the multi-objective optimization model and iteratively corrects the optimal comprehensive performance parameters of the pump-turbine, so as to ensure the optimal selection parameters of the pump-turbine and realize the stable operation of the power station.

[0069] In the embodiment, a method for optimizing the selection parameters of the pump-turbine is provided, which can be used for the electronic device described above, Figure 2 is a flowchart of a method for optimizing the selection parameters of the pump-turbine according to the embodiment of the present application, as Figure 2 shown, the flowchart includes the following steps:

[0070] Step S201, the current key hydraulic parameters of the pump-turbine of the target power station are obtained, and the optimal reference power station is selected based on the current key hydraulic parameters of the pump-turbine.

[0071] Specifically, the step S201 includes the following steps:

[0072] Step S2011, the key hydraulic historical parameters of the pump-turbine of other power stations are obtained, the current key hydraulic parameters of the pump-turbine are matched with the key hydraulic historical parameters of the pump-turbine of other power stations, and the reference power station and the key hydraulic parameters of the reference pump-turbine are determined.

[0073] Specifically, the historical runner design cases similar to the current power station parameters are selected from the selection database by using the similarity criterion, and the reference power station parameters and the pump-turbine performance parameters are extracted; wherein, the key hydraulic historical parameters of the pump-turbine of other power stations are stored in the selection database.

[0074] Further, a similarity evaluation function is defined, and the expression is as follows:

[0075]

[0076] wherein, similarity, weight coefficient corresponding to the key hydraulic parameter, X i current pump-turbine key hydraulic parameter, X ref reference pump-turbine key hydraulic parameter.

[0077] Further, the first K cases with the highest similarity are selected as the initial selection reference, i.e., the reference power station and the reference pump-turbine key hydraulic parameter. K

[0078] Step S2012, based on the reference pump-turbine key hydraulic parameter, the weight algorithm is used to determine the optimal pump-turbine key hydraulic historical parameter, and the reference power station corresponding to the optimal pump-turbine key hydraulic historical parameter is taken as the optimal reference power station.

[0079] Specifically, K In the first K cases, the weight method is used to assign weights to the selected reference pump-turbine key hydraulic parameters, and the pump-turbine with excellent performance under wide load and close specific speed is mainly considered.

[0080] Further, the weight coefficients are defined, and the reference pump-turbine key hydraulic parameters and their corresponding weights are as follows: rated point specific speed (weight 0.5), optimal efficiency (weight 0.2), and efficiency under 50% load of rated head (weight 0.3); then the reference pump-turbine key hydraulic parameters and their corresponding weights are multiplied, the reference pump-turbine key hydraulic parameters multiplied by the weights are added to obtain the total score of the reference power station, and then the reference power station with the highest score is selected as the optimal reference power station.

[0081] Step S202, the runner geometric parameters and the movable guide vane geometric parameters of the optimal reference power station are obtained, and a multi-objective optimization model is established based on the runner geometric parameters and the movable guide vane geometric parameters. For details, please refer to step S102 of the embodiment shown in Figure 1 not repeated here.

[0082] Step S203, the multi-objective optimization model is subjected to multi-objective optimization to obtain the optimal comprehensive performance parameters of the pump-turbine. For details, please refer to step S103 of the embodiment shown in Figure 1 not repeated here.

[0083] Step S204, the optimal comprehensive performance parameters of the pump-turbine are subjected to iterative feedback correction to obtain the optimal selection parameters of the pump-turbine. For details, please refer to step S104 of the embodiment shown in Figure 1 not repeated here.

[0084] ​The embodiment provides a water pump water turbine type selection parameter optimization method, which selects a reference power station similar to a current water pump water turbine key hydraulic parameter as an initial type selection, and then determines optimal water pump water turbine key hydraulic historical parameters by using a weight algorithm, so that accurate selection of an optimal reference power station is realized, the water pump water turbine key hydraulic historical parameters corresponding to the optimal reference power station are used as water pump water turbine key hydraulic parameters of the current power station, the calculation efficiency and accuracy of the water pump water turbine type selection parameters are improved, and a foundation is laid for subsequent optimization of the water pump water turbine type selection parameters.

