Wind matrix system power regulation and control method and device

Abstract

The invention provides a wind matrix system power regulation and control method and device. The method comprises the steps of obtaining an actual wind speed of a wind matrix system; inputting the actual wind speed into a pre-trained wind matrix power prediction model, and predicting to obtain the fan power of the wind matrix system; and inputting the fan power into the fuzzy self-adaptive PID controller, and performing feedback adjustment on the fan power based on the fuzzy self-adaptive PID controller to obtain the target fan power. According to the method provided by the invention, the actual wind speed of the wind matrix system is input into the pre-trained wind matrix power prediction model for power prediction, and the predicted fan power is subjected to feedback adjustment through the fuzzy self-adaptive PID controller, so that the precision of the adjusted target fan power is higher, and the wind field simulation precision is improved; and a test condition closer to a real complex environment is provided for an unmanned aerial vehicle experiment.

Description

Technical Field

[0001] The present invention relates to the technical field of wind matrix system control, and in particular to a wind matrix system power control method and device. Background Art

[0002] In the UAV test environment, the importance of the wind matrix cannot be ignored. As a key tool for simulating complex wind conditions in nature, it provides an ideal experimental platform for UAV performance testing, structural verification, and optimization of flight control algorithms. Especially in the performance testing of UAVs, the wind matrix can accurately create a variety of complex and changeable airflow environments in the test site through the coordinated operation of multiple fans.

[0003] The flexibility of the wind matrix is ​​one of its major advantages. By precisely controlling the working state of each fan, it can simulate airflows of different directions, intensities and patterns, allowing the drone to be tested in an environment close to real flight conditions. This highly simulated test environment is crucial for fully evaluating the performance of drones. For example, when simulating a turbulent mountain environment, the wind matrix can randomly change the direction and intensity of the airflow to test the flight stability and attitude control capabilities of the drone under complex airflow conditions. Such tests can not only reveal the performance of the drone under extreme conditions, but also provide valuable experimental data for the optimization of flight control algorithms.

[0004] However, although the wind matrix has achieved remarkable results in simulating a variety of wind conditions, its simulation capabilities still need to be further improved when facing extreme or fine wind field characteristics. In particular, when it comes to complex wind field characteristics such as micro-scale turbulence structures, the simulation accuracy of the wind matrix is ​​often difficult to achieve the ideal state. This is mainly due to the fact that the power control accuracy of the wind matrix system is still insufficient, which makes it difficult to achieve the expected accuracy when simulating these fine wind field characteristics. Summary of the invention

[0005] The present invention provides a wind matrix system power control method and device, which are used to solve the defect of low power control accuracy of the wind matrix system in the prior art.

[0006] A wind matrix system power control method, comprising:

[0007] Get the actual wind speed of the wind matrix system;

[0008] The actual wind speed is input into a pre-trained wind matrix power prediction model, and based on the model, the fan power of the wind matrix system is predicted;

[0009] The fan power is input into a fuzzy adaptive PID controller, and feedback adjustment is performed on the fan power based on the fuzzy adaptive PID controller to obtain a target fan power of a wind matrix system.

[0010] Furthermore, in the wind matrix system power control method as described above, the pre-trained wind matrix power prediction model is trained using the following method:

[0011] Obtain the wind speeds corresponding to the wind matrix system under different wind conditions, and the fan power corresponding to each wind speed;

[0012] The wind speeds and fan powers under all different wind conditions are used as training samples to train the initial wind matrix power prediction model to obtain the trained wind matrix power prediction model.

[0013] Furthermore, in the wind matrix system power control method as described above, the initial wind matrix power prediction model is constructed using a CNN model.

[0014] Furthermore, in the wind matrix system power control method as described above, the parameters of the fuzzy adaptive PID controller are optimal parameters obtained based on a simulated annealing algorithm.

