Water turbine governor control method and device considering structural response
By constructing a multi-index control parameter planning model and a particle swarm optimization algorithm, the problem of low control accuracy of the turbine governor was solved, and more efficient and safer turbine governor control was achieved.
Patent Information
- Application Number
- CN202511320538.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-16
- Publication Date
- 2025-11-04
AI Technical Summary
Existing turbine governor control methods cannot accurately capture the three-dimensional unsteady flow behavior inside the turbine, resulting in low control accuracy. They also ignore sudden load changes and abnormal disturbances during unit start-up, affecting equipment safety and service life.
By employing a multi-index control parameter planning model and combining it with the particle swarm optimization algorithm, and by studying the structural response and flow field dynamic characteristics during the unit start-up process, a multi-index control model is constructed that includes pressure pulsation amplitude, dynamic stress amplitude, steady-state speed regulation time, and speed fluctuation frequency, thereby optimizing the governor control parameters.
It improves the accuracy and quality of turbine governor control, enhances the safety and efficiency of unit start-up and speed regulation, and ensures structural stability and rapid response.
Smart Images
Figure CN120889699A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application belongs to the technical field of hydroelectric power generation, and particularly relates to the technical field of fluid engine, and more particularly relates to a water turbine governor control method and device considering structural response. BACKGROUND
[0002] Currently, the existing research on the control law optimization of the speed regulation system in the starting process of a hydroelectric generating unit usually adopts a one-dimensional water hammer model to dynamically describe the hydraulic transient process, and takes the guide vane opening control law as the optimization variable, and obtains the optimal guide vane opening variation law of the governor through optimization method.
[0003] However, since the one-dimensional water hammer model can only reflect the one-dimensional dynamic characteristics of the flow and pressure in the flow passage system changing with time, it cannot accurately capture the complex three-dimensional unsteady flow behavior inside the water turbine, and at the same time, it ignores the load mutation and abnormal disturbance existing in the starting process of the unit, resulting in low control accuracy of the above-mentioned existing governor control method.
[0004] Therefore, how to better realize the control of the water turbine governor has become a technical problem to be solved in the industry. SUMMARY
[0005] In view of the defects of the prior art, the purpose of the present application is to better realize the control of the water turbine governor, and to solve the problem of low control accuracy of the existing governor control method.
[0006] The first aspect of the present application relates to a water turbine governor control method considering structural response, which comprises: determining a multi-index control parameter planning model based on a plurality of performance indexes of a unit runner; the plurality of performance indexes include pressure pulsation amplitude and dynamic stress amplitude, and also include steady-state speed regulation time and / or speed fluctuation times; Taking the governor control parameters of the water turbine as variables, the multi-index control parameter planning model is iteratively solved to determine the optimal governor control parameters of the water turbine, so as to control the operation of the water turbine governor.
[0007] In some embodiments, the multi-index control parameter planning model is iteratively solved by taking the governor control parameters of the water turbine as variables to determine the optimal governor control parameters of the water turbine, comprising: randomly generating a plurality of particles; each particle includes a set of governor control parameters; determining the target fitness function of the particle swarm optimization algorithm based on the objective function of the multi-index control parameter planning model; the objective function is determined based on the calculation formula of the plurality of performance indexes; The particle swarm optimization algorithm is iteratively solved by using the plurality of particles as a target of minimizing the fitness value of the target fitness function, to obtain the optimal governor control parameter.
[0008] In some embodiments, the particle swarm optimization algorithm is iteratively solved by using the plurality of particles as a target of minimizing the fitness value of the target fitness function, to obtain the optimal governor control parameter, including: Step S101, initializing each of the particles, the local optimal position of each of the particles, and the current global optimal particle; Step S102, inputting the governor control parameter corresponding to each of the particles into a preset structure response-control system coupling model for simulation to obtain corresponding model response output data, and determining the fitness value of each of the particles based on the target fitness function and the model response data corresponding to each of the particles; Step S103, updating the local optimal position of each of the particles in the current iteration process and the global optimal particle as a target of minimizing the fitness value; Step S104, judging whether the current iteration number reaches the maximum iteration number or the fitness value of the current global optimal particle converges; if not, updating the position and speed of each of the particles, and jumping to step S102; if yes, executing step S105; Step S105, obtaining the global optimal particle of the particle swarm optimization algorithm, and determining the optimal governor control parameter based on the global optimal particle.
[0009] In some embodiments, the preset structure response-control system coupling model includes a one-dimensional transient flow governing system model and a structure response prediction model; and the step S102 includes: inputting the governor control parameter corresponding to each of the particles into the one-dimensional transient flow governing system model to obtain corresponding guide vane opening data and corresponding unit speed data; inputting the guide vane opening data and the unit speed data corresponding to each of the particles into the structure response prediction model to obtain the pressure pulsation amplitude data and the runner dynamic stress amplitude data corresponding to each of the particles output by the structure response prediction model; the structure response prediction model is trained according to the water turbine governor control parameter sample and the corresponding pressure pulsation data label and runner dynamic stress data label; calculating the target fitness function according to the unit speed data, the pressure pulsation amplitude data, and the runner dynamic stress amplitude data corresponding to each of the particles to obtain the fitness value of each of the particles.
