Variable pitch control method, device and system based on BP neural network

Abstract

The invention relates to a variable pitch control method, device and system based on a BP neural network. The method comprises the steps of obtaining a first target rotating speed and an actual rotating speed of a wind driven generator, determining a first error value between the first target rotating speed and the actual rotating speed, inputting the first target rotating speed, the actual rotating speed and the first error value into a trained BP neural network, and obtaining a proportionality coefficient and an integral coefficient output by the BP neural network, and updating configuration parameters of the PI controller by using the proportionality coefficient and the integral coefficient to obtain an updated PI controller, inputting the first error into the updated PI controller to obtain a first blade angle output by the updated PI controller, and adjusting the blade angle of the wind driven generator based on the first blade angle. According to the scheme, the accuracy of the control parameters of the variable pitch controller can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind turbines, and in particular to a pitch control method, device and system based on a BP neural network. Background Art

[0002] In the related art, after the wind turbine reaches the rated speed, the torque setting is constant, and the blade angle is controlled by the pitch controller to keep the absorbed wind energy constant, thereby keeping the power constant and the speed constant. To achieve good control effects, the pitch PI control must adjust the control effects of proportion and integral. The common pitch controller in the field of wind power generation is the classic incremental digital PI controller. In this way, the proportion and integral in PID control are linearly related. However, the relationship between proportion and integral is not necessarily a simple linear combination, which leads to the inaccuracy of determining the control parameters of the pitch controller based on the linear relationship between proportion and integral, which makes it difficult to accurately control the blades. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a pitch control method, device and system based on BP neural network.

[0004] According to a first aspect of an embodiment of the present disclosure, a pitch control method based on a BP neural network is provided, comprising:

[0005] Acquire a first target speed and an actual speed of the wind turbine, and determine a first error value between the first target speed and the actual speed;

[0006] Inputting the first target speed, the actual speed and the first error value into the trained BP neural network to obtain a proportional coefficient and an integral coefficient output by the BP neural network;

[0007] Updating the configuration parameters of the PI controller using the proportional coefficient and the integral coefficient to obtain the updated PI controller;

[0008] Inputting the first error into the updated PI controller to obtain a first blade angle output by the updated PI controller;

[0009] The blade angle of the wind turbine is adjusted based on the first blade angle, and the process returns to the step of obtaining the first target rotational speed and the actual rotational speed of the wind turbine.

[0010] In some embodiments of the present disclosure, before obtaining the first target rotation speed and the actual rotation speed of the wind turbine, the method further includes:

[0011] When the speed of the wind turbine generator reaches the rated speed, obtaining a second target speed and an actual speed of the wind turbine generator;

[0012] Calculating the difference between the second target speed and the actual speed to obtain a second error value corresponding to the current parameter optimization round;

[0013] Based on the second error value, a weighted coefficient in the BP neural network to be trained is corrected to obtain a corrected BP neural network;

[0014] Determining whether the BP neural network to be trained converges based on the second target speed and the actual speed;

[0015] When it is determined that the BP neural network to be trained has not converged, return to the step of obtaining the second target speed and the actual speed of the wind generator when the speed of the wind generator reaches the rated speed, until it is determined that the BP neural network to be trained has converged, thereby obtaining the BP neural network that has completed training.

[0016] In some embodiments of the present disclosure, the BP neural network includes an input layer, a hidden layer and an output layer;

[0017] The method of correcting the weighted coefficients in the BP neural network to be trained based on the second error value to obtain a corrected BP neural network includes:

[0018] The first change is calculated using the following formula:

[0019]

[0020] Among them, Δw li (k) is the first change in the kth parameter optimization round, Δw li (k-1) is the first change in the k-1th parameter optimization round, η is the learning rate; α is the inertia coefficient, is the i-th output value of the hidden layer, e(k) is the second error value, G(β) is the nonlinear function of the pitch angle, y(k) is the actual speed, u(k) is the first blade angle, is the output value of the network layer, g(x) is the activation function of the output layer;

[0021] Adding the first change amount to the output layer weight coefficient corresponding to the previous parameter optimization round to obtain a first weight coefficient;

[0022] The second variation of the hidden layer is calculated using the following formula:

[0023]

[0024] Among them, Δwij (k) is the second change in the kth parameter optimization round, Δw ij (k-1) is the second change in the k-1th parameter optimization round, is the jth input value of the input layer, and f(x) is the activation function of the output layer;

[0025] Adding the second change amount to the hidden layer weight coefficient corresponding to the previous parameter optimization round to obtain a second weight coefficient;

[0026] The weighted coefficient of the output layer is corrected using the first weighted coefficient, and the weighted coefficient of the hidden layer is corrected using the second weighted coefficient to obtain the corrected BP neural network.