[0085] In the embodiment, a water pump water turbine type selection parameter optimization method is provided, which can be used for the electronic device described above, Figure 3 is a flowchart of a water pump water turbine type selection parameter optimization method according to the embodiment of the present application, as shown in the figure, the flowchart comprises the following steps: Figure 3

[0086] In step S301, current water pump water turbine key hydraulic parameters of a target power station are obtained, and an optimal reference power station is selected based on the current water pump water turbine key hydraulic parameters. For details, refer to step S201 in the embodiment shown in Figure 2 , which will not be repeated here.

[0087] In step S302, runner geometric parameters and movable guide vane geometric parameters of the optimal reference power station are obtained, and a multi-objective optimization model is established based on the runner geometric parameters and the movable guide vane geometric parameters. For details, refer to step S202 in the embodiment shown in Figure 2 , which will not be repeated here.

[0088] In step S303, the multi-objective optimization model is subjected to multi-objective optimization, and optimal comprehensive performance parameters of the water pump water turbine are obtained.

[0089] Specifically, the above step S303 comprises:

[0090] In step S3031, the multi-objective optimization model is subjected to model accuracy verification.

[0091] In some optional embodiments, the above step S3031 comprises:

[0092] In step a1, CFD simulation data and historical data of the water pump water turbine are obtained, and a verification data set is established based on the CFD simulation data and the historical data.

[0093] ​Specifically, sample points (i.e. performance parameters of the pump-turbine) are selected, and input parameters and corresponding output parameter sets are obtained according to CFD (Computational Fluid Dynamics) simulation and a historical database; wherein the sample points in the verification data set include input data including parameters in the parameterized modeling, i.e. runner inlet setting angle, runner outlet setting angle, runner wrap angle, runner control point coordinates, inlet setting angle of the movable guide vane, outlet setting angle of the movable guide vane and movable guide vane control point coordinates, and output data including efficiency, pressure fluctuation, S characteristic residual and effective cavitation residual.

[0094] Step a2, fitting the multi-objective optimization model based on the verification data set to obtain predicted performance parameters of the pump-turbine.

[0095] Step a3, comparing the predicted performance parameters of the pump-turbine with the performance parameters in the verification data set to determine the model accuracy of the multi-objective optimization model.

[0096] Step a4, comparing the model accuracy of the multi-objective optimization model with the accuracy condition to determine the model accuracy verification result.

[0097] Specifically, it is determined whether the model accuracy meets the requirements, if not, returning to step a1 to increase the number of sample points or optimize the distribution of sample points, and re-verifying the model accuracy of the multi-objective optimization model; if yes, outputting the multi-objective optimization model.

[0098] Step S3032, if the model accuracy meets the accuracy condition, using the NSGA-III algorithm with an elite strategy to solve the multi-objective optimization model to obtain optimal comprehensive performance parameters of the pump-turbine.

[0099] Specifically, the NSGA-III (Non-dominated Sorting Genetic Algorithm III) optimization algorithm with an elite strategy is run, wherein the initial population uses the samples generated by LHS, and the objective function in the optimization algorithm uses the output proxy model; a Pareto front solution is obtained, and the optimal solution is selected from the solution set, the optimal solution being output parameters (efficiency, pressure fluctuation, S characteristic residual and effective cavitation residual) with optimal comprehensive performance and corresponding input parameters (runner inlet setting angle, runner outlet setting angle, runner wrap angle, runner control point coordinates, inlet setting angle of the movable guide vane, outlet setting angle of the movable guide vane and movable guide vane control point coordinates); and the output parameters and input parameters with optimal comprehensive performance are taken as the optimal comprehensive performance parameters of the pump-turbine.

