Hydroelectric generating set adaptive PID controller design method based on whale optimization algorithm and BP neural network

Abstract

The invention discloses a hydroelectric generating set adaptive PID controller design method based on a whale optimization algorithm and a BP neural network. Comprising the following steps: S1, constructing a numerical simulation model of the water turbine regulating system; s2, working conditions are divided according to the water head and the guide vane opening degree; s3, constructing a comprehensive objective function of the whale optimization algorithm; s4, obtaining an optimal PID parameter under a typical working condition based on a whale optimization algorithm; s5, determining the number of hidden layer neurons of the controller neural network model; and S6, combining the optimal PID parameter data set and a BP neural network to construct a controller neural network model taking the water head and the guide vane opening as input and KP or KI as output. According to the hydroelectric generating set PID parameter optimization method considering the runner stress and the blade pressure, the influence of the PID parameters on the runner stress and the blade pressure can be fully considered, and safe and stable operation of the hydroelectric generating set is effectively guaranteed.

Description

Technical Field

[0001] The invention belongs to the technical field of safe and stable operation of hydropower units, and in particular relates to a design method for an adaptive PID controller of a hydropower unit based on a whale optimization algorithm and a BP neural network. Background Art

[0002] Hydropower units occupy an important position in modern power systems, and their operating efficiency and stability directly affect the overall performance of the power system. In order to ensure the efficient operation of hydropower units, the design of the control system is particularly critical. Traditional PID (proportional-integral-differential) controllers are widely used in the control of hydropower units due to their simplicity and effectiveness. However, the operating environment of hydropower units is complex and changeable, and has the characteristics of nonlinearity, time-varying and strong coupling, making it difficult for traditional PID controllers to maintain optimal performance under various operating conditions;

[0003] Due to the nonlinear and time-varying characteristics of hydropower units, traditional fixed-parameter PID controllers are difficult to guarantee optimal performance under different operating conditions. Therefore, it is particularly important to design a PID controller that can adaptively adjust control parameters according to the operating state. The adaptive PID controller can adjust parameters online, improve the robustness and response speed of the control system, and thus optimize the operating performance of the hydropower unit.

[0004] The whale optimization algorithm is a new type of swarm intelligence optimization algorithm. The algorithm simulates the predation behavior of humpback whales, especially its "bubble net attack" strategy, and solves complex optimization problems through bionic principles. The whale optimization algorithm has the advantages of strong global search ability, fast convergence speed, and easy implementation. It is widely used in function optimization, engineering design optimization, and machine learning. Back propagation neural network (BP neural network) is a classic artificial neural network that is widely used in pattern recognition, function approximation, and prediction. BP neural network adjusts the weights and biases of the network through the back propagation algorithm to minimize the prediction error. Its powerful nonlinear mapping ability enables it to effectively handle complex nonlinear problems. Combining the whale optimization algorithm with the BP neural network to design an adaptive PID controller can effectively solve the shortcomings of the traditional PID controller. Specifically, the whale optimization algorithm is used to optimize the parameters of the PID controller under typical working conditions, and then the BP neural network is used to realize offline training and online adaptive adjustment of the control parameters, so that the controller can be adaptively adjusted according to the real-time working conditions, improving the control accuracy and system stability.

[0005] In view of the limitation that traditional PID controllers do not adequately consider the impact of operating condition changes, it is necessary to propose a new design method for hydropower unit PID controllers to comprehensively consider the impact of operating condition changes on the regulation quality of the turbine regulation system. This optimization method will enable hydropower units to achieve more efficient and stable operation under different working conditions, thereby extending equipment life, reducing maintenance costs and improving power generation efficiency. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a design method for an adaptive PID controller for a hydropower unit based on a whale optimization algorithm and a BP neural network. The PID controller design method designed by the present invention, which takes into account the influence of operating condition changes, can fully consider the influence of operating condition changes on the regulation quality of the turbine regulation system, and effectively ensure the safe and stable operation of the hydropower unit.