[0027] In some embodiments of the present disclosure, the determining whether the BP neural network to be trained converges based on the second target speed and the actual speed includes:

[0028] The performance index function value of the BP neural network to be trained is calculated using the following formula:

[0029] J = 0.5 (r(k) - y(k)) 2

[0030] Wherein, J is the performance index function value, r(k) is the second target speed, and y(k) is the actual speed;

[0031] When the performance indicator function value satisfies a preset condition, determining that the BP neural network to be trained converges;

[0032] When the performance indicator function value does not satisfy a preset condition, it is determined that the BP neural network to be trained has not converged.

[0033] In some embodiments of the present disclosure, adjusting the blade angle of the wind turbine based on the first blade angle includes:

[0034] Acquire the current pitch angle of the wind turbine;

[0035] Determine a second pitch angle based on the current pitch angle and the first pitch angle using a pitch gain table; the pitch gain table is obtained based on a nonlinear function of the pitch angle;

[0036] The current pitch angle of the wind turbine is adjusted to the second pitch angle.

[0037] According to a second aspect of an embodiment of the present disclosure, a pitch control device based on a BP neural network is provided, comprising:

[0038] a first determining unit, configured to obtain a first target speed and an actual speed of the wind turbine, and determine a first error value between the first target speed and the actual speed;

[0039] An input unit, used for inputting the first target speed, the actual speed and the first error value into the trained BP neural network to obtain a proportional coefficient and an integral coefficient output by the BP neural network;

[0040] An updating unit, configured to update configuration parameters of a PI controller using the proportional coefficient and the integral coefficient to obtain an updated PI controller;

[0041] an output unit, configured to input the first error into the updated PI controller to obtain a first blade angle output by the updated PI controller;

[0042] An adjustment unit is used to adjust the blade angle of the wind turbine based on the first blade angle, and return to execute the operation step of obtaining the first target rotation speed and actual rotation speed of the wind turbine.

[0043] In some embodiments of the present disclosure, the device further includes:

[0044] an acquisition unit, configured to acquire a second target rotational speed and an actual rotational speed of the wind generator when the rotational speed of the wind generator reaches a rated rotational speed;

[0045] a calculation unit, configured to calculate a difference between the second target speed and the actual speed, and obtain a second error value corresponding to a current parameter optimization round;

[0046] A correction unit, configured to correct the weight coefficients in the BP neural network to be trained based on the second error value to obtain a corrected BP neural network;

[0047] a second determining unit, configured to determine whether the BP neural network to be trained has converged based on the second target speed and the actual speed;

[0048] The execution unit is used to return to the step of obtaining the second target speed and the actual speed of the wind turbine when the speed of the wind turbine reaches the rated speed when it is determined that the BP neural network to be trained has not converged, until it is determined that the BP neural network to be trained has converged, thereby obtaining the BP neural network that has completed training.

[0049] According to a third aspect of an embodiment of the present disclosure, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the first aspects is implemented.

[0050] According to a fourth aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0051] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method as described in any one of the first aspects when executed by a processor.

[0052] The technical solution provided by the embodiment of the present disclosure may include the following beneficial effects: by obtaining the first target speed and the actual speed of the wind turbine, determining the first error value between the first target speed and the actual speed, inputting the first target speed, the actual speed and the first error value into the trained BP neural network, obtaining the proportional coefficient and the integral coefficient output by the BP neural network, using the proportional coefficient and the integral coefficient to update the configuration parameters of the PI controller, obtaining the updated PI controller, inputting the first error into the updated PI controller, obtaining the first blade angle output by the updated PI controller, and adjusting the blade angle of the wind turbine based on the first blade angle. The proportional coefficient and the integral coefficient in the BP neural network are optimized in a nonlinear manner through the BP neural network, thereby improving the accuracy of the control parameters of the variable pitch controller, thereby improving the accuracy of the control of the blades.