[0015] Furthermore, in the power control method of the wind matrix system as described above, the parameters of the fuzzy adaptive PID controller are the optimal parameters obtained based on the simulated annealing algorithm and include:

[0016] Get the initialization parameters of the fuzzy adaptive PID controller;

[0017] At the current temperature, randomly perturb the initialization parameters to obtain updated parameters;

[0018] Based on the fuzzy adaptive PID controller corresponding to the update parameter, the wind matrix system is operated to obtain the stable wind speed of the wind matrix system within a preset time and the power corresponding to the stable wind speed;

[0019] Determining an objective function value corresponding to the current temperature according to the stable wind speed and the power corresponding to the stable wind speed;

[0020] The objective function value J corresponding to the current temperature and the initial minimum objective function value J′ min Compare and determine the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J according to the comparison results min ;

[0021] The current temperature is iteratively updated, and based on the objective function value corresponding to the updated temperature, the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J are adjusted. min The update is performed until the updated temperature is lower than the preset termination temperature, and the final optimal parameters corresponding to the fuzzy adaptive PID controller are output.

[0022] Furthermore, in the above-mentioned wind matrix system power control method, the objective function value J corresponding to the current temperature is compared with the initial minimum objective function value J′ min Compare and determine the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J according to the comparison results min include:

[0023] The objective function value J corresponding to the current temperature is less than the initial minimum objective function value J′ min In the case of, the updated parameter is used as the current optimal parameter of the fuzzy adaptive PID controller; and the objective function value J corresponding to the current temperature is used as the updated current minimum objective function value J mim .

[0024] Furthermore, in the above-mentioned wind matrix system power control method, the objective function value J corresponding to the current temperature is greater than or equal to the initial minimum objective function value J′ min In the case of, calculate the acceptance probability P, and based on the acceptance probability P, determine the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J min ;

[0025]

[0026] Among them, J` is the objective function value corresponding to the current temperature, J min is the current minimum objective function value, and T is the current temperature.

[0027] Furthermore, in the power control method of the wind matrix system as described above, the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J are determined based on the acceptance probability P. mim Including: when the acceptance probability P is greater than the preset random parameter ρ, the updated parameter is used as the current optimal parameter of the fuzzy adaptive PID controller; and the objective function value J corresponding to the current temperature is used as the updated current minimum objective function value J min ;

[0028] When the acceptance probability P is less than or equal to the preset random parameter ρ, the optimal parameter corresponding to the last updated temperature is used as the current optimal parameter of the fuzzy adaptive PID controller, and the objective function value J corresponding to the last updated temperature is used as the current minimum objective function value J min .

[0029] Furthermore, in the wind matrix system power control method as described above, the obtaining of initialization parameters of the fuzzy adaptive PID controller includes:

[0030] According to experience, the initial fuzzy adaptive PID control parameters of the PID controller are set;

[0031] Based on the fuzzy adaptive PID controller corresponding to the initial fuzzy adaptive PID control parameters, the wind matrix system is operated to determine the current actual wind speed of the wind matrix system;

[0032] Determine the wind speed error e and the error change rate ec according to the current actual wind speed and the target wind speed of the wind matrix system;

[0033] According to the predefined fuzzy subsets and membership functions, the wind speed error e and the error change rate ec are fuzzified into corresponding fuzzy values;

[0034] Perform fuzzy reasoning based on the fuzzy control rule table to determine the parameter adjustment amount of the fuzzy adaptive PID controller;

[0035] Based on the center of gravity method, the parameter adjustment amount is converted into the precise parameter of the fuzzy adaptive PID controller, and the precise parameter is used as the initialization parameter of the fuzzy adaptive PID controller.

[0036] The present invention also provides a wind matrix system power control device, comprising:

[0037] An acquisition unit, used for acquiring the actual wind speed of the wind matrix system;

[0038] A prediction unit, configured to input the actual wind speed into a pre-trained wind matrix power prediction model, and predict the fan power of the wind matrix system based on the model;

[0039] The adjustment unit is used to input the fan power into a fuzzy adaptive PID controller, and perform feedback adjustment on the fan power based on the fuzzy adaptive PID controller to obtain a target fan power of a wind matrix system.