[0007] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0008] A design method for adaptive PID controller of hydropower unit based on whale optimization algorithm and BP neural network, the steps are as follows:

[0009] S1, construct a numerical simulation model of the turbine regulation system;

[0010] S2, divided into operating conditions according to water head and guide vane opening;

[0011] S3, constructs the comprehensive objective function of the whale optimization algorithm;

[0012] S4, obtain the optimal PID parameters under typical working conditions based on the whale optimization algorithm;

[0013] S5, determining the number of hidden layer neurons of the controller neural network model;

[0014] S6, combining the optimal PID parameter data set and BP neural network to construct a K P or K I The controller neural network model is the output.

[0015] Preferably, in step S1, the numerical simulation model of the turbine regulation system is built based on the Octave tool, and the numerical simulation model of the turbine regulation system includes a water diversion system model, a turbine model, a generator and power grid model, and a speed governor and follow-up system model.

[0016] Preferably, the specific method of step S2 is:

[0017] At the minimum water head H min With maximum head H max The water head is divided into two groups according to the interval H. DDivide; then under the divided water head, at the no-load opening Y 空载 With full opening Y max By interval Y D The guide vane opening is divided to realize the working condition division, and the obtained working condition is called the typical working condition.

[0018] Preferably, the step S3 is specifically:

[0019] A comprehensive objective function considering overshoot, backshoot, rise time and standard ITAE indicators is constructed; among them, J ITAE It is a commonly used objective function for PID parameter optimization, as shown in the following formula:

[0020]

[0021] Where t is the actual time; t s is the total simulation time; e(t) is the integral of the turbine control signal error; J ITAE represents the standard ITAE index;

[0022] Comprehensive objective function J including overshoot, backshoot, rise time and standard ITAE indicators 综合 As shown below:

[0023]

[0024] In the formula, σ1 is the overshoot; σ2 is the backshoot; t r is the rise time; ω1, ω2 and ω3 are weight coefficients.

[0025] Preferably, the step S4 is specifically:

[0026] Based on the whale optimization algorithm with strong optimization ability, the optimal PID parameters of the hydropower unit controller are obtained under various typical operating conditions.

[0027] Preferably, the step S5 is specifically:

[0028] First, the maximum number of hidden layer neurons is determined according to the empirical formula, and then the sensitivity analysis of the number of hidden layer neurons is carried out to determine the reasonable number of hidden layer neurons in the controller neural network model; the empirical formula for the number of hidden layer neurons is:

[0029]

[0030] Where l is the number of hidden layer nodes, m is the number of input layer nodes, n is the number of output layer nodes, and a is a constant between 0 and 10.

[0031] Preferably, the step S6 is specifically:

[0032] Combine the optimal PID parameter data set and BP neural network to build a K P or K I The controller neural network model is the output.

[0033] Preferably, the construction formulas of the water system model, turbine model, generator and power grid model, speed regulator and servo system model are as follows:

[0034] 1) Water diversion system model:

[0035] The water diversion system adopts a rigid water hammer model, which is mathematically described as:

[0036] G h (s)=-T w s;

[0037] Where T w is the water flow inertia time constant.

[0038] 2) Generator and grid model:

[0039] Considering an infinite power grid, the generator and load transfer functions are:

[0040]

[0041] Where T a is the unit inertia time constant, e g is the generator load self-regulation coefficient;

[0042] 3) Governor model:

[0043] The transfer function of the linear part of the PID controller is;

[0044]

[0045] Where: T 1v is the time constant of the differential link; u is the controller output; e is the tracking error; K P , K I and K D are proportional, integral and differential gains respectively; considering the actual situation, K is taken when the unit is running in speed or power mode D =0, take K in no-load operation mode D are the original parameters of the power plant;

[0046] 4) Follow-up system model:

[0047] The servo system contains nonlinear links such as delay, saturation, speed limit, dead zone, etc. The transfer function of its linear part is;

[0048]

[0049] Where: K y is the comprehensive amplifier coefficient; T y1 and T y are the reaction time constants of the intermediate servomotor and the main servomotor respectively;

[0050] 5) Turbine model:

[0051] Based on the neural network, a flow characteristic neural network model and a torque characteristic neural network model are constructed with unit speed and guide vane opening as input and turbine flow and torque as output respectively.