[0010] In some embodiments, before the step of inputting the guide vane opening degree data corresponding to each of the particles and the corresponding unit rotation speed data into the structural response prediction model, the method further comprises: The pressure pulsation amplitude data and the dynamic stress amplitude data of the runner of the hydraulic turbine under different governor control parameter samples are determined by using a three-dimensional fluid-structure coupling model of the hydraulic turbine, to serve as data labels for training of a preset neural network model; Each governor control parameter sample and the corresponding data label thereof are taken as a set of training samples, and a plurality of sets of the training samples are obtained; The preset neural network model is trained by using the plurality of sets of the training samples, to obtain the structural response prediction model.
[0011] In some embodiments, the governor control parameters include PID control parameters and guide vane opening degree segmentation setting parameters.
[0012] A second aspect of the present application relates to a hydraulic turbine governor control device considering structural response, the hydraulic turbine governor control device comprising: A first processing module is configured to determine a multi-index control parameter planning model based on a plurality of performance indexes of a unit runner; the plurality of performance indexes include a pressure pulsation amplitude and a dynamic stress amplitude, and further include a steady-state rotation speed adjustment time and / or a rotation speed fluctuation frequency; A second processing module is configured to take a governor control parameter of a hydraulic turbine as a variable, iteratively solve the multi-index control parameter planning model, and determine an optimal governor control parameter of the hydraulic turbine, to control operation of a hydraulic turbine governor.
[0013] In a third aspect, the present application provides an electronic device, comprising: at least one memory configured to store a program; and at least one processor configured to execute the program stored in the memory, and when the program stored in the memory is executed, the processor is configured to execute the method described in the first aspect or any possible implementation manner of the first aspect.
[0014] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is run on a processor, the processor is caused to execute the method described in the first aspect or any possible implementation manner of the first aspect.
[0015] In a fifth aspect, the present application provides a computer program product, and when the computer program product is run on a processor, the processor is caused to execute the method described in the first aspect or any possible implementation manner of the first aspect.
[0016] It can be understood that the beneficial effects of the above-mentioned second aspect to fifth aspect can be referred to the related description in the first aspect, and will not be repeated here.
[0017] Overall, compared with the prior art, the above technical solutions conceived by the present application have the following beneficial effects: The present application provides a water turbine governor control method and device considering structural response, by studying the influence of load mutation and abnormal disturbance existing in the unit starting process on the structural dynamic response characteristics of the unit, combining the flow field dynamic characteristics and structural dynamic response characteristics in the starting process of the hydroelectric generating unit, and comprehensively constructing a multi-index control parameter planning model containing structural response data and flow field dynamic response data, wherein the structural response data includes pressure fluctuation amplitude and dynamic stress amplitude, and the flow field dynamic response data includes steady-state speed regulation time and / or speed fluctuation frequency, the rapidity, stability and structural safety of the water turbine speed response are comprehensively characterized, and the speed regulator control parameters are taken as decision variables, the model is solved by using a multi-objective optimization strategy, the optimal control parameters of the unit governor can be accurately obtained, the precision and regulation quality of the water turbine governor control are improved, and the safety and efficiency in the starting, speed regulation and smooth running process of the unit can be effectively improved. BRIEF DESCRIPTION OF DRAWINGS
[0018] Figure 1 is a flowchart of a water turbine governor control method considering structural response provided by an embodiment of the present application; Figure 2 is a structural schematic diagram of a water turbine governor control device considering structural response provided by an embodiment of the present application; Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.
[0020] In the present application, the term "and / or" is used to describe the association relationship between the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In the present application, the symbol " / " represents the relationship of or, for example, A / B represents A or B.
[0021] In the present application, the terms "first" and "second" are used to distinguish different objects, rather than to describe the specific order of the objects. For example, the first response message and the second response message are used to distinguish different response messages, rather than to describe the specific order of the response messages.
[0022] In the embodiments of the present application, the word "exemplary" or "for example" is used to mean serving as an example, instance, or illustration. Any embodiment or design described in the embodiments of the present application as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the word "exemplary" or "for example" is used to present concepts in a particular manner.
[0023] In the description of the embodiments of the present application, unless otherwise specified, "a plurality of" means two or more, for example, a plurality of processing units means two or more processing units, and the like, a plurality of elements means two or more elements, and the like.