[0100] Further, the water pump turbine performance parameters (including the above input parameters and output parameters) are taken as decision variables, and initial population with uniform distribution is generated in variable space by Latin Hypercube Sampling (LHS) to ensure uniform coverage of the design space. The population size is set to 300, the crossover probability , and the mutation probability .

[0101] Further, the specific steps of the NSGA-III algorithm with an elite strategy include: calculating the objective function value of each individual in the initial population by using a multi-objective optimization model, and taking the initial population as the basis of the first generation of elite pool; selecting the parent from the current parent population in the initial population by tournament selection method (or roulette wheel selection method) to ensure that the selected individuals have better non-dominance and diversity; performing crossover (such as simulated binary crossover) on the selected parents to generate intermediate individuals and enhance the exploration ability of the population; performing mutation (such as polynomial mutation) on the intermediate individuals after crossover to introduce randomness and avoid the population falling into local optimum; generating a child population with the same size as the parent population after crossover and mutation; combining the current parent population and the child population to form a hybrid population with a size of 2N, N representing the size; performing non-dominated sorting on the hybrid population to obtain a plurality of non-dominated front layers ; generating H uniformly distributed reference points (such as by the hierarchical grid method) in the target space according to the number M of objective functions, and the number H of reference points needs to cover the possible optimal region of the target space; for each individual in the hybrid population, calculating the “vertical distance” (reflecting the closeness of the individual to the reference point) between the individual and each reference point, and the smaller the distance, the closer the individual to the optimal direction represented by the reference point; assigning an “associated individual” (i.e. the individual closest to the reference point) to each reference point; selecting the next generation of parents (elite population): starting from the non-dominated front layer , and sequentially adding individuals in each layer to the next generation of parents until the total number exceeds N after adding individuals in a certain layer ; for the individuals (i.e. the individuals not selected in ) that exceed the total number, selecting them according to the “crowding degree” of their associated reference points: preferentially retaining the individuals associated with the “current sparsest reference point” (i.e. the individual associated with the reference point is the least), to ensure the diversity of the population in the target space; finally obtaining the next generation of parents with a size of N, which is the “elite population” of the current iteration; if the termination condition (such as reaching the maximum number of iterations, the population convergence accuracy meeting the standard, etc.) is met, the iteration is stopped, and the non-dominated solution in the final population (i.e. the Pareto optimal solution set of the optimization problem) is output; otherwise, repeat the child generation and hybrid selection process until the termination condition is met.

[0102] Further, the Latin hypercube sampling, the Kriging surrogate model and the NSGA-III algorithm with an elite strategy can call the machine learning library in python (a computer programming language) to perform corresponding calculation.

[0103] In step S304, the optimal comprehensive performance parameters of the pump-turbine are iteratively and feedbackly corrected to obtain optimal selection parameters of the pump-turbine. For details, please refer to Figure 2 In step S204 of the embodiment shown in the figure, no further elaboration is given here.

[0104] The optimization method for selection parameters of a pump-turbine provided in this embodiment can ensure population diversity through LHS initialization of a population, accelerate target calculation through a surrogate model, and ensure retention of high-quality solutions through the elite strategy (merging of parent and child generations, non-dominated sorting + reference point selection) of NSGA-III, so as to finally efficiently solve a multi-objective optimization problem. The core is to balance convergence (approximation to the real Pareto front) and diversity (covering different trade-off solutions), and it is suitable for scenarios with high simulation cost and multi-objective conflict (such as engineering design and resource allocation).

[0105] In this embodiment, an optimization method for selection parameters of a pump-turbine is provided, which can be used in the electronic device described above, Figure 4 is a flowchart of an optimization method for selection parameters of a pump-turbine according to an embodiment of the present application, as shown in the figure, the flowchart includes the following steps: Figure 4

[0106] In step S401, the current key hydraulic parameters of the pump-turbine of the target power station are obtained, and the optimal reference power station is selected based on the current key hydraulic parameters of the pump-turbine. For details, please refer to Figure 3 In step S301 of the embodiment shown in the figure, no further elaboration is given here.