[0052] A hydropower unit adaptive PID controller design system based on a whale optimization algorithm and a BP neural network adopts the hydropower unit adaptive PID controller design method based on a whale optimization algorithm and a BP neural network, comprising:

[0053] Octave simulation module: used to build a numerical simulation model of the turbine regulation system;

[0054] Data analysis and classification module: used to classify working conditions according to water head and guide vane opening;

[0055] Optimization algorithm module: used to construct the comprehensive objective function of the whale optimization algorithm;

[0056] PID automatic optimization module: used to obtain the optimal PID parameters under typical working conditions based on the whale optimization algorithm;

[0057] Neural network design module: used to determine the number of hidden layer neurons of the controller neural network model;

[0058] Machine learning modeling module: used to combine the optimal PID parameter data set and BP neural network to build a K P or K I The controller neural network model is the output.

[0059] A computer device comprising:

[0060] one or more processors;

[0061] The processor is used to store one or more programs;

[0062] When the one or more programs are executed by the one or more processors, a method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network is implemented.

[0063] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed, a design method for a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network is implemented as described.

[0064] The present invention can achieve the following beneficial effects:

[0065] The PID controller design method designed by the present invention taking into account the influence of operating condition changes can fully consider the influence of operating condition changes on the regulation quality of the turbine regulation system, and effectively ensure the safe and stable operation of the hydropower unit.

[0066] As the core equipment for power generation in hydropower stations, the safe and stable operation of hydropower units has become a hot topic in the industry. Aiming at the limitation that traditional PID controllers do not take into account the changes in working conditions, this paper proposes a design method for an adaptive PID controller for hydropower units based on a whale optimization algorithm and a BP neural network.

[0067] The beneficial effect of the present invention is that: under the condition of ensuring the conventional regulation requirements of the hydropower unit, the obtained adaptive PID parameters fully consider the changes in operating conditions and have good regulation quality, effectively ensuring the safe and stable operation of the hydropower unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0069] Figure 1 Designing steps for the method of the present invention;

[0070] Figure 2 The calculation process of the whale optimization algorithm of the present invention;

[0071] Figure 3 It is a schematic diagram of the BP neural network training process of the present invention;

[0072] Figure 4 It is a schematic diagram of the adaptive PID controller of the present invention. DETAILED DESCRIPTION

[0073] The preferred solution is Figures 1 to 4 As shown in the figure, a design method of adaptive PID controller for hydropower units based on whale optimization algorithm and BP neural network is proposed.

[0074] S1, build a numerical simulation model of the turbine regulation system; the specific operations are as follows:

[0075] The simulation model of the turbine regulation system is built based on Octave tool. The simulation model includes the water diversion system model, turbine model, generator and power grid model, speed governor and follow-up system model.

[0076] 1) Water diversion system model

[0077] For simplicity, the water diversion system can adopt a rigid water hammer model, which is mathematically described as:

[0078] G h (s)=-T w s (1);

[0079] 2) Generator and grid model

[0080] Considering an infinite power grid, the generator and load transfer functions are:

[0081]

[0082] Where T a is the unit inertia time constant, e g is the generator load self-regulation coefficient.

[0083] 3) Speed ​​​​regulator model

[0084] The transfer function of the linear part of the PID controller is shown in formula (3).

[0085]

[0086] Where: T 1v is the time constant of the differential link; u is the controller output; e is the tracking error; K P , K I and K D They are proportional, integral and differential gains respectively. Considering the actual situation, when the unit is running in speed or power mode, take K D =0, take K in no-load operation mode D These are the original parameters of the power plant.

[0087] 4) Follow-up system model

[0088] The servo system contains nonlinear links such as delay, saturation, speed limit, and dead zone. The transfer function of its linear part is shown in formula (4).

[0089]

[0090] Where: K y is the comprehensive amplifier coefficient; T y1 and T y are the reaction time constants of the intermediate servomotor and the main servomotor respectively.