[0024] In the prior art, the existing optimization research on the control law of the speed regulation system in the starting process of the hydroelectric generating set usually adopts a one-dimensional water hammer model. However, since the one-dimensional water hammer model can only reflect the one-dimensional dynamic characteristics of the flow and pressure in the flow passage system changing with time, it cannot accurately capture the complex three-dimensional unsteady flow behavior inside the water turbine. In the starting and stopping process of the unit, the load mutation and the abnormal disturbance process, the impeller of the water turbine is subjected to the action of hydraulic excitation, and significant periodic dynamic stress and pressure pulsation of the impeller will be generated. It is found through research that the existing optimization method generally ignores the influence of the speed regulator control law on the dynamic stress of the impeller, the structural vibration and the like.
[0025] Specifically, in the rapid starting and stopping of the unit and the sharp change of the load, the pressure distribution inside the flow field rapidly adjusts, and the complex unsteady turbulent flow is excited in the guide vane-impeller interaction area, resulting in the generation of dynamic stress with significant amplitude and irregular vibration response of the runner blade. On the one hand, if only the traditional fixed parameter controller (such as fixed PID parameters) is relied on, the guide vane opening degree response cannot be adjusted in time according to the real-time structural change, which is easy to cause the frequency overshoot, the over-shoot and even the instability of the unit; on the other hand, the long-term neglect of the optimization of the speed regulation law of the structural response will accelerate the development of the fatigue cracks of the impeller and shorten the service life of the equipment.
[0026] It should be noted that the various defects of the technical solutions in the prior art above are the results obtained by the inventors after careful practice and research, and therefore, the discovery process of the above problems and the solutions proposed by the embodiments of the present application to the above problems should be the contributions made by the inventors to the present application in the implementation process of the present application.
[0027] To solve the above technical problems, the present application provides a water turbine speed regulator control method and device considering structural response.
[0028] The embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0029] Figure 1is a flowchart of a water turbine governor control method considering structural response provided by the embodiment of the present application, as shown in Figure 1 , comprising: Step S1, determining a multi-index control parameter planning model based on a plurality of performance indexes of a unit runner; the plurality of performance indexes include pressure pulsation amplitude and dynamic stress amplitude, and further include steady-state speed regulation time and / or speed fluctuation times; Step S2, taking the governor control parameter of the water turbine as a variable, iteratively solving the multi-index control parameter planning model to determine the optimal governor control parameter of the water turbine, so as to control the operation of the water turbine governor.
[0030] Specifically, the plurality of performance indexes described in the embodiment of the present application specifically include pressure pulsation amplitude and dynamic stress amplitude, and further include steady-state speed regulation time and / or speed fluctuation times.
[0031] Among them, the pressure pulsation amplitude refers to the amplitude of the periodic / random change of the fluid pressure in the runner flow passage with time or space, and the peak-to-peak value of the pressure pulsation is commonly used; the dynamic stress amplitude refers to the stress fluctuation amplitude of the runner under the combined action of fluid dynamic load, mechanical vibration and thermal stress.
[0032] The steady-state speed regulation time refers to the time when the runner unit speed first enters and continuously remains within the ±5% steady-state error band; the speed fluctuation times refer to the number of zero-crossing points or peak-valley points in the speed response curve n(t), which is specifically determined by analyzing the number of zero-crossing points or local extreme values of the speed response curve.
[0033] The governor control parameter of the water turbine described in the embodiment of the present application can specifically include PID control parameters and / or guide vane opening setting parameters. Among them, the PID control parameters include proportional coefficient , integral coefficient , and differential coefficient ; the guide vane opening setting parameters include first segment guide vane opening set value and second segment guide vane opening set value , here, and are respectively used for the nonlinear segment guide vane adjustment strategy of the governor, represents the first control switching point, i.e. the first segment guide vane adjustment speed in the two-segment starting strategy; represents the second control segment threshold value, which is used to define the fast opening rate of the second segment guide vane response in the two-segment starting strategy, so as to enhance the adjustment performance under strong disturbance.
[0034] In the embodiments of the present application, in step S1, based on the multiple performance indexes of the unit runner, including the pressure fluctuation amplitude and the dynamic stress amplitude, and also including the steady-state speed regulation time and / or the number of speed fluctuations, the target function of the model is jointly determined according to the calculation formulas of the performance indexes, and then the multi-index control parameter planning model can be constructed based on the target function of the model.
[0035] Optionally, the governor control parameter includes a PID control parameter and a guide vane opening segment setting parameter. Specifically, in the embodiments of the present application, the governor control parameter may be expressed as: = .
[0036] Compared with the way of solving the optimal guide vane opening change rule of the governor in the traditional control method by only taking the guide vane opening control rule as the optimization variable, or the governor control mode of only fixing the PID parameter, the method of the present application can further improve the control accuracy of the water turbine governor by simultaneously considering the PID control parameter and the guide vane opening response parameter to construct the governor control parameter, and taking the governor control parameter as the optimization variable for optimization and solving.
[0037] In the embodiments of the present application, in step S2, a variety of bionic optimization algorithms, such as the particle swarm algorithm and the genetic algorithm, can be used to take the governor control parameter of the water turbine as a variable to iteratively solve the multi-index control parameter planning model, so as to solve the optimal governor control parameter of the water turbine, and then the operation of the water turbine governor can be controlled according to the optimal governor control parameter.