[0107] In step S402, the runner geometric parameters and the movable guide vane geometric parameters of the optimal reference power station are obtained, and a multi-objective optimization model is established based on the runner geometric parameters and the movable guide vane geometric parameters. For details, please refer to Figure 3 In step S302 of the embodiment shown in the figure, no further elaboration is given here.

[0108] In step S403, the multi-objective optimization model is subjected to multi-objective optimization to obtain the optimal comprehensive performance parameters of the pump-turbine. For details, please refer to Figure 3 In step S303 of the embodiment shown in the figure, no further elaboration is given here.

[0109] In step S404, the optimal comprehensive performance parameters of the pump-turbine are iteratively and feedbackly corrected to obtain optimal selection parameters of the pump-turbine.

[0110] Specifically, the above step S404 includes:

[0111] ​Step S4041: Conduct a model test on the optimal comprehensive performance parameters of the water pump turbine to obtain the test parameters.

[0112] Specifically, the hydraulic performance of the pump-turbine under wide-load operating conditions, corresponding to the optimal comprehensive performance parameters, is tested on a closed test bench. This includes parameters such as efficiency, pressure pulsation, S-characteristics, and cavitation characteristics.

[0113] Step S4042: Verify the experimental parameters with data, and iteratively update the multi-objective optimization model based on the data verification results until the multi-objective optimization model meets the iterative convergence condition, then stop the iterative update and obtain the optimal parameters of the water pump turbine.

[0114] Specifically, deviation thresholds are defined as: efficiency deviation, pressure pulsation deviation, and S-characteristic margin deviation. If the experimental parameters exceed the deviation thresholds, the weights of the impeller / guide vane control points are adjusted, and the model parameters of the multi-objective optimization model are updated, thus re-optimizing the multi-objective optimization model. When the rate of change of the optimization objective function in two consecutive iterations... When the design convergence is determined, the optimal parameters for the pump-turbine are output.

[0115] This embodiment provides an optimization method for the selection parameters of a water pump turbine. By conducting model tests, data verification, and iterative updates on the optimal comprehensive performance parameters of the water pump turbine, the optimal selection parameters of the water pump turbine are ensured to better meet the operating requirements of the power station, thus guaranteeing the stable operation of the power station.

[0116] The following specific embodiment illustrates the detailed steps of a method for optimizing the selection parameters of a water pump turbine.

[0117] Example 1:

[0118] like Figure 5 As shown, the specific steps of a pump-turbine selection and design optimization method based on historical turbine database and multi-objective collaborative optimization include:

[0119] 1) Wide load adaptability selection based on selection database.

[0120] 1.1 Input power station parameters: The current key hydraulic parameters of the pump-turbine include the turbine's highest head. H TM_max Minimum head of the water turbine H TM_min Rated head of water turbine H TM_n Maximum head of water pump H PM_max Minimum head of water pump H PM_min Single unit capacityP and rotational speed N .

[0121] 1.2 Historical data matching: Based on the similarity criteria, the historical runner design cases similar to the current power station parameters are screened from the selection database, and the reference power station parameters and pump-turbine performance parameters are extracted.

[0122] 1.3. Optimal reference power station selection: The weight method is adopted to assign weights to the key hydraulic parameters of the selected reference pump-turbine, and the pump-turbines with excellent performance under wide load and close specific speed are mainly considered.

[0123] 2) Parametric modeling of structure and multi-objective optimization;

[0124] 2.1 Parametric modeling: The runner geometric parameters include the runner inlet setting angle, the runner outlet setting angle, and the runner wrap angle. The pressure surface and suction surface curves of the runner airfoil are controlled by quintic Bezier curves, obtaining the runner control point coordinates. The active guide vane geometric parameters include the active guide vane inlet setting angle and the active guide vane outlet setting angle. The active guide vane airfoil is controlled by cubic Bezier curves, obtaining the active guide vane control point coordinates.