[0053] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0055] Figure 1 It is a flow chart of a pitch control method based on BP neural network according to an exemplary embodiment.

[0056] Figure 2 It is a schematic diagram of the BP neural network structure proposed in the embodiment of the present application.

[0057] Figure 3 It is a flow chart of pitch control based on BP neural network proposed in the embodiment of the present application.

[0058] Figure 4 It is a block diagram of a pitch control device based on a BP neural network according to an exemplary embodiment.

[0059] Figure 5It is a block diagram of a device for a pitch control method based on a BP neural network according to an exemplary embodiment. DETAILED DESCRIPTION

[0060] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0061] The terms used in the disclosed embodiments are only for the purpose of describing specific embodiments, and are not intended to limit the disclosed embodiments. The singular forms "a", "an" and "the" used in the disclosed embodiments and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0062] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the disclosed embodiments, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the disclosed embodiments, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at" or "when" or "in response to determination".

[0063] In addition, various forms of processes shown in the embodiments of the present disclosure may be used to reorder, add or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present disclosure can be achieved, and this document does not limit this.

[0064] In the related art, after the wind turbine reaches the rated speed, the torque setting is constant, and the blade angle is controlled by the pitch controller to keep the absorbed wind energy constant, thereby keeping the power constant and the speed constant. To achieve good control effects, the pitch PI control must adjust the control effects of proportion and integral. The common pitch controller in the field of wind power generation is the classic incremental digital PI controller. In this way, the proportion and integral in PID control are linearly related. However, the relationship between proportion and integral is not necessarily a simple linear combination, which leads to the inaccuracy of determining the control parameters of the pitch controller based on the linear relationship between proportion and integral, which makes it difficult to accurately control the blades.

[0065] In order to solve the above problems, the present disclosure provides a variable pitch control method, device and system based on BP neural network, by obtaining the first target speed and actual speed of the wind turbine, determining the first error value between the first target speed and the actual speed, inputting the first target speed, the actual speed and the first error value into the trained BP neural network, obtaining the proportional coefficient and the integral coefficient output by the BP neural network, using the proportional coefficient and the integral coefficient to update the configuration parameters of the PI controller, obtaining the updated PI controller, inputting the first error into the updated PI controller, obtaining the first blade angle output by the updated PI controller, and adjusting the blade angle of the wind turbine based on the first blade angle. The proportional coefficient and the integral coefficient in the BP neural network are optimized in a nonlinear manner through the BP neural network, thereby improving the accuracy of the control parameters of the variable pitch controller, and further improving the accuracy of the control of the blades.

[0066] Figure 1 is a flow chart of a pitch control method based on a BP neural network according to an exemplary embodiment. Figure 1 As shown, it should be noted that the pitch control method based on the BP neural network of the embodiment of the present disclosure is applied to the pitch control device based on the BP neural network. Figure 1 As shown, the method may include the following steps:

[0067] Step 101: Obtain a first target rotation speed and an actual rotation speed of a wind turbine generator, and determine a first error value between the first target rotation speed and the actual rotation speed.

[0068] In one embodiment, the first target speed may be a target speed preset according to actual needs.

[0069] As an example, the first target speed can be subtracted from the actual speed to obtain a first error value:

[0070] Step 102: Input the first target speed, the actual speed and the first error value into the trained BP neural network to obtain the proportional coefficient and the integral coefficient output by the BP neural network.

[0071] In one embodiment, the first target speed, the actual speed and the first error value may be input into a trained BP neural network, and the BP neural network calculates a proportional coefficient and an integral coefficient based on the first target speed, the actual speed and the first error value.

[0072] In some embodiments of the present application, Figure 2As shown, the BP neural network can be divided into a network input layer, a network hidden layer, and a network output layer. In the present invention, the number of network hidden layers is 1. Assume that the input layer has M input nodes, Q hidden layer nodes, and 2 output nodes. The input node corresponds to the selected system operation state quantity, which can generally be the input and output of the system at different times. Here, r(k), y(k), e(k), and 1 are selected. The output node corresponds to two parameters of the PI controller. The hidden layer neuron activation function f(x) is taken as a positive and negative symmetric Sigmoid function, and the output layer neuron activation function g(x) is taken as a non-negative Sigmoid function. It is agreed that the superscripts (1), (2), and (3) represent the input layer, hidden layer, and output layer, respectively.