[0038] The water turbine governor control method considering structural response of the embodiments of the present application can comprehensively construct a multi-index control parameter planning model containing structural response data and flow field dynamic response data by researching the influence of load mutation and abnormal disturbance existing in the unit starting process on the structural dynamic response characteristics of the unit, combining the flow field dynamic characteristics and the structural dynamic response characteristics in the unit starting process, and comprehensively constructing the multi-index control parameter planning model containing the structural response data and the flow field dynamic response data. The structural response data includes the pressure fluctuation amplitude and the dynamic stress amplitude, and the flow field dynamic response data includes the steady-state speed regulation time and / or the number of speed fluctuations, which comprehensively represent the rapidity, stability and structural safety of the water turbine speed response. Taking the governor control parameter as the decision variable, the model is solved by using a multi-objective optimization strategy, so as to accurately obtain the optimal control parameter of the unit governor, improve the accuracy and regulation quality of the water turbine governor control, and effectively improve the safety and efficiency in the unit starting, speed regulation and smooth running process.
[0039] Based on the content of the above embodiments, as an optional embodiment, step S2 is to solve the multi-index control parameter planning model iteratively with the governor control parameters of the hydraulic turbine as variables to determine the optimal governor control parameters of the hydraulic turbine, including: Randomly generating a plurality of particles; each particle includes a set of governor control parameters; Based on the objective function of the multi-index control parameter planning model, determine the target fitness function of the particle swarm optimization algorithm; the objective function is determined based on the calculation formula of the plurality of performance indicators; With the goal of minimizing the fitness value of the target fitness function, use multiple particles to perform particle swarm optimization algorithm iteration to obtain the optimal governor control parameters.
[0040] Specifically, in the embodiments of the present application, each particle can represent a governor control parameter combination .
[0041] Further, the optimization target includes: The rapidity index is the steady-state speed regulation time, and its calculation formula is as follows:
[0042] In the formula, is the speed change, is the steady-state speed, is the allowable error band, which is generally ±5% of the steady-state error band.
[0043] The stability index is the number of speed fluctuations under the one-dimensional transient flow speed regulation system model, and its calculation formula is as follows: ; In the formula, is the reference speed; is the discrete sampling time; is an indicator function, which is 1 when the bracket is true, and 0 otherwise.
[0044] It should be noted that the one-dimensional transient flow speed regulation system model is a commonly used one-dimensional transient flow mathematical model in existing hydraulic turbine speed regulation systems, which specifically includes: a speed regulator, a servo hydraulic mechanism, a draft tube, and a unit load module, which takes the guide vane opening curve as input, and can be used to output the unit speed response curve .
[0045] The structural safety index is the peak-to-peak value of pressure pulsation and the rotor dynamic stress amplitude under the three-dimensional coupled model, and the calculation formula of the peak-to-peak value of pressure pulsation and the rotor dynamic stress amplitude is as follows: ; In the formula, ; The rotating wheel dynamic stress amplitude can take the maximum rotating wheel dynamic stress amplitude, and the calculation formula is as follows: ; ; In the formula, p indicates the index of the measuring point on the rotating wheel, indicates the dynamic stress amplitude of each measuring point, p is the maximum stress in a stress cycle, is the minimum stress in a stress cycle, indicates the maximum value in all measuring points.
[0046] The above indexes constitute a multi-objective optimization evaluation function , which constitutes the objective function of the multi-index control parameter planning model and can be used as the objective fitness function of the subsequent particle swarm optimization algorithm.
[0047] Further, in the embodiments of the present application, the particle swarm optimization algorithm is iteratively solved by using multiple particles to minimize the fitness value of the objective fitness function, and the governor parameter solution set approximating the Pareto optimal front is obtained through multi-objective particle swarm optimization algorithm iteration update. The final non-inferior solution is the optimal governor control parameter considering the regulation performance and structural safety, which provides parameter reference and decision support for practical application.
[0048] The method of the embodiments of the present application can quickly and accurately solve the optimal governor control parameter by constructing a multi-index control parameter planning model and proposing a multi-objective particle swarm optimization algorithm based on the governor control parameter, and iteratively solving the particle swarm optimization algorithm to minimize the fitness value of the multi-index function.
[0049] Based on the above embodiments, as an optional embodiment, the particle swarm optimization algorithm is iteratively solved by using multiple particles to minimize the fitness value of the objective fitness function, and the optimal governor control parameter is obtained, including: Step S101, initializing each particle, the local best position of each particle, and the current global best particle; Step S102, inputting the governor control parameter corresponding to each particle into a pre-set structure response-control system coupling model for simulation to obtain corresponding model response output data, and determining the fitness value of each particle based on the objective fitness function and the model response data corresponding to each particle; Step S103, updating the local best position of each particle and the global best particle in the current iteration process to minimize the fitness value; Step S104, it is judged whether the current iteration number reaches the maximum iteration number or the fitness value of the current global optimal particle converges; if not, the position and speed of each particle are updated, and the step S102 is jumped to; if yes, the step S105 is executed; Step S105, the global optimal particle of the particle swarm optimization algorithm is obtained, and the optimal governor control parameter is determined based on the global optimal particle.