[0125] 2.2 Multi-objective optimization model:

[0126] The objective function is:

[0127]

[0128] The constraint conditions are set according to the given design requirements, including weighted efficiency, different water head section pressure pulsation, S characteristic allowance, and cavitation and other hydraulic performance.

[0129] 2.3 Optimization algorithm: (1) Select sample points, obtain input parameters and corresponding output parameter set according to CFD simulation and historical database; (2) Call Kriging surrogate model for fitting; (3) Verify the accuracy of the model; (4) Determine whether the accuracy meets the requirements, if not, return to (1) to increase the number of sample points or optimize the sample point distribution, if it meets the requirements, output the surrogate model; (5) Run the NSGA-III optimization algorithm with elite strategy, where the initial population uses the samples generated by LHS, and the objective function in the optimization algorithm uses the output surrogate model; (6) As shown in Figure 6 , get the Pareto frontier solution, and analyze and select the optimal solution from the solution set; the optimal solution is the output parameter with the optimal comprehensive performance and its corresponding input parameter.

[0130] 3) Iterative design optimization driven by experimental verification:

[0131] 3.1. Model test: test the hydraulic performance of the pump-turbine under wide load operation conditions on a closed test bench, including efficiency, pressure fluctuation, S characteristic, cavitation characteristic, and other parameters.

[0132] 3.2. Data verification and feedback correction:

[0133] Define deviation threshold: efficiency deviation, pressure fluctuation deviation, S characteristic allowance deviation; if the deviation is exceeded, adjust the runner / control vane control point weight and update the surrogate model parameters, and repeat step 2) optimization.

[0134] 3.3 Iterative convergence determination: when the optimization objective function change rate of two consecutive iterations is less than 0.01%, it is determined that the design converges.

[0135] In this embodiment, a pump-turbine selection parameter optimization 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 contemplated.

[0136] The present embodiment provides a pump-turbine selection parameter optimization device, as shown in Figure 7 , comprising:

[0137] The screening module 701 is configured to obtain the current key hydraulic parameters of the pump-turbine of the target power station, and screen the optimal reference power station based on the current key hydraulic parameters of the pump-turbine.

[0138] The establishment module 702 is configured to obtain the runner geometric parameters and the movable guide vane geometric parameters of the optimal reference power station, and establish a multi-objective optimization model based on the runner geometric parameters and the movable guide vane geometric parameters.

[0139] The optimization module 703 is configured to perform multi-objective optimization on the multi-objective optimization model to obtain optimal comprehensive performance parameters of the pump-turbine.

[0140] The correction module 704 is configured to perform iterative feedback correction on the optimal comprehensive performance parameters of the pump-turbine to obtain optimal selection parameters of the pump-turbine.

[0141] In some optional embodiments, the screening module 701 comprises:

[0142] The matching unit is configured to obtain the key hydraulic historical parameters of the pump-turbine of other power stations, match the current key hydraulic parameters of the pump-turbine with the key hydraulic historical parameters of the pump-turbine of other power stations, and determine the reference power station and the key hydraulic parameters of the reference pump-turbine.

[0143] The determination unit is used to determine the optimal key hydraulic historical parameters of the pump turbine based on the key hydraulic parameters of the reference pump turbine using a weighted algorithm, and to take the reference power station corresponding to the optimal key hydraulic historical parameters of the pump turbine as the optimal reference power station.

[0144] In some optional implementations, the expression for the objective function corresponding to the multi-objective optimization model in module 702 is:

[0145]

[0146] in, Indicates efficiency. Indicates pressure pulsation. Indicates the S-characteristic margin. Indicates the effective net positive suction head (NPSH). Indicates the angle at which the rotor inlet is positioned. Indicates the angle at which the rotor exits. Indicates the wrap angle of the reel. Indicates the coordinates of the control point of the rotary wheel. Indicates the inlet placement angle of the movable guide vane. Indicates the outlet placement angle of the movable guide vane. This indicates the coordinates of the control point of the active guide vane.

[0147] In some alternative implementations, the optimization module 703 includes:

[0148] The verification unit is used to verify the accuracy of the multi-objective optimization model.