[0073] In one embodiment, the network input layer can be represented by the following formula:

[0074]

[0075] Where j = 1, 2, ..., M, x(j) is the system input node, is the network input layer.

[0076] The input of the hidden layer of the network is:

[0077]

[0078] where w ii is the weight coefficient of the network hidden layer.

[0079] The output of the hidden layer of the network is:

[0080]

[0081] Where i = 1, 2, …, Q, f(x) is the activation function of the hidden layer of the network.

[0082] The input of the network output layer is:

[0083]

[0084] Among them, w li is the weight coefficient of the network output layer.

[0085] The output of the network output layer is:

[0086]

[0087]

[0088]

[0089] Where l = 1, 2, g(x) is the activation function of the network output layer, Kp is the updated proportional coefficient of the PI controller, and Ki is the updated integral coefficient of the PI controller.

[0090] Step 103: Update the configuration parameters of the PI controller using the proportional coefficient and the integral coefficient to obtain an updated PI controller.

[0091] In one embodiment, the current proportional coefficient of the PI controller is updated to the proportional coefficient output by the BP neural network, and the current integral coefficient of the PI controller is updated to the integral coefficient output by the BP neural network.

[0092] Step 104 , inputting the first error into the updated PI controller to obtain a first blade angle output by the updated PI controller.

[0093] In one embodiment, the PI controller may calculate the first blade angle using the following formula:

[0094] u(k)=u(k-1)+Δu(k)

[0095] Δu(k)=Kp*(e(k)-e(k-1))+Ki*(e(k))

[0096] Among them, u(k) is the output of the PI controller in the current kth control round (that is, the first blade angle), u(k-1) is the output of the PI controller in the previous control round, e(k) is the system error (that is, the first error value), that is, the input of the PI controller, Kp is the proportional coefficient of the PI controller after update, and Ki is the integral coefficient of the PI controller after update.

[0097] It should be noted that before controlling the wind turbine for the first time, the proportional coefficient and the integral coefficient may be initialized.

[0098] Step 105, adjusting the blade angle of the wind turbine based on the first blade angle, and returning to execute the operation step of obtaining the first target rotation speed and the actual rotation speed of the wind turbine.

[0099] In one embodiment, during the operation of the wind turbine generator, steps 101 to 105 may be executed cyclically until the wind turbine generator stops operating.

[0100] In some embodiments of the present application, step 105 may specifically include the following steps:

[0101] Get the current pitch angle of the wind turbine;

[0102] Determine the second pitch angle based on the current pitch angle and the first pitch angle using a pitch gain table; the pitch gain table is obtained based on a nonlinear function of the pitch angle;

[0103] The current pitch angle of the wind turbine is adjusted to a second pitch angle.

[0104] In one embodiment, Figure 3 As shown, after the PI controller calculates the first pitch angle u(k), the variable pitch gain table (i.e., the nonlinear function G(β) based on the pitch angle) is used to determine the second pitch angle u'(k) based on the current pitch angle and the first pitch angle, and the current pitch angle of the wind turbine is adjusted to the second pitch angle u'(k).

[0105] In some embodiments of the present application, Figure 3 As shown, a first target speed r(k) and an actual speed y(k) of the wind turbine are obtained, a first error value e(k) between r(k) and y(k) is determined, r(k), y(k) and e(k) are input into the trained BP neural network, a proportional coefficient Kp and an integral coefficient Ki output by the BP neural network are obtained, Kp and Ki are used to update the configuration parameters of the PI controller, an updated PI controller is obtained, e(k) is input into the updated PI controller, a first blade angle u(k) output by the updated PI controller is obtained, the blade angle of the wind turbine is adjusted based on the first blade angle, a second pitch angle u'(k) is determined based on the current pitch angle and the first pitch angle using a pitch gain table (i.e., a nonlinear function G(β) based on the pitch angle), and the current pitch angle of the wind turbine is adjusted to the second pitch angle u'(k).

[0106] In some embodiments of the present application, before step 101, the method may further include:

[0107] Step a1: when the rotation speed of the wind turbine generator reaches the rated rotation speed, obtain the second target rotation speed and the actual rotation speed of the wind turbine generator.

[0108] Step a2, calculating the difference between the second target speed and the actual speed, and obtaining a second error value corresponding to the current parameter optimization round.