[0040] The wind matrix system power control method and device provided by the present invention predict the power by inputting the actual wind speed of the wind matrix system into a pre-trained wind matrix power prediction model, and then feedback-adjusting the predicted fan power through a fuzzy adaptive PID controller, so that the adjusted target fan power has higher accuracy, thereby improving the wind field simulation accuracy and providing test conditions for UAV experiments that are closer to real complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 A flow chart of the wind matrix system power control method provided by the present invention;

[0043] Figure 2 A schematic diagram of the structure of the wind matrix system provided by the present invention;

[0044] Figure 3 A flow chart of the simulated annealing algorithm provided by the present invention;

[0045] Figure 4 This is a structural block diagram of the wind matrix system power control device provided by the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In the UAV experimental environment, the setting of the wind matrix is ​​crucial. According to the specific needs of the experiment, the layout and scale of the wind matrix will be carefully designed. These wind matrices are composed of multiple fans, and work together through advanced control systems, so that airflows of various directions, intensities and modes can be simulated. The UAV performs flight tests in such an airflow environment, and the experimenter can simulate different meteorological conditions by adjusting the parameters (wind speed, power) of the wind matrix, providing a comprehensive test environment for the performance evaluation of the UAV. Although the wind matrix can produce a variety of wind conditions, current technology still has deficiencies in simulating some extreme or fine wind field characteristics. For example, when simulating micro-scale turbulent structures, it may not be possible to accurately reproduce the spectral characteristics and spatial distribution of turbulence in nature. This causes certain differences between the experimental environment and the actual complex environment, affecting the accuracy of the performance evaluation of the UAV under extreme conditions. In order to solve this problem, the present invention applies neural networks and fuzzy adaptive PID controllers to the control of the wind matrix system.

[0048] Among them, neural networks, with their powerful nonlinear mapping ability and self-learning ability, have shown excellent performance in dealing with complex and uncertain system problems. In the control of the wind matrix system, the neural network can learn the potential relationship between fan power and wind speed through training of a large amount of historical data, thereby realizing accurate prediction and control of fan power. This data-based control method can not only improve the accuracy of wind speed control, but also reduce the energy consumption of the system to a certain extent. On the other hand, the fuzzy adaptive PID controller combines the advantages of fuzzy logic and PID control, and can dynamically adjust the control parameters according to the real-time state of the system, so that the control system can respond quickly when facing external interference or internal changes in the system, and maintain a stable control effect. In the wind matrix system, the fuzzy adaptive PID controller can flexibly adjust the power output of the fan according to the real-time feedback of the wind speed to ensure that the wind speed is always maintained within the set target range. The present invention combines the neural network with the fuzzy adaptive PID controller to further improve the control performance of the wind matrix system. Specifically, the neural network can be used to construct a prediction model between fan power and wind speed, providing accurate reference information for the fuzzy adaptive PID controller; and the fuzzy adaptive PID controller can adjust the control strategy in real time according to these prediction information to ensure the accuracy and stability of wind speed control. The scheme provided by the present invention is described in detail below:

[0049] Figure 1 The flow chart of the wind matrix system power control method provided by the present invention is as follows: Figure 1 As shown, the method comprises the following steps:

[0050] Step 1: Get the actual wind speed of the wind matrix system.

[0051] Specifically, Figure 2 The wind matrix system structure diagram provided by the present invention is as follows: Figure 2 As shown, the wind speed sensor collects the actual wind speed of the wind matrix. The control system includes a fuzzy adaptive PID controller and a power prediction model; the wind speed sensor inputs the collected actual wind speed into the power prediction model, and based on the power prediction model, predicts the fan power corresponding to the actual wind speed, and uses the predicted fan power as the input of the fuzzy adaptive PID controller. After feedback adjustment by the fuzzy adaptive PID controller, the adjusted fan power is finally output, and the industrial control system uses the fan power to control the operation of the wind matrix, so that the wind matrix simulates the required meteorological conditions.