[0050] Specifically, in the embodiment of the present application, M particles are randomly generated, each particle being a set of decision variables Under the framework of multi-objective particle swarm optimization (MOPSO), each particle represents a set of governor control parameters to be optimized. By randomly generating M initial particles in a five-dimensional parameter space, an initial optimization population can be formed. In step S101, each particle, the local best position of each particle, and the current global best particle are initialized.
[0051] In step S102, the governor control parameters corresponding to each particle are input into a preset structure response-control system coupling model for simulation, the corresponding model response output data can be obtained, and the relevant fitness value calculation can be performed based on the aforementioned target fitness function and the model response data corresponding to each particle, so that the fitness value of each particle can be determined.
[0052] Based on the content of the above embodiment, as an optional embodiment, the preset structure response-control system coupling model includes a one-dimensional transient flow governing system model and a structure response prediction model; step S102 includes: The governor control parameters corresponding to each particle are input into the one-dimensional transient flow governing system model to obtain the corresponding guide vane opening data and the corresponding unit speed data; The guide vane opening data and the unit speed data corresponding to each particle are input into the structure response prediction model to obtain the pressure pulsation amplitude data and the runner dynamic stress amplitude data corresponding to each particle output by the structure response prediction model; the structure response prediction model is trained according to the water turbine governor control parameter sample and the corresponding pressure pulsation data label and runner dynamic stress data label; The target fitness function is calculated according to the unit speed data, the pressure pulsation amplitude data, and the runner dynamic stress amplitude data corresponding to each particle, so as to obtain the fitness value of each particle.
[0053] Specifically, in the embodiment of the present application, the preset structure response-control system coupling model specifically includes a one-dimensional transient flow governing system model and a structure response prediction model.
[0054] Firstly, the one-dimensional transient flow governing system model is called, and the governing parameters corresponding to each particle are input into the one-dimensional transient flow governing system model to obtain the guide vane opening response curve y(t) under the corresponding governing parameters, and further to solve the unit speed response curve n(t), i.e. to obtain the corresponding guide vane opening data and the corresponding unit speed data. Subsequently, the time domain data of y(t) and n(t) can be used as input to call the trained structure response prediction model, such as the BP neural network model, to predict the corresponding runner pressure pulsation amplitude data and dynamic stress amplitude data.
[0055] For each particle (i.e. a set of governing parameters), the structure response-control system coupling model needs to be called for complete simulation evaluation, and the specific calculation process is as follows: Step one, input the parameters corresponding to the current particle into the one-dimensional transient flow governing system model to simulate the unit operation response, including the guide vane opening response curve data y(t) and the unit speed response curve data n(t).
[0056] Step two, extract the dynamic response information from the unit speed response curve data n(t) to calculate the speed characteristic indexes, including: steady-state speed regulation time : the time required for the speed to enter the ±5% steady-state error band and to remain stable; speed fluctuation times : estimated by the number of zero-crossing or peak-valley points in the speed response curve data n(t).
[0057] Specifically, the unit speed response curve data n(t) can be substituted into the calculation formulas of the steady-state speed regulation time and the speed fluctuation times in the aforementioned objective fitness function to calculate the steady-state speed regulation time and the speed fluctuation times .
[0058] Step three, the structure response prediction model is called, and the guide vane opening data corresponding to the current particle and the unit speed data are input into the structure response prediction model to output the corresponding pressure pulsation amplitude data and the corresponding runner dynamic stress amplitude data. Using the pressure pulsation amplitude data corresponding to the particle and the runner dynamic stress amplitude data, combined with the calculation formulas of the pressure pulsation peak-to-peak value and the runner dynamic stress amplitude in the aforementioned objective fitness function, the pressure pulsation peak-to-peak value and the runner dynamic stress amplitude can be calculated.
[0059] Step four, the fitness evaluation vector F= can be finally constructed as the fitness index of the current particle.
[0060] The method of the embodiment of the application can form a structure response-control system coupling model by embedding the trained structure response prediction model in the one-dimensional transient flow governing system model of the hydraulic turbine, and can calculate the speed response and the structure response simultaneously when the control parameters of the governor are input, so as to facilitate subsequent multi-objective evaluation and greatly improve the efficiency of the governor control.
[0061] Further, in step S103, the local optimal position of each particle in the current iteration process and the global optimal particle are updated with the minimum fitness value as the target.