[0109] Step a3: modifying the weighted coefficients in the BP neural network to be trained based on the second error value to obtain a modified BP neural network.

[0110] In some embodiments of the present application, the BP neural network includes an input layer, a hidden layer and an output layer, and step a3 may specifically include the following steps:

[0111] The first change is calculated using the following formula:

[0112]

[0113]

[0114] Among them, Δw li (k) is the first change in the kth parameter optimization round, Δw li (k-1) is the first change in the k-1th parameter optimization round, η is the learning rate; α is the inertia coefficient, is the i-th output value of the hidden layer, e(k) is the second error value, G(β) is the nonlinear function of the pitch angle, y(k) is the actual speed, u(k) is the first blade angle, is the output value of the network layer, and g(x) is the activation function of the output layer;

[0115] Adding the first change amount to the output layer weight coefficient corresponding to the previous parameter optimization round to obtain a first weight coefficient;

[0116] The second change of the hidden layer is calculated using the following formula:

[0117]

[0118] Among them, Δw ij (k) is the second change in the kth parameter optimization round, Δw ij (k-1) is the second change in the k-1th parameter optimization round, is the jth input value of the input layer, and f(x) is the activation function of the output layer;

[0119] Adding the second change amount to the hidden layer weight coefficient corresponding to the previous parameter optimization round to obtain a second weight coefficient;

[0120] The first weighting coefficient is used to correct the weighting coefficient of the output layer, and the second weighting coefficient is used to correct the weighting coefficient of the hidden layer to obtain a corrected BP neural network.

[0121] In one embodiment, the network weight coefficients may be modified according to the gradient descent method with the addition of an inertia term that enables the search to converge quickly to the global minimum.

[0122] As an example, the change Δw of the output layer network weight coefficient in the kth parameter optimization round is li (k) can be expressed by the following formula:

[0123]

[0124] Among them, η is the learning rate; α is the inertia coefficient.

[0125] The partial differential term in the above formula can be derived as follows:

[0126]

[0127] in,

[0128] Unknown, symbolic functions available Replacement; is the nonlinear gain scheduling function of the pitch controller, which is a function of the pitch angle β and is only related to the actual pitch angle fed back by the wind turbine;

[0129] against When l = 1,

[0130] When l = 2, in Derivative of the output layer activation function:

[0131]

[0132] in, is the hidden layer output.

[0133] Therefore, the output layer network weight coefficient learning algorithm can be simplified as:

[0134]

[0135] Similarly, the learning algorithm for the hidden layer network weight coefficient is:

[0136]

[0137] in,

[0138] Step a4: determining whether the BP neural network to be trained has converged based on the second target speed and the actual speed.

[0139] In some embodiments of the present application, step a4 may specifically include the following steps:

[0140] The performance index function value of the BP neural network to be trained is calculated using the following formula:

[0141] J = 0.5 (r(k) - y(k)) 2

[0142] Wherein, J is the performance index function value, r(k) is the second target speed, and y(k) is the actual speed;

[0143] When the performance indicator function value meets the preset conditions, it is determined that the BP neural network to be trained converges;

[0144] When the performance indicator function value does not meet the preset condition, it is determined that the BP neural network to be trained has not converged.

[0145] Step a5, when it is determined that the BP neural network to be trained has not converged, return to step a1 and execute until it is determined that the BP neural network to be trained has converged, thereby obtaining a BP neural network that has completed training.

[0146] In one embodiment, before executing step a1, the pitch nonlinear function G(β) may be initialized in advance according to the blade parameters of the wind turbine. Also, the network weight coefficient, learning rate and inertia coefficient may be initialized in advance.

[0147] According to the variable pitch control method based on BP neural network proposed in the embodiment of the present disclosure, by obtaining the first target speed and the actual speed of the wind turbine, the first error value between the first target speed and the actual speed is determined, the first target speed, the actual speed and the first error value are input into the trained BP neural network, the proportional coefficient and the integral coefficient output by the BP neural network are obtained, the configuration parameters of the PI controller are updated using the proportional coefficient and the integral coefficient, the updated PI controller is obtained, the first error is input into the updated PI controller, the first blade angle output by the updated PI controller is obtained, and the blade angle of the wind turbine is adjusted based on the first blade angle. The proportional coefficient and the integral coefficient in the BP neural network are optimized in a nonlinear manner through the BP neural network, so that the accuracy of the control parameters of the variable pitch controller can be improved, thereby improving the accuracy of the control of the blades.