[0052] In the embodiment of the present invention, the wind matrix system is composed of a combination of 40×40 fans, and a 6×6 wind speed sensor array in front of the wind matrix is ​​used to accurately collect the corresponding wind speed to obtain a wind speed matrix.

[0053] Step 2: Input the actual wind speed into the pre-trained wind matrix power prediction model, and based on the model, predict the fan power of the wind matrix system.

[0054] Specifically, the actual wind speed matrix measured by the sensor is input into a pre-trained wind matrix power prediction model. The pre-trained wind matrix power prediction model extracts and analyzes features of the wind speed matrix, converts the wind speed matrix information into a preliminary estimate of the wind matrix power control signal, and outputs the power adjustment recommended value corresponding to each fan.

[0055] Step 3: Input the fan power into the fuzzy adaptive PID controller, perform feedback adjustment on the fan power based on the fuzzy adaptive PID controller, and obtain the target fan power of the wind matrix system.

[0056] Specifically, the power adjustment recommendation value corresponding to each fan output by the wind matrix power prediction model is input into the fuzzy adaptive PID controller, and the fuzzy adaptive PID controller is used to feedback adjust the power corresponding to each fan, and finally obtain the adjusted target fan power.

[0057] The wind matrix system power control method provided by the present invention performs power prediction by inputting the actual wind speed of the wind matrix system into a pre-trained wind matrix power prediction model, and then feedback-adjusts the predicted fan power through a fuzzy adaptive PID controller, so that the adjusted target fan power has higher accuracy, thereby improving the wind field simulation accuracy and providing test conditions for UAV experiments that are closer to real complex environments.

[0058] Furthermore, the pre-trained wind matrix power prediction model is trained using the following method:

[0059] Firstly, the wind speeds corresponding to the wind matrix system under different wind conditions and the fan power corresponding to each wind speed are obtained; secondly, the wind speeds and fan powers under different wind conditions are used as training samples to train the initial wind matrix power prediction model to obtain a trained wind matrix power prediction model.

[0060] Specifically, the training process of the model is as follows:

[0061] 1. Data collection:

[0062] After the wind matrix system is started, the data acquisition equipment begins to collect wind speed and fan power data, with a sampling frequency of once per second. A large number of experiments are carried out in the wind matrix system, comprehensively changing the power combination of 40×40 fans, and using the 6×6 wind speed sensor array in front of the wind matrix to accurately collect the corresponding wind speed pattern data.

[0063] 2. Dataset preprocessing:

[0064] Data normalization:

[0065] Use mean filtering to preprocess the data, normalize the wind speed data and fan power data respectively, and normalize the data to the (0,1) interval. The specific formula is as follows:

[0066]

[0067] Among them, Z is the normalized data, X is the original data, X_min and X_max are the minimum and maximum values ​​in the original data, respectively, so as to better handle data of different magnitudes in model training.

[0068] For the wind speed matrix A, its size is M×N, assuming the window size is (m×n), the size of the filtered matrix B is (M-m+1)×(N-n+1), and its calculation formula is:

[0069]

[0070] 3. Dataset segmentation:

[0071] The collected preprocessed data are divided into training set, validation set and test set in the ratio of 70%, 20% and 10%.

[0072] 4. CNN model construction:

[0073] A CNN model structure suitable for processing the wind matrix power-wind speed relationship was constructed. After multiple experiments and model performance evaluation, it was determined that the combination of 3 convolutional layers and 2 pooling layers could achieve a good balance between model complexity and performance.

[0074] Output layer: 6*6 matrix, input channel is 1.

[0075] First convolutional layer: The convolution kernel size is set to 5×5 and the stride is 1, the number of convolution kernels is 16, the number of input channels is 1 (consistent with the input layer), and the number of output channels is 16.

[0076] First pooling layer: It follows the first convolutional layer, with a window size of 2×2 and a stride of 2. The number of input channels of this pooling layer is 16 (the same as the number of output channels of the previous convolutional layer), and the number of output channels is also 16.