[0091] 5) Turbine model

[0092] To ensure the accuracy of the model, a flow characteristic neural network model (DCNN, Q11 =Q 11 (n 11 , Y)) and torque characteristic neural network model (TCNN, M 11 =M 11 (n 11 , Y)).

[0093] S2, divide the working conditions according to the water head and guide vane opening; the specific operation is as follows:

[0094] At the minimum water head H min With maximum head H max The water head is divided into two groups according to the interval H. D Divide; then under the divided water head, at the no-load opening Y 空载 With full opening Y max By interval Y D The guide vane opening is divided to realize the working condition division, and the obtained working condition is called the typical working condition.

[0095] S3, construct the comprehensive objective function of the whale optimization algorithm; the specific operations are as follows:

[0096] Construct a system that considers overshoot, reverse shoot, rise time and standard ITAE index (J ITAE ) is the comprehensive objective function.

[0097] Among them, J ITAE It is a commonly used objective function for PID parameter optimization, as shown in the following formula:

[0098]

[0099] Where t is the actual time; t s is the total simulation time; e(t) is the integral of the turbine control signal error.

[0100] Contains overshoot, reverse shoot, rise time and standard ITAE indicators (J ITAE )’s comprehensive objective function J 综合 As shown below:

[0101]

[0102] In the formula, σ1 is the overshoot; σ2 is the backshoot; t r is the rise time; ω1, ω2 and ω3 are weight coefficients.

[0103] S4, based on the whale optimization algorithm to obtain the optimal PID parameters under typical working conditions; the specific operations are as follows:

[0104] Based on the whale optimization algorithm with strong optimization ability, the optimal PID parameters of the hydropower unit controller are obtained under various typical operating conditions.

[0105] Among them, the whale optimization algorithm (WOA) is a natural metaheuristic algorithm that searches for the optimal solution by simulating the bubble net predation behavior of humpback whales. The algorithm has few parameters, simple mechanism, and does not require relevant gradient information. Local search and global search are performed alternately according to parameter changes, which can effectively avoid the emergence of local optimal solutions. The WOA algorithm simulates the hunting behavior of humpback whales, which mainly includes three stages: surrounding prey, bubble net attack, and searching for prey. The formula for the surrounding prey stage is as follows:

[0106]

[0107] Where: t represents the number of iterations; t max Indicates the maximum number of iterations; is the coefficient vector; A random number between the range [0, 1]; represents the search particle, Represents the target prey, which is the position vector of the current optimal solution, and is continuously updated in iterations to obtain a better solution; is the convergence factor that decreases linearly from 2 to 0 during the iteration process.

[0108] WOA mathematically models the attack behavior of bubble networks through the shrinking and surrounding mechanism and the spiral updating mechanism. These two methods are used alternately according to the probability p (p is a probability randomly generated from [0, 1]). When p < 0.5, the shrinking and surrounding mechanism is used; when p > 0.5, the spiral mechanism is used to update the position of the search particle, that is:

[0109]

[0110] Where: b is the shape parameter of the logarithmic spiral, l is a random number between [-1, 1], Represents the distance between the search particle and the current optimal solution.

[0111] It decreases linearly, resulting in The value of will be Changes between. Then the search particles gradually surround the current optimal solution, which belongs to the local optimization stage in WOA. The distance data will be randomly updated, causing the whale to deviate from the original optimal individual and update the population according to the random position to perform a global search. In the process of searching for prey, its mathematical model is defined as follows:

[0112]

[0113] In the formula, represents a search particle randomly selected from the population.

[0114] The execution of the WOA algorithm starts with a set of randomly initialized parameters, and saves the best solution based on the calculation result of the fitness function. Then, the parameters are updated according to the above search mechanism, and the loop is iterated to the maximum number of times. Finally, the WOA algorithm terminates and outputs the global optimal solution.