[0148] Figure 4 is a block diagram of a pitch control device based on a BP neural network according to an exemplary embodiment. Figure 4 The device includes a first determining unit 401, an input unit 402, an updating unit 403, an output unit 404 and an adjusting unit 405.

[0149] The first determining unit 401 is used to obtain a first target speed and an actual speed of the wind turbine, and determine a first error value between the first target speed and the actual speed;

[0150] An input unit 402 is used to input the first target speed, the actual speed and the first error value into the trained BP neural network to obtain a proportional coefficient and an integral coefficient output by the BP neural network;

[0151] An updating unit 403, used to update the configuration parameters of the PI controller using the proportional coefficient and the integral coefficient to obtain an updated PI controller;

[0152] An output unit 404 is used to input the first error into the updated PI controller to obtain a first blade angle output by the updated PI controller;

[0153] The adjusting unit 405 is used to adjust the blade angle of the wind turbine based on the first blade angle, and return to execute the operation step of obtaining the first target rotation speed and the actual rotation speed of the wind turbine.

[0154] In some embodiments of the present application, the device further includes:

[0155] an acquisition unit, configured to acquire a second target rotational speed and an actual rotational speed of the wind generator when the rotational speed of the wind generator reaches the rated rotational speed;

[0156] A calculation unit, used to calculate the difference between the second target speed and the actual speed, and obtain a second error value corresponding to the current parameter optimization round;

[0157] A correction unit, used for correcting the weighted coefficients in the BP neural network to be trained based on the second error value to obtain a corrected BP neural network;

[0158] A second determining unit, used to determine whether the BP neural network to be trained converges based on the second target speed and the actual speed;

[0159] The execution unit is used to return to the step of obtaining the second target speed and the actual speed of the wind generator when the speed of the wind generator reaches the rated speed when it is determined that the BP neural network to be trained has not converged, until it is determined that the BP neural network to be trained has converged, thereby obtaining a BP neural network that has completed training.

[0160] In some embodiments of the present application, the BP neural network includes an input layer, a hidden layer and an output layer, and the correction unit can be specifically used to perform the following steps:

[0161] The first change is calculated using the following formula:

[0162]

[0163] Among them, Δw li (k) is the first change in the kth parameter optimization round, Δw li (k-1) is the first change in the k-1th parameter optimization round, η is the learning rate; α is the inertia coefficient, is the i-th output value of the hidden layer, e(k) is the second error value, G(β) is the nonlinear function of the pitch angle, y(k) is the actual speed, u(k) is the first blade angle, is the output value of the network layer, and g(x) is the activation function of the output layer;

[0164] Adding the first change amount to the output layer weight coefficient corresponding to the previous parameter optimization round to obtain a first weight coefficient;

[0165] The second change of the hidden layer is calculated using the following formula:

[0166]

[0167] Among them, Δw ij (k) is the second change in the kth parameter optimization round, Δw ij (k-1) is the second change in the k-1th parameter optimization round, is the jth input value of the input layer, and f(x) is the activation function of the output layer;

[0168] Adding the second change amount to the hidden layer weight coefficient corresponding to the previous parameter optimization round to obtain a second weight coefficient;

[0169] The first weighting coefficient is used to correct the weighting coefficient of the output layer, and the second weighting coefficient is used to correct the weighting coefficient of the hidden layer to obtain a corrected BP neural network.

[0170] In some embodiments of the present application, the second determining unit may be specifically configured to perform the following steps:

[0171] The performance index function value of the BP neural network to be trained is calculated using the following formula:

[0172] J = 0.5 (r(k) - y(k)) 2

[0173] Wherein, J is the performance index function value, r(k) is the second target speed, and y(k) is the actual speed;

[0174] When the performance indicator function value meets the preset conditions, it is determined that the BP neural network to be trained converges;

[0175] When the performance indicator function value does not meet the preset condition, it is determined that the BP neural network to be trained has not converged.

[0176] In some embodiments of the present application, the execution unit may be specifically configured to execute the following steps:

[0177] Get the current pitch angle of the wind turbine;

[0178] Determine the second pitch angle based on the current pitch angle and the first pitch angle using a pitch gain table; the pitch gain table is obtained based on a nonlinear function of the pitch angle;

[0179] The current pitch angle of the wind turbine is adjusted to the second pitch angle. Regarding the device in the above embodiment, the specific way in which each module performs the operation has been described in detail in the embodiment of the method, and will not be described in detail here.