[0062] Specifically, in the embodiment of the application, non-dominated sorting is adopted: the evaluation vectors of all particles are input into a multi-objective optimization judgment module, and non-dominated sorting is performed according to the Pareto dominance relationship. The individual optimal position of each particle (i.e. the optimal fitness value in history), the global non-inferior solution set (Pareto optimal set) in the whole population, and the external archive set (external elite library) are updated according to the sorting result, so as to provide a reference for guiding the motion direction of the particles in the next step.
[0063] The implementation of updating the particles is as follows: the next generation of particle swarm can be generated under the joint action of the inertia weight, the individual optimal guidance and the global optimal guidance according to the speed and position updating rules set in the MOPSO algorithm. For each dimension (i.e. the control parameter of the governor), the updating is performed through the following formula: ; ; wherein, xi is the position of the current particle (i.e. a set of control parameters), vi is the speed vector, pi and gi are the individual historical optimal and global non-inferior guidance positions, w , c 1, r 1, c 2, r 2are the speed and position updating coefficients of the corresponding parameters.
[0064] Further, in step S104, it is judged whether the current iteration number reaches the maximum iteration number or the fitness value of the current global optimal particle converges (or the Pareto front solution set in the external elite archive changes continuously for a certain number of generations and tends to be stable); if not, the position and speed of each particle are updated, and the step S102 is jumped to; if yes, the iteration is terminated, and the following step S105 is performed.
[0065] Step S105, the final output is a set of non-inferior controller parameter solution set, each set of parameters corresponds to an optimal strategy configuration balancing speed regulation performance and structural response, that is, the global optimal particle of the particle swarm optimization algorithm is obtained, and based on the global optimal particle, the optimal governor control parameter is determined, thereby providing diversified adjustment strategy support for subsequent engineering selection and implementation.
[0066] The method of the embodiment of the application can further greatly improve the accuracy and efficiency of the optimization of the governor control parameter by fully combining the flow field dynamic characteristics and the structural dynamic response characteristics in the starting process of the hydroelectric unit and continuously iteratively optimizing the control parameter of the turbine governor by using the PSO algorithm.
[0067] Based on the content of the above embodiment, as an optional embodiment, before the guide vane opening degree data corresponding to each particle and the corresponding unit speed data are input into the structural response prediction model, the method further includes: The three-dimensional fluid-structure coupling model of the turbine is used to determine the pressure pulsation amplitude data and dynamic stress amplitude data of the runner of the turbine under different governor control parameter samples, so as to serve as the data label for training of the preset neural network model; Each governor control parameter sample and the corresponding data label thereof are taken as a set of training samples, and multiple sets of training samples are obtained; The preset neural network model is trained by using the multiple sets of training samples, so as to obtain the structural response prediction model.
[0068] Specifically, in the embodiment of the application, in order to quickly predict the influence of the governor control parameter on the structural response, the three-dimensional fluid-structure coupling model of the turbine is used to collect the simulation data of the runner pressure pulsation amplitude and the dynamic stress amplitude corresponding to a large number of different starting process conditions after completing the runner speed regulation simulation, and a preset neural network model taking the governor control parameter as a sample and taking the structural response index as an output is constructed. The preset neural network model can specifically adopt a back propagation (BP) neural network model.
[0069] The description of the BP neural network model is as follows: The calculation formula from the input layer to the hidden layer is as follows: ; Wherein, is the weight matrix from the input layer to the hidden layer, is the bias vector, is the activation function of the hidden layer.
[0070] The calculation formula from the hidden layer to the output layer is as follows: ; Wherein, is the weight matrix from the input layer to the hidden layer, bias vector, activation function of the output layer.
[0071] Specifically, first, a three-dimensional fluid-structure coupling model of the spiral case, stay vane, impeller and draft tube is constructed according to the unit full-flow passage CAD drawing, and a transient flow field numerical simulation is performed by using a CFD software to obtain the instantaneous pressure distribution and flow velocity field under each typical working condition; then the flow field load data output by the CFD simulation is mapped to the surface of the structural finite element model to construct a fluid-structure coupling boundary; then the dynamic stress response of the impeller structure under different loads is solved in the finite element analysis software to obtain the time history response data of the rotor dynamic stress amplitude; finally, the above process is repeated under multiple stay vane opening, flow rate and rotating speed combinations to extract the pressure fluctuation amplitude and rotor dynamic stress amplitude data under the working condition corresponding to different governor control parameter samples. Among them, the flow rate and rotating speed are determined based on the PID control parameters of the unit. Thus, the pressure fluctuation amplitude data and dynamic stress amplitude data of the turbine runner under different governor control parameter samples can be obtained and used as data labels for training of a preset neural network model.
[0072] Further, each governor control parameter sample (stay vane opening and each PID control parameter) is paired with the corresponding structural response data label (pressure fluctuation amplitude and dynamic stress amplitude) obtained by the simulation to construct multiple training samples.