[0115] S5, determining the number of hidden layer neurons of the controller neural network model; the specific operation is as follows:

[0116] First, the maximum number of hidden layer neurons is determined according to the empirical formula, and then the sensitivity analysis of the number of hidden layer neurons is carried out to determine the reasonable number of hidden layer neurons in the controller neural network model. The empirical formula for the number of hidden layer neurons is:

[0117]

[0118] Where l is the number of hidden layer nodes, m is the number of input layer nodes, n is the number of output layer nodes, and a is a constant between 0 and 10.

[0119] S6, combining the optimal PID parameter data set and BP neural network to construct a K P or K I is the output controller neural network model. The specific operations are as follows:

[0120] Combine the optimal PID parameter data set and BP neural network to build a K P or K I The controller neural network model is the output.

[0121] The design method of the adaptive PID controller for hydropower units taking into account the changes in operating conditions designed by the present invention includes three parts: constructing a numerical simulation platform for the turbine regulation system, obtaining the optimal PID parameters under typical operating conditions, and constructing a controller neural network model. The implementation steps mainly include: constructing a numerical simulation model of the turbine regulation system; dividing the operating conditions according to the water head and the guide vane opening; constructing a comprehensive objective function of the whale optimization algorithm; obtaining the optimal PID parameters under typical operating conditions based on the whale optimization algorithm; determining the number of hidden layer neurons in the controller neural network model; combining the optimal PID parameter data set and the BP neural network to construct a controller neural network model with the water head and the guide vane opening as input and K P or K I The controller neural network model is the output. The design method of the adaptive PID controller for hydropower units considering operating condition changes can fully consider the impact of operating condition changes on the regulation quality of the PID controller and effectively ensure the safe and stable operation of the hydropower units.

[0122] A hydropower unit adaptive PID controller design system based on a whale optimization algorithm and a BP neural network, characterized in that the hydropower unit adaptive PID controller design method based on a whale optimization algorithm and a BP neural network is adopted, comprising:

[0123] Octave simulation module: used to build a numerical simulation model of the turbine regulation system;

[0124] Data analysis and classification module: used to classify working conditions according to water head and guide vane opening;

[0125] Optimization algorithm module: used to construct the comprehensive objective function of the whale optimization algorithm;

[0126] PID automatic optimization module: used to obtain the optimal PID parameters under typical working conditions based on the whale optimization algorithm;

[0127] Neural network design module: used to determine the number of hidden layer neurons of the controller neural network model;

[0128] Machine learning modeling module: used to combine the optimal PID parameter data set and BP neural network to build a K P or K I The controller neural network model is the output.

[0129] A computer device comprising:

[0130] one or more processors;

[0131] The processor is used to store one or more programs;

[0132] When the one or more programs are executed by the one or more processors, a method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network is implemented.

[0133] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed, a design method for a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network is implemented as described.

[0134] The above embodiments are only preferred technical solutions of the present invention and should not be regarded as limiting the present invention. The protection scope of the present invention shall be the technical solutions recorded in the claims, including equivalent replacement solutions of the technical features in the technical solutions recorded in the claims. That is, equivalent replacement improvements within this scope are also within the protection scope of the present invention.

Claims

1. A design method for adaptive PID controller of hydropower unit based on whale optimization algorithm and BP neural network, characterized in that: The following steps are involved: S1, construct a numerical simulation model of the turbine regulation system; S2, divided into operating conditions according to water head and guide vane opening; S3, constructs the comprehensive objective function of the whale optimization algorithm; S4, obtain the optimal PID parameters under typical working conditions based on the whale optimization algorithm; S5, determining the number of hidden layer neurons of the controller neural network model; S6, combining the optimal PID parameter data set and BP neural network to construct a K P or K I The controller neural network model is the output.

2. The method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network according to claim 1, characterized in that: In step S1, the numerical simulation model of the hydraulic turbine regulation system is built based on the Octave tool. The numerical simulation model of the hydraulic turbine regulation system includes a water diversion system model, a hydraulic turbine model, a generator and power grid model, and a speed governor and servo system model.

3. The design method of a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network according to claim 1 is characterized in that: The specific method of step S2 is: At the minimum water head H min With maximum head H max The water head is divided into two groups according to the interval H. D Divide; then under the divided water head, at the no-load opening Y 空载 With full opening Y max By interval Y D The guide vane opening is divided to realize the working condition division, and the obtained working condition is called the typical working condition.