[0077] Second convolutional layer: The convolution kernel size is still 5×5 and the stride is 1, the number of convolution kernels increases to 32, the number of input channels is 16 (the same as the number of output channels of the previous pooling layer), and the number of output channels is 32.

[0078] Second pooling layer: The pooling operation is also performed with a window size of 2×2 and a stride of 2. The number of input channels is 32 (the same as the number of output channels of the previous convolutional layer), and the number of output channels is 32.

[0079] The third convolutional layer: The convolution kernel size remains 5×5 and the stride is 1, the number of convolution kernels increases to 64, the number of input channels is 32 (the same as the number of output channels of the previous pooling layer), and the number of output channels is 64.

[0080] Fully connected layer: The weight parameter matrix size of the fully connected layer is 1024*1600, and the bias parameter vector size is 1600.

[0081] Activation function: Use ReLU function as the activation function.

[0082] In an embodiment of the present invention, the initial wind matrix power prediction model is constructed using a CNN model.

[0083] Specifically, in wind matrix power prediction, the CNN model can effectively extract complex spatiotemporal features in wind power time series through multi-layer convolution and pooling operations. This feature extraction capability enables the CNN model to more accurately capture the changing laws of wind power, thereby improving the prediction accuracy of power. At the same time, the CNN model can also use methods such as cross-validation to optimize parameters to further improve the prediction performance of the model. This efficient model training and optimization capability enables the CNN model to have faster training speed and better generalization ability in wind matrix power prediction. Moreover, the CNN model has strong adaptability and scalability. It can adapt to wind farms of different sizes and different wind power prediction scenarios. With the continuous accumulation of wind power data and the improvement of computing power, the CNN model can be further expanded and optimized to cope with more complex wind power prediction problems.

[0084] Furthermore, the parameters of the fuzzy adaptive PID controller provided by the present invention are optimal parameters obtained based on a simulated annealing algorithm.

[0085] Specifically, the simulated annealing algorithm can effectively explore the global optimal solution in a huge solution space. When optimizing the parameters of the fuzzy adaptive PID controller, the parameters of the fuzzy adaptive PID controller can be gradually adjusted through the iterative process of the simulated annealing algorithm, thereby improving the accuracy of the parameters. The present invention improves the existing simulated annealing algorithm and optimizes the parameters of the fuzzy adaptive PID controller using the improved simulated annealing algorithm. The optimization method is introduced in detail below. Figure 3 The simulated annealing algorithm flow chart provided by the present invention is as follows: Figure 3 As shown, the method includes:

[0086] Step 1: Get the initialization parameters of the fuzzy adaptive PID controller.

[0087] Among them, the initialization parameters of the fuzzy adaptive PID controller are obtained according to the following method:

[0088] According to experience, set the initial fuzzy adaptive PID control parameters of the PID controller; based on the fuzzy adaptive PID controller corresponding to the initial fuzzy adaptive PID control parameters, run the wind matrix system to determine the current actual wind speed of the wind matrix system; according to the current actual wind speed and the target wind speed of the wind matrix system, determine the wind speed error e and the error change rate ec; according to the predefined fuzzy subsets and membership functions, fuzzify the wind speed error e and the error change rate ec into corresponding fuzzy values; based on the fuzzy control rule table, perform fuzzy inference to determine the parameter adjustment amount of the fuzzy adaptive PID controller; based on the centroid method, convert the parameter adjustment amount into the exact parameters of the fuzzy adaptive PID controller, and use the exact parameters as the initialization parameters of the fuzzy adaptive PID controller.

[0089] Specifically, based on past experience, initially set the parameters of the fuzzy adaptive PID controller. The initial value of the proportionality coefficient K p is set to 1.0, the initial value of the integral coefficient K i is set to 0.05, and the initial value of the derivative coefficient K d is set to 0.5.

[0090] Define the fuzzy subsets {Negative Big (NB), Negative Medium (NM), Zero (ZO), Positive Medium (PM), Positive Big (PB)}.