[0180] According to the variable pitch control device based on BP neural network proposed in the embodiment of the present disclosure, by obtaining the first target speed and the actual speed of the wind turbine, the first error value between the first target speed and the actual speed is determined, the first target speed, the actual speed and the first error value are input into the trained BP neural network, the proportional coefficient and the integral coefficient output by the BP neural network are obtained, the configuration parameters of the PI controller are updated using the proportional coefficient and the integral coefficient, the updated PI controller is obtained, the first error is input into the updated PI controller, the first blade angle output by the updated PI controller is obtained, and the blade angle of the wind turbine is adjusted based on the first blade angle. The proportional coefficient and the integral coefficient in the BP neural network are optimized in a nonlinear manner through the BP neural network, so that the accuracy of the control parameters of the variable pitch controller can be improved, thereby improving the accuracy of the control of the blades.

[0181] Figure 5 It is a block diagram of a device for a pitch control method based on a BP neural network according to an exemplary embodiment. For example, the device 500 may be an electronic device, such as a programmable logic controller PLC or a computer.

[0182] Reference Figure 5 , the apparatus 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , a sensor component 514 , and a communication component 516 .

[0183] The processing component 502 generally controls the overall operation of the device 500, such as communicating with the display and data. The processing component 502 may include one or more processors 520 to execute instructions to complete all or part of the steps of the above method. In addition, the processing component 502 may include one or more modules to facilitate the interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate the interaction between the multimedia component 508 and the processing component 502.

[0184] The memory 504 is configured to store various types of data to support operations on the device 500. Examples of such data include instructions for any application or method operating on the device 500. The memory 504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, or flash memory.

[0185] Power component 506 provides power to various components of device 500. Power component 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for device 500.

[0186] The multimedia component 508 includes a screen that provides an output interface between the device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0187] The sensor assembly 514 includes one or more sensors for providing various aspects of status evaluation for the device 500. For example, the sensor assembly 514 may include an absolute encoder for evaluating the impeller position and impeller speed, and may also include an anemometer for evaluating wind speed, etc. In addition, it may also include other sensors for wind turbines, such as: a vibration sensor, an incremental encoder, an anemometer vane, a temperature sensor, and a pressure sensor.

[0188] The communication component 516 is configured to facilitate wired or wireless communication between the apparatus 500 and other devices. For example, an industrial bus such as modbus-tcp, modbus-rtu, canopen, profibus, etc. can be used to implement wind turbine network communication.

[0189] In an exemplary embodiment, the apparatus 500 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above methods.

[0190] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the instructions can be executed by the processor 520 of the device 500 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0191] In an exemplary embodiment, a computer program product is also provided, comprising a computer program, which implements the above method when executed by the processor 520 of the device 500.

[0192] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0193] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A pitch control method based on BP neural network, characterized in that: include: Acquire a first target speed and an actual speed of the wind turbine, and determine a first error value between the first target speed and the actual speed; Inputting the first target speed, the actual speed and the first error value into the trained BP neural network to obtain a proportional coefficient and an integral coefficient output by the BP neural network; Updating the configuration parameters of the PI controller using the proportional coefficient and the integral coefficient to obtain the updated PI controller; Inputting the first error into the updated PI controller to obtain a first blade angle output by the updated PI controller; The blade angle of the wind turbine is adjusted based on the first blade angle, and the process returns to the step of obtaining the first target rotational speed and the actual rotational speed of the wind turbine.

2. The pitch control method based on BP neural network according to claim 1 is characterized in that: Before obtaining the first target rotation speed and the actual rotation speed of the wind turbine, the method further includes: When the speed of the wind turbine generator reaches the rated speed, obtaining a second target speed and an actual speed of the wind turbine generator; Calculating the difference between the second target speed and the actual speed to obtain a second error value corresponding to the current parameter optimization round; Based on the second error value, a weighted coefficient in the BP neural network to be trained is corrected to obtain a corrected BP neural network; Determining whether the BP neural network to be trained converges based on the second target speed and the actual speed; When it is determined that the BP neural network to be trained has not converged, return to execute the step of obtaining the second target speed and the actual speed of the wind generator when the speed of the wind generator reaches the rated speed, until it is determined that the BP neural network to be trained has converged, thereby obtaining the BP neural network that has completed training.