4. The method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network according to claim 1 is characterized in that: The step S3 is specifically as follows: A comprehensive objective function considering overshoot, backshoot, rise time and standard ITAE indicators is constructed; among them, J ITAE It is a commonly used objective function for PID parameter optimization, as shown in the following formula: Where t is the actual time; t s is the total simulation time; e(t) is the integral of the turbine control signal error; J ITAE represents the standard ITAE index; Comprehensive objective function J including overshoot, backshoot, rise time and standard ITAE indicators 综合 As shown below: In the formula, σ1 is the overshoot; σ2 is the backshoot; t r is the rise time; ω1, ω2 and ω3 are weight coefficients.

5. The design method of a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network according to claim 2 is characterized in that: The step S4 is specifically as follows: Based on the whale optimization algorithm with strong optimization ability, the optimal PID parameters of the hydropower unit controller are obtained under various typical operating conditions.

6. The method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network according to claim 1 is characterized in that: The step S5 is specifically as follows: First, the maximum number of hidden layer neurons is determined according to the empirical formula, and then the sensitivity analysis of the number of hidden layer neurons is carried out to determine the reasonable number of hidden layer neurons in the controller neural network model; the empirical formula for the number of hidden layer neurons is: Where l is the number of hidden layer nodes, m is the number of input layer nodes, n is the number of output layer nodes, and a is a constant between 0 and 10.

7. The method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network according to claim 1 is characterized in that: The step S6 is specifically as follows: Combine the optimal PID parameter data set and BP neural network to build a K P or K I The controller neural network model is the output.

8. The method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network according to claim 1 is characterized in that: The construction formulas of the water system model, turbine model, generator and power grid model, speed regulator and servo system model are as follows: 1) Water diversion system model: The water diversion system adopts a rigid water hammer model, which is mathematically described as: G h (s)=-T w s; Where T w is the water flow inertia time constant; 2) Generator and grid model: Considering an infinite power grid, the generator and load transfer functions are: Where T a is the unit inertia time constant, e g is the generator load self-regulation coefficient; 3) Governor model: The transfer function of the linear part of the PID controller is; Where: T 1v is the time constant of the differential link; u is the controller output; e is the tracking error; K P , K I and K D are proportional, integral and differential gains respectively; considering the actual situation, K is taken when the unit is running in speed or power mode D =0, take K in no-load operation mode D are the original parameters of the power plant; 4) Follow-up system model: The servo system contains nonlinear links such as delay, saturation, speed limit, dead zone, etc. The transfer function of its linear part is; Where: K y is the comprehensive amplifier coefficient; T y1 and T y are the reaction time constants of the intermediate servomotor and the main servomotor respectively; 5) Turbine model: Based on the neural network, a flow characteristic neural network model and a torque characteristic neural network model are constructed with unit speed and guide vane opening as input and turbine flow and torque as output respectively.

9. A design system for adaptive PID controller of hydropower unit based on whale optimization algorithm and BP neural network, characterized in that: A method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network according to any one of claims 1 to 7 is adopted, comprising: Ovtave simulation module: used to build a numerical simulation model of the turbine regulation system; Data analysis and classification module: used to classify working conditions according to water head and guide vane opening; Optimization algorithm module: used to construct the comprehensive objective function of the whale optimization algorithm; PID automatic optimization module: used to obtain the optimal PID parameters under typical working conditions based on the whale optimization algorithm; Neural network design module: used to determine the number of hidden layer neurons of the controller neural network model; Machine learning modeling module: used to combine the optimal PID parameter data set and BP neural network to build a K P or K I The controller neural network model is the output.

10. A computer device, characterized in that: include: one or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, a method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network as described in any one of claims 1 to 9 is implemented.

11. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed, a method for designing a hydropower unit adaptive PID controller based on a whale optimization algorithm and a BP neural network is implemented as described in any one of claims 1 to 9.

Images