[0091] The membership function adopts the triangular membership function,

[0092] and the calculation formula is as follows:

[0093] When x < a, μ(x) = 0;

[0094] When a ≤ x < β,

[0095] When x = b, μ(x) = 1;

[0096] When b < x ≤ c,

[0097] When x > c, μ(x) = 0.

[0098] Among them, x is the input variable, a is the lower limit value, b is the peak value, and c is the upper limit value.

[0099] Definition of the fuzzy sets and membership function parameters of the error e and the error change rate ec

[0100] Table 1:

[0101]

[0102] Table 2:

[0103]

[0104]

[0105] The fuzzy adaptive PID controller obtains the power control signal output by the CNN network as well as the error e and the error change rate ec between the current actual wind speed and the target wind speed.

[0106] Fuzzification step: According to the predefined fuzzy subsets and membership functions, the error e and the error change rate ec are fuzzified into corresponding fuzzy values. For example, the error e is fuzzified into fuzzy subsets such as negative large (NB), negative medium (NM), zero (ZO), positive medium (PM), and positive large (PB), and its membership in each fuzzy subset is determined.

[0107] Fuzzy reasoning steps: perform fuzzy reasoning based on the fuzzy control rule table. According to the fuzzy value combination of error e and error change rate ec, determine the adjustment amount ΔK of the PID parameter according to the rule table. p , ΔK i , ΔK d The fuzzy output.

[0108] Clarification step: Use the center of gravity method to convert the fuzzy output PID parameter adjustment into precise values. Compare these precise PID parameter adjustment values ​​with the current K p , K i , K d Add and update the parameters of the PID controller.

[0109] Finally, the PID controller adjusts the wind matrix power control signal output by the CNN network according to the updated parameters, obtains the final power control signal and sends it to the power controller, which adjusts the actual power output of the fan according to this signal.

[0110] Step 2: At the current temperature, randomly perturb the initialization parameters to obtain the updated parameters

[0111] ```

[0112] (K p ,K i ,K d ).

[0113] Step 3: Based on the fuzzy adaptive PID controller corresponding to the updated parameters, the wind matrix system is operated to obtain the stable wind speed of the wind matrix system within a preset time and the power corresponding to the stable wind speed.

[0114] ```

[0115] Specifically, the updated parameter (K p ,K i ,K d ) is applied to the fuzzy adaptive PID controller of the wind matrix system, and the wind matrix system is operated for 10 minutes, and the wind speed data and fan power data during this period are collected. Among them, the wind speed data and fan power data are the average wind speed value within the stable interval within the 10 minutes of operation, and the power is the average power value corresponding to the wind speed within the stable interval.

[0116] Step 4: Determine the objective function value corresponding to the current temperature based on the stable wind speed and the power corresponding to the stable wind speed.

[0117] Specifically, the objective function is J=w1*MSE+w2*Overshoot+w3*Energy. The embodiment of the present invention defines the objective function in the form of weighted sum, where MSE is the mean square error, which is used to measure the accuracy of wind speed control. The calculation formula is: Where N is the number of samples, y i To set the wind speed value, is the stable wind speed value; Overshoot is the overshoot; Energy is the power corresponding to the stable wind speed. w1, w2, w3 are weight coefficients.

[0118] Step 5: Compare the objective function value J corresponding to the current temperature with the initial minimum objective function value J′ min Make a comparison.

[0119] Step 6: The objective function value J corresponding to the current temperature is less than the initial minimum objective function value J′ min In the case of, the updated parameters are used as the current optimal parameters of the fuzzy adaptive PID controller; and the objective function value J corresponding to the current temperature is used as the updated current minimum objective function value J min .

[0120] Step 7: The objective function value J corresponding to the current temperature is greater than or equal to the initial minimum objective function value J′ min Calculate the acceptance probability P in the case of

[0121]

[0122] Among them, J` is the objective function value corresponding to the current temperature, J min is the current minimum objective function value.