[0073] Further, by calling a one-dimensional transient flow governing system model, the corresponding governor control parameter sample in each training sample is input into the one-dimensional transient flow governing system model to simulate and generate unit operation response data samples, including stay vane opening data samples and unit rotating speed data samples, and the corresponding structural response data label is used to iteratively train the preset neural network model until the maximum number of iterations is reached or the model convergence condition is met, so that a trained structural response prediction model can be obtained.
[0074] The method of the embodiments of the present application uses each governor control parameter sample and its corresponding structural response data label as a group of training samples, trains the preset neural network model using multiple training samples, forms a nonlinear mapping relationship between the control parameters and the structural responses, so that the trained structural response prediction model can be efficiently called in the optimization iteration process, avoiding the need to run complex three-dimensional CFD simulation every time for evaluation, and is conducive to further improving the efficiency of the turbine governor control.
[0075] The water turbine governor control device considering structural response provided by the present application is described below, and the water turbine governor control device considering structural response described below can be mutually corresponding to the water turbine governor control method considering structural response described above.
[0076] Figure 2 is a structural diagram of a water turbine governor control device considering structural response provided by an embodiment of the present application, as shown in Figure 2 includes: A first processing module 10 is configured to determine a multi-index control parameter planning model based on a plurality of performance indexes of a runner of a unit; the plurality of performance indexes include a pressure pulsation amplitude and a dynamic stress amplitude, and further include at least one of a steady-state rotational speed regulation time and a rotational speed fluctuation frequency; A second processing module 20 is configured to solve the multi-index control parameter planning model iteratively with a governor control parameter of a water turbine as a variable, to determine an optimal governor control parameter of the water turbine, so as to control operation of the water turbine governor.
[0077] It can be understood that the detailed function implementation of each unit / module described above can refer to the description in the foregoing method embodiments, which will not be repeated here.
[0078] It should be understood that the above device is used to execute the method in the above embodiments, and the corresponding program modules in the device have similar implementation principles and technical effects to those described in the above method, and the working process of the device can refer to the corresponding process in the above method, which will not be repeated here.
[0079] The water turbine governor control device considering structural response provided by the embodiment of the present application, by studying the influence of load mutation and abnormal disturbance existing in the unit starting process on the dynamic response characteristics of the unit structure, combining the flow field dynamic characteristics and the structural dynamic response characteristics in the unit starting process, and comprehensively constructing a multi-index control parameter planning model containing structural response data and flow field dynamic response data, wherein the structural response data includes a pressure pulsation amplitude and a dynamic stress amplitude, and the flow field dynamic response data includes a steady-state rotational speed regulation time and / or a rotational speed fluctuation frequency, the rapidity, stability and structural safety of the water turbine speed response are comprehensively characterized, and the governor control parameter is taken as a decision variable, the model is solved by using a multi-objective optimization strategy, the optimal control parameter of the unit governor can be accurately obtained, the precision and regulation quality of the water turbine governor control are improved, and the safety and efficiency in the unit starting, speed regulation and smooth running process can be effectively improved.
[0080] Based on the method in the above embodiments, an electronic device is provided, as shown in Figure 3As shown, the electronic device can include a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 complete communications with each other through the communications bus 340. The processor 310 can invoke a logical instruction in the memory 330 to execute the method in the above-described embodiments.
[0081] In addition, the logical instruction in the memory 330 described above can be implemented in the form of a software functional unit and sold or used as an independent product, and can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or in other words the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
[0082] Based on the method in the above-described embodiments, the embodiments of the present application provide a computer-readable storage medium, which stores a computer program, and when the computer program runs on a processor, the processor executes the method in the above-described embodiments.
[0083] Based on the method in the above-described embodiments, the embodiments of the present application provide a computer program product, and when the computer program product runs on a processor, the processor executes the method in the above-described embodiments.
[0084] It can be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor can be a microprocessor, or any conventional processor.
[0085] The method steps in the embodiments of the present application can be implemented by means of hardware, or by means of a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in a Random Access Memory (RAM), a flash memory, a Read-only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), a register, a hard disk, a mobile hard disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.
[0086] In the above embodiments, all or part of the embodiments can be implemented by means of software, hardware, firmware, or any combination thereof. When implemented by means of software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted by means of the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by means of a wire (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more available media sets. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as DVD), or semiconductor media (such as Solid State Disk (SSD)), etc.
[0087] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of differentiation, and do not limit the scope of the embodiments of the present application.
[0088] It should be understood that the terms such as "include" and "may include" used in the present application indicate the presence of the disclosed functions, operations, or constituent elements, and do not limit one or more additional functions, operations, and constituent elements. In the present application, terms such as "include" and / or "have" can be interpreted to denote a specific characteristic, number, operation, constituent element, component, or a combination thereof, but can not be interpreted to exclude the presence or possibility of one or more other characteristics, numbers, operations, constituent elements, components, or combinations thereof.
[0089] The above description is merely that of specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present application, and such changes or substitutions should be encompassed within the scope of protection of the present application. Therefore, the scope of protection of the present application should be construed according to the scope of protection of the claims.