[0149] The solution unit is used to solve the multi-objective optimization model using the NSGA-III algorithm with an elite strategy if the model accuracy meets the accuracy condition, so as to obtain the optimal comprehensive performance parameters of the pump turbine.

[0150] In some optional implementations, the verification unit includes:

[0151] A sub-unit is established to acquire CFD simulation data and historical data of the water pump turbine, and a verification dataset is established based on the CFD simulation data and historical data.

[0152] The fitting subunit is used to fit the multi-objective optimization model based on the validation dataset to obtain the predicted performance parameters of the pump turbine.

[0153] The comparison sub-unit is used to compare the predicted performance parameters of the water pump turbine with the performance parameters in the validation dataset to determine the model accuracy of the multi-objective optimization model.

[0154] The sub-unit is determined to compare the model accuracy of the multi-objective optimization model with the accuracy conditions and determine the model accuracy verification result.

[0155] In some alternative implementations, the correction module 704 includes:

[0156] The test unit is used to conduct model tests on the optimal comprehensive performance parameters of the water pump turbine to obtain the test parameters;

[0157] The iterative update unit is used to verify the experimental parameters and iteratively update the multi-objective optimization model based on the data verification results until the multi-objective optimization model meets the iterative convergence condition, at which point the iterative update stops and the optimal parameters of the pump turbine are obtained.

[0158] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0159] In this embodiment, the device for optimizing the selection parameters of a water pump and turbine is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0160] This invention also provides a computer device having the above-described features. Figure 7 The diagram shows an optimization device for selecting parameters of a water pump and turbine.

[0161] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 8 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0162] The processor 10 can be a central processing unit, a network processing unit, 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 device, a general array logic, or any combination thereof.

[0163] 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 in the above embodiments.

[0164] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system and application programs required by at least one function. The data storage area can store data created according to the 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 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.

[0165] The memory 20 can include a volatile memory, such as a random access memory, and can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid state disk. The memory 20 can further include a combination of the above-mentioned types of memories.

[0166] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 can be connected through a bus or other means, Figure 8 For example, the connection through the bus is taken as an example.

[0167] The input device 30 can receive input digital or character information, and generate key signal inputs related to the user settings and function controls of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, and the like. The output device 40 can include a display device, an auxiliary lighting device (e.g., an LED), a tactile feedback device (e.g., a vibration motor), and the like. The display device includes, but is not limited to, a liquid crystal display, a light emitting diode, a display, and a plasma display. In some alternative embodiments, the display device can be a touch screen.

[0168] The embodiments of the present application further provide a computer readable storage medium, and the method 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, so that the method 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 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, etc. Further, the storage medium can also include a combination of the above-mentioned 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, when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0169] 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, the method and / or technical solutions according to the present application can be called or provided. Those skilled in the art should understand that the form of computer program instructions in a computer readable medium includes but is not limited to source files, executable files, installation package files, etc. Correspondingly, the way of executing computer program instructions 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.

[0170] Although the embodiments of the present application are described in conjunction with the accompanying 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 optimizing the selection parameters of a water pump and turbine, characterized in that, The method includes: Obtain the current key hydraulic parameters of the pump-turbine of the target power station, and select the optimal reference power station based on the current key hydraulic parameters of the pump-turbine; Obtain the runner geometry parameters and movable guide vane geometry parameters of the optimal reference power station, and establish a multi-objective optimization model based on the runner geometry parameters and movable guide vane geometry parameters; wherein, the expression of the objective function corresponding to the multi-objective optimization model is: in, Indicates efficiency. Indicates pressure pulsation. Indicates the S-characteristic margin. Indicates the effective net positive suction head (NPSH). Indicates the angle at which the rotor inlet is positioned. Indicates the angle at which the runner exits. Indicates the wrap angle of the reel. Indicates the coordinates of the control point of the rotary wheel. Indicates the inlet placement angle of the movable guide vane. Indicates the outlet placement angle of the movable guide vane. Indicates the coordinates of the control points of the active guide vane; The multi-objective optimization model is subjected to multi-objective optimization to obtain the optimal comprehensive performance parameters of the pump turbine. The optimal comprehensive performance parameters of the pump-turbine are iteratively fed back and corrected to obtain the optimal parameters of the pump-turbine.