[0123] Step 8: Generate a random number ρ that is uniformly distributed in the interval [0,1], and compare the acceptance probability P with the preset random parameter ρ.

[0124] Step 9: When the acceptance probability P is greater than the preset random parameter ρ, the updated parameter is used as the current optimal parameter of the fuzzy adaptive PID controller; and the objective function value J corresponding to the current temperature is used as the updated current minimum objective function value J min .

[0125] Step 10: When the acceptance probability P is less than or equal to the preset random parameter ρ, the optimal parameter corresponding to the last updated temperature is used as the current optimal parameter of the fuzzy adaptive PID controller, and the objective function value J corresponding to the last updated temperature is used as the current minimum objective function value J min .

[0126] Specifically, generate a random number ρ uniformly distributed in the interval [0,1]. If P>ρ, accept the new ``

[0127] Parameter solution (K` P , K i , K d ), that is, update the current optimal parameter combination to a new parameter combination, and update J min =J ` ; If P≤ρ, reject the new parameter solution and retain the current optimal parameter combination.

[0128] Step 11: Iteratively update the current temperature to obtain an updated temperature.

[0129] Step 12: Based on the objective function value corresponding to the updated temperature, the initial optimal parameters and the current minimum objective function value J of the fuzzy adaptive PID controller are mi to update.

[0130] Step 13: Determine whether the updated temperature is lower than the preset termination temperature T min If it is lower than the preset termination temperature T min , then the final optimal parameters corresponding to the fuzzy adaptive PID controller are output.

[0131] Specifically, the initial temperature T0 is set to 100°C, the temperature drop coefficient α is taken to be 0.95°C, and the end temperature T min Set to 1, and the number of iterations at each temperature is set to 100. After completing L iterations at the current temperature T, update the temperature according to the temperature drop formula T = α*T. Then determine whether the current temperature T is lower than the termination temperature T min If it is lower than , the search process of the simulated annealing algorithm is stopped and the current optimal fuzzy adaptive PID parameter combination is output; if it is higher than , it returns to the step of generating a new parameter solution and continues to search for parameters at the new temperature.

[0132] The wind matrix system power control device provided by the present invention is described below. The wind matrix system power control device described below and the wind matrix system power control method described above can be referenced to each other.

[0133] The present invention also provides a wind matrix system power control device, Figure 4 The structural block diagram of the wind matrix system power control device provided by the present invention is as follows: Figure 4 As shown, the device comprises:

[0134] An acquisition unit 401 is used to acquire the actual wind speed of the wind matrix system;

[0135] A prediction unit 402 is used to input the actual wind speed into a pre-trained wind matrix power prediction model, and predict the fan power of the wind matrix system based on the model;

[0136] The adjustment unit 403 is used to input the fan power into the fuzzy adaptive PID controller, and perform feedback adjustment on the fan power based on the fuzzy adaptive PID controller to obtain the target fan power of the wind matrix system.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A wind matrix system power control method, characterized in that: include: Get the actual wind speed of the wind matrix system; The actual wind speed is input into a pre-trained wind matrix power prediction model, and based on the model, the fan power of the wind matrix system is predicted; The fan power is input into a fuzzy adaptive PID controller, and feedback adjustment is performed on the fan power based on the fuzzy adaptive PID controller to obtain a target fan power of a wind matrix system.

2. The wind matrix system power control method according to claim 1 is characterized in that: The pre-trained wind matrix power prediction model is trained using the following method: Obtain the wind speeds corresponding to the wind matrix system under different wind conditions, and the fan power corresponding to each wind speed; The wind speeds and fan powers under all different wind conditions are used as training samples to train the initial wind matrix power prediction model to obtain the trained wind matrix power prediction model.

3. The wind matrix system power control method according to claim 2 is characterized in that: The initial wind matrix power prediction model is constructed using a CNN model.

4. The wind matrix system power control method according to any one of claims 1 to 3, characterized in that: The parameters of the fuzzy adaptive PID controller are optimal parameters obtained based on a simulated annealing algorithm.