Claims
1. A hydro-turbine governor control method considering structural response, characterized by, The method comprises the steps of: determining a multi-index control parameter planning model based on a plurality of performance indexes of a unit runner, wherein the plurality of performance indexes comprise a pressure pulsation amplitude and a dynamic stress amplitude, and further comprise a steady-state speed regulation time and / or a speed fluctuation frequency; taking a governor control parameter of the hydraulic turbine as a variable, iteratively solving the multi-index control parameter planning model to determine an optimal governor control parameter of the hydraulic turbine, and controlling operation of the hydraulic turbine governor.
2. The method of claim 1, wherein, The step of taking the governor control parameter of the hydraulic turbine as the variable, iteratively solving the multi-index control parameter planning model to determine the optimal governor control parameter of the hydraulic turbine comprises: randomly generating a plurality of particles, wherein each particle comprises a set of governor control parameters; determining a target fitness function of a particle swarm optimization algorithm based on a target function of the multi-index control parameter planning model, wherein the target function is determined based on a calculation formula of the plurality of performance indexes; taking minimizing a fitness value of the target fitness function as a target, iteratively solving the particle swarm optimization algorithm by using the plurality of particles to obtain the optimal governor control parameter.
3. The method of claim 2, wherein, The step of taking minimizing the fitness value of the target fitness function as the target, iteratively solving the particle swarm optimization algorithm by using the plurality of particles to obtain the optimal governor control parameter comprises: Step S101, initializing each particle, a local optimal position of each particle, and a current global optimal particle; Step S102, inputting the governor control parameter corresponding to each particle into a preset structure response-control system coupling model for simulation to obtain corresponding model response output data, and determining a fitness value of each particle based on the target fitness function and the model response data corresponding to each particle; Step S103, taking minimizing the fitness value as a target, updating the local optimal position of each particle in the current iteration process and the global optimal particle; Step S104, determining whether a current iteration number reaches a maximum iteration number or a fitness value of a current global optimal particle converges; if not, updating a position and a speed of each particle, and jumping to Step S102; if yes, executing Step S105; Step S105, obtaining a global optimal particle of the particle swarm optimization algorithm, and determining the optimal governor control parameter based on the global optimal particle.
4. The method of claim 3, wherein, The preset structure response-control system coupling model comprises a one-dimensional transient flow governing system model and a structure response prediction model; and Step S102 comprises: inputting the governor control parameter corresponding to each particle into the one-dimensional transient flow governing system model to obtain corresponding guide vane opening data and corresponding unit speed data; inputting the guide vane opening data and the unit speed data corresponding to each particle into the structure response prediction model to obtain pressure pulsation amplitude data and runner dynamic stress amplitude data corresponding to each particle output by the structure response prediction model; the structure response prediction model is trained according to a hydraulic turbine governor control parameter sample and corresponding pressure pulsation data labels and runner dynamic stress data labels. According to the corresponding unit rotation speed data, corresponding pressure pulsation amplitude data and corresponding runner dynamic stress amplitude data of each particle, the target fitness function is calculated to obtain the fitness value of each particle.
5. The method of claim 4, wherein, Before the guide vane opening data and the corresponding unit rotation speed data of each particle are input into the structure response prediction model, the method further comprises: A three-dimensional fluid-structure coupling model of the hydraulic turbine is used to determine the pressure pulsation amplitude data and the dynamic stress amplitude data of the runner of the hydraulic turbine under different governor control parameter samples, so as to serve as data labels for training of a preset neural network model; Each governor control parameter sample and its corresponding data label are used as a set of training samples, and multiple sets of the training samples are obtained; The preset neural network model is trained by using the multiple sets of training samples to obtain the structure response prediction model.
6. The method of claim 1-5, wherein, The governor control parameters include PID control parameters and guide vane opening segment setting parameters.
7. A hydro-turbine governor control device considering structural response, characterized by, Comprise: The first processing module is configured to determine a multi-index control parameter planning model based on a plurality of performance indexes of the unit runner; the plurality of performance indexes include pressure pulsation amplitude and dynamic stress amplitude, and further include steady-state rotation speed adjustment time and / or rotation speed fluctuation times; The second processing module is configured to take the governor control parameters of the hydraulic turbine as variables, iteratively solve the multi-index control parameter planning model, and determine the optimal governor control parameters of the hydraulic turbine to control the operation of the hydraulic turbine governor.
8. An electronic device, comprising: Comprise a memory, one or more processors; The memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprising computer instructions; The one or more processors invoke the computer instructions to cause the electronic device to perform the method of any one of claims 1-6.
9. A computer readable storage medium comprising instructions, characterized in that: When the instructions run on an electronic device, the electronic device is caused to perform the method of any one of claims 1-6.
10. A computer program product comprising a computer program or instructions, characterized in that: When the computer program or instructions run on an electronic device, the electronic device is caused to perform the method of any one of claims 1-6.