3. The pitch control method based on BP neural network according to claim 2 is characterized in that: The BP neural network includes an input layer, a hidden layer and an output layer; The method of correcting the weighted coefficients in the BP neural network to be trained based on the second error value to obtain a corrected BP neural network includes: The first change is calculated using the following formula: Among them, Δw li (k) is the first change in the kth parameter optimization round, Δw li (k-1) is the first change in the k-1th parameter optimization round, η is the learning rate; α is the inertia coefficient, is the i-th output value of the hidden layer, e(k) is the second error value, G(β) is the nonlinear function of the pitch angle, y(k) is the actual speed, u(k) is the first blade angle, is the output value of the network layer, and g(x) is the activation function of the output layer; Adding the first change amount to the output layer weight coefficient corresponding to the previous parameter optimization round to obtain a first weight coefficient; The second variation of the hidden layer is calculated using the following formula: Among them, Δw ij (k) is the second change in the kth parameter optimization round, Δw ij (k-1) is the second change in the k-1th parameter optimization round, is the jth input value of the input layer, and f(x) is the activation function of the output layer; Adding the second change amount to the hidden layer weight coefficient corresponding to the previous parameter optimization round to obtain a second weight coefficient; The weighted coefficient of the output layer is corrected using the first weighted coefficient, and the weighted coefficient of the hidden layer is corrected using the second weighted coefficient to obtain the corrected BP neural network.

4. The pitch control method based on BP neural network according to claim 2 is characterized in that: The determining whether the BP neural network to be trained converges based on the second target speed and the actual speed includes: The performance index function value of the BP neural network to be trained is calculated using the following formula: J=0.5(r(k)-y(k)) 2 Wherein, J is the performance index function value, r(k) is the second target speed, and y(k) is the actual speed; When the performance indicator function value satisfies a preset condition, determining that the BP neural network to be trained converges; When the performance indicator function value does not satisfy a preset condition, it is determined that the BP neural network to be trained has not converged.

5. The pitch control method based on BP neural network according to claim 1, characterized in that: The adjusting the blade angle of the wind turbine based on the first blade angle includes: Acquire the current pitch angle of the wind turbine; Determine a second pitch angle based on the current pitch angle and the first pitch angle using a pitch gain table; the pitch gain table is obtained based on a nonlinear function of the pitch angle; The current pitch angle of the wind turbine is adjusted to the second pitch angle.

6. A pitch control device based on BP neural network, characterized in that: include: a first determining unit, configured to obtain a first target speed and an actual speed of the wind turbine, and determine a first error value between the first target speed and the actual speed; An input unit, used for inputting the first target speed, the actual speed and the first error value into the trained BP neural network to obtain a proportional coefficient and an integral coefficient output by the BP neural network; An updating unit, configured to update configuration parameters of a PI controller using the proportional coefficient and the integral coefficient to obtain an updated PI controller; an output unit, configured to input the first error into the updated PI controller to obtain a first blade angle output by the updated PI controller; An adjustment unit is used to adjust the blade angle of the wind turbine based on the first blade angle, and return to execute the operation step of obtaining the first target rotation speed and actual rotation speed of the wind turbine.

7. The pitch control device based on BP neural network according to claim 1, characterized in that: The device also includes: an acquisition unit, configured to acquire a second target rotational speed and an actual rotational speed of the wind generator when the rotational speed of the wind generator reaches a rated rotational speed; a calculation unit, configured to calculate a difference between the second target speed and the actual speed, and obtain a second error value corresponding to a current parameter optimization round; A correction unit, configured to correct the weight coefficients in the BP neural network to be trained based on the second error value to obtain a corrected BP neural network; a second determining unit, configured to determine whether the BP neural network to be trained has converged based on the second target speed and the actual speed; The execution unit is used to return to the step of obtaining the second target speed and the actual speed of the wind turbine when the speed of the wind turbine reaches the rated speed when it is determined that the BP neural network to be trained has not converged, until it is determined that the BP neural network to be trained has converged, thereby obtaining the BP neural network that has completed training.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

10. A computer program product, comprising a computer program, characterized in that The computer program implements the method according to any one of claims 1 to 5 when executed by a processor.

Images