5. The wind matrix system power control method according to claim 4 is characterized in that: The parameters of the fuzzy adaptive PID controller are the optimal parameters obtained based on the simulated annealing algorithm and include: Get the initialization parameters of the fuzzy adaptive PID controller; At the current temperature, randomly perturb the initialization parameters to obtain updated parameters; Based on the fuzzy adaptive PID controller corresponding to the update parameter, the wind matrix system is operated to obtain the stable wind speed of the wind matrix system within a preset time and the power corresponding to the stable wind speed; Determining an objective function value corresponding to the current temperature according to the stable wind speed and the power corresponding to the stable wind speed; The objective function value J corresponding to the current temperature and the initial minimum objective function value J′ min Compare and determine the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J according to the comparison results min ; The current temperature is iteratively updated, and based on the objective function value corresponding to the updated temperature, the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J are adjusted. min The update is performed until the updated temperature is lower than the preset termination temperature, and the final optimal parameters corresponding to the fuzzy adaptive PID controller are output.

6. The wind matrix system power control method according to claim 5 is characterized in that: The objective function value J corresponding to the current temperature and the initial minimum objective function value J′ min Compare and determine the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J according to the comparison results min include: The objective function value J corresponding to the current temperature is less than the initial minimum objective function value J′ min In the case of, the updated parameter is used as the current optimal parameter of the fuzzy adaptive PID controller; and the objective function value J corresponding to the current temperature is used as the updated current minimum objective function value J min .

7. The wind matrix system power control method according to claim 6 is characterized in that: The objective function value J corresponding to the current temperature is greater than or equal to the initial minimum objective function value J′ min In the case of, calculate the acceptance probability P, and based on the acceptance probability P, determine the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J min ; Among them, J` is the objective function value corresponding to the current temperature, J min is the current minimum objective function value, and T is the current temperature.

8. The wind matrix system power control method according to claim 7 is characterized in that: Based on the acceptance probability P, the initial optimal parameters of the fuzzy adaptive PID controller and the current minimum objective function value J are determined. min include: When the acceptance probability P is greater than the preset random parameter ρ, the updated parameter is used as the current optimal parameter of the fuzzy adaptive PID controller; and the objective function value J corresponding to the current temperature is used as the updated current minimum objective function value J min ; When the acceptance probability P is less than or equal to the preset random parameter ρ, the optimal parameter corresponding to the last updated temperature is used as the current optimal parameter of the fuzzy adaptive PID controller, and the objective function value J corresponding to the last updated temperature is used as the current minimum objective function value J min .

9. The wind matrix system power control method according to claim 5, characterized in that: The method of obtaining the initialization parameters of the fuzzy adaptive PID controller includes: According to experience, the initial fuzzy adaptive PID control parameters of the PID controller are set; Based on the fuzzy adaptive PID controller corresponding to the initial fuzzy adaptive PID control parameters, the wind matrix system is operated to determine the current actual wind speed of the wind matrix system; Determine the wind speed error e and the error change rate ec according to the current actual wind speed and the target wind speed of the wind matrix system; According to the predefined fuzzy subsets and membership functions, the wind speed error e and the error change rate ec are fuzzified into corresponding fuzzy values; Perform fuzzy reasoning based on the fuzzy control rule table to determine the parameter adjustment amount of the fuzzy adaptive PID controller; Based on the center of gravity method, the parameter adjustment amount is converted into the precise parameter of the fuzzy adaptive PID controller, and the precise parameter is used as the initialization parameter of the fuzzy adaptive PID controller.

10. A wind matrix system power control device, characterized in that: include: An acquisition unit, used for acquiring the actual wind speed of the wind matrix system; A prediction unit, configured to input the actual wind speed into a pre-trained wind matrix power prediction model, and predict the fan power of the wind matrix system based on the model; The adjustment unit is used to input the fan power into a fuzzy adaptive PID controller, and perform feedback adjustment on the fan power based on the fuzzy adaptive PID controller to obtain a target fan power of a wind matrix system.

Images