2. The method according to claim 1, characterized in that, The process of selecting the optimal reference power station based on the current key hydraulic parameters of the pump-turbine includes: Obtain key hydraulic historical parameters of pump-turbines from other power stations, match the current key hydraulic parameters of pump-turbines with the key hydraulic historical parameters of pump-turbines from other power stations, and determine the reference power station and reference key hydraulic parameters of pump-turbines. Based on the key hydraulic parameters of the reference pump-turbine, the optimal key hydraulic historical parameters of the pump-turbine are determined using a weighted algorithm, and the reference power station corresponding to the optimal key hydraulic historical parameters of the pump-turbine is taken as the optimal reference power station.

3. The method according to claim 1, characterized in that, The multi-objective optimization of the multi-objective optimization model to obtain the optimal comprehensive performance parameters of the pump-turbine includes: The accuracy of the multi-objective optimization model is verified. If the model accuracy meets the accuracy condition, the NSGA-III algorithm with elite strategy is used to solve the multi-objective optimization model to obtain the optimal comprehensive performance parameters of the pump turbine.

4. The method according to claim 3, characterized in that, The accuracy verification of the multi-objective optimization model includes: Obtain CFD simulation data and historical data of the water pump turbine, and establish a verification dataset based on the CFD simulation data and the historical data; The multi-objective optimization model is fitted based on the validation dataset to obtain the predicted performance parameters of the pump turbine. The predicted performance parameters of the water pump turbine are compared with the performance parameters in the validation dataset to determine the model accuracy of the multi-objective optimization model. The model accuracy of the multi-objective optimization model is compared with the accuracy conditions to determine the model accuracy verification result.

5. The method according to claim 1, characterized in that, The iterative feedback correction of the optimal comprehensive performance parameters of the pump-turbine to obtain the optimal selection parameters of the pump-turbine includes: The optimal comprehensive performance parameters of the pump-turbine were obtained by model testing. The test parameters are verified by data, and the multi-objective optimization model is iteratively updated based on the data verification results until the multi-objective optimization model meets the iterative convergence condition. Then the iterative update is stopped, and the optimal parameters of the pump turbine are obtained.

6. A device for optimizing the selection parameters of a water pump and turbine, characterized in that, The device includes: The filtering module is used to obtain the current key hydraulic parameters of the pump-turbine of the target power station, and to filter the optimal reference power station based on the current key hydraulic parameters of the pump-turbine. A module is established to obtain the runner geometry parameters and movable guide vane geometry parameters of the optimal reference power station, and to establish a multi-objective optimization model based on the runner geometry parameters and movable guide vane geometry parameters; wherein, the expression of the objective function corresponding to the multi-objective optimization model is: in, Indicates efficiency. Indicates pressure pulsation. Indicates the S-characteristic margin. Indicates the effective net positive suction head (NPSH). Indicates the angle at which the rotor inlet is positioned. Indicates the angle at which the runner exits. Indicates the wrap angle of the reel. Indicates the coordinates of the control point of the rotary wheel. Indicates the inlet placement angle of the movable guide vane. Indicates the outlet placement angle of the movable guide vane. Indicates the coordinates of the control points of the active guide vane; The optimization module is used to perform multi-objective optimization on the multi-objective optimization model to obtain the optimal comprehensive performance parameters of the pump turbine. The correction module is used to iteratively correct the optimal comprehensive performance parameters of the water pump turbine to obtain the optimal parameters of the water pump turbine.

7. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the method for optimizing the selection parameters of the water pump turbine as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the method for optimizing the selection parameters of the water pump turbine as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the method for optimizing the selection parameters of the water pump turbine as described in any one of claims 1 to 5.

Images