Offshore wind turbine pitch control method, system, device and medium

Abstract

The present invention belongs to the field of wind turbine control technology. In order to solve the problem that existing wind turbines are insufficient in speed and robustness when coping with unstable wind conditions and changeable environments at sea, a method, system, equipment and medium for offshore wind turbine pitch control are proposed. The wind turbine pitch control parameters are determined by modeling; an interval type-II fuzzy controller and a PID controller for wind turbine pitch control are constructed, and the PID controller parameters are optimized by an improved crow search algorithm; the improved crow search algorithm dynamically adjusts the perception probability and flight length during the search process by a variable function; the optimized PID controller and interval type-II fuzzy controller are used to adjust the wind turbine pitch control parameters to realize wind turbine pitch control, thereby further improving the speed and robustness of the control method.

Description

Technical Field

[0001] The present invention belongs to the technical field related to wind turbine control, and in particular relates to a method, system, equipment and medium for controlling pitch of an offshore wind turbine. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Offshore wind turbines can access more abundant wind energy resources than onshore wind turbines. However, the complex and changeable wind environment at sea can cause rapid fluctuations in wind turbine loads, thereby affecting the service life and safety of wind turbines. Therefore, more advanced control strategies are needed to maintain wind turbine load stability under complex wind conditions.

[0004] To address load fluctuations, wind turbines typically use pitch control and stall control to adjust their power output and speed in response to varying wind conditions. With the development of wind power generation technology, wind turbines based on pitch control have become the predominant type of wind turbine. Currently, the primary method for wind turbine pitch control is pitch control based on the PID algorithm. While the PID algorithm offers better controllability and higher control accuracy than other control methods, it still struggles with speed and robustness in unstable offshore wind conditions and changing environments.

[0005] Therefore, how to improve the speed and robustness of wind turbine pitch control when dealing with unstable wind conditions and changing environments at sea is a problem that needs to be solved. Summary of the Invention

[0006] In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides a method, system, equipment and medium for offshore wind turbine pitch control, which combines the controllability and accuracy of the PID algorithm, and adopts the interval type-II fuzzy control method on the basis of fuzzy control to further improve the speed and robustness of the control method.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a method for controlling pitch of an offshore wind turbine, comprising:

[0009] Determining wind turbine pitch control parameters based on a wind turbine actuator model and a transmission mechanism model;

[0010] Construct an interval type-II fuzzy controller and a PID controller for wind turbine pitch control, and use the crow search algorithm to optimize the PID controller parameters;

[0011] The optimized PID controller and interval type-II fuzzy controller are used to adjust the wind turbine pitch control parameters to achieve wind turbine pitch control.

[0012] In a second aspect, the present invention provides an offshore wind turbine pitch control system, comprising:

[0013] a determination module configured to: determine a wind turbine pitch control parameter based on a wind turbine actuator model and a transmission mechanism model;

[0014] A building module is configured to: build an interval type-II fuzzy controller and a PID controller for wind turbine pitch control, and optimize the PID controller parameters using a crow search algorithm;

[0015] The control module is configured to adjust the wind turbine pitch control parameters by using the optimized PID controller and the interval type-II fuzzy controller to realize the wind turbine pitch control.

[0016] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0018] One or more of the above technical solutions have the following beneficial effects:

[0019] The present invention first models the wind turbine's pitch actuator and transmission mechanism to determine the wind turbine's pitch control parameters; combines the controllability and accuracy of the PID algorithm, and adopts the interval type-II fuzzy control method on the basis of fuzzy control to further improve the speed and robustness of the control method.

[0020] The present invention optimizes PID controller parameters through an improved crow search algorithm and dynamically adjusts the perception probability and flight length during the search process through a ramping function. This can not only improve the global search capability of the algorithm in the early stage, ensuring the rapid determination of the range of the optimal solution when the number of crows N is large, but also ensure the local search capability in the later stage and select the optimal PID parameters.

[0021] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0023] FIG1( a ) is a schematic diagram of the E membership function in the first embodiment of the present invention;

[0024] FIG1 (b) is an example of E in the first embodiment of the present invention. C Schematic diagram of membership function;

[0025] FIG2 (a) shows a fuzzy rule of a type 1 fuzzy control of E in the first embodiment of the present invention;

[0026] FIG2 (b) is an example of E in the first embodiment of the present invention. C Type I fuzzy control fuzzy rules;

[0027] FIG2 (c) is a schematic diagram of torque output in the first embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of a fuzzy output surface of a type fuzzy control in embodiment 1 of the present invention;

[0029] FIG4 (a) is an interval type-2 fuzzy controller input membership function of E in the first embodiment of the present invention;

[0030] FIG4 (b) is an example of E in the first embodiment of the present invention. C The input membership function of the interval type-2 fuzzy controller;

[0031] Figure 5 is the fuzzy output surface of the interval type-2 fuzzy controller in the first embodiment of the present invention;

[0032] Figure 6 Comparison of simulation results in Example 1 of the present invention;

[0033] Figure 7 This is a flow chart of a pitch control method for an offshore wind turbine in Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0034] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0035] It should be noted that the terms used herein are for describing particular embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0036] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0037] Example 1

[0038] This embodiment discloses a method for controlling pitch control of an offshore wind turbine, comprising:

[0039] Determining wind turbine pitch control parameters based on a wind turbine actuator model and a transmission mechanism model;

[0040] Construct an interval type-II fuzzy controller and a PID controller for wind turbine pitch control, and use the crow search algorithm to optimize the PID controller parameters;

[0041] The optimized PID controller and interval type-II fuzzy controller are used to adjust the wind turbine pitch control parameters to achieve wind turbine pitch control.

[0042] The following combination Figure 7 The present invention provides a detailed description of the offshore wind turbine pitch control method.

[0043] Step 1: Based on the various parameters of the wind turbine used, establish the mathematical model of the pitch actuator and transmission mechanism.

[0044] (1) Establish a mathematical model of the wind turbine pitch actuator:

[0045] For the pitch actuator, it is simplified to a first-order inertia link:

[0046] (1)

[0047] Where, is the time constant, is the pitch angle reference value, is the current pitch angle of the wind turbine. Applying Laplace transform to this equation, we can get the transfer function of the pitch actuator:

[0048] (2)

[0049] (2) Establish a mathematical model of the wind turbine transmission mechanism:

[0050] According to the transmission system dynamics, the mathematical model of the transmission system can be expressed as:

[0051] (3)

[0052] Where, is the moment of inertia of the transmission system, is the damping coefficient of the transmission system, is the transmission system rotor speed, is the transmission system torque, and applying Laplace transform to this formula yields:

[0053] (4)

[0054] in, s represents a complex frequency domain variable.

[0055] The above completes the establishment of the mathematical model of the variable pitch actuator and transmission mechanism.

[0056] Specifically, the output of the controller is the torque of the transmission system , the current pitch angle of the wind turbine The controller input is the desired pitch angle as feedback to the controller. The controller changes the torque of the transmission system by To change the pitch angle of the pitch actuator , thereby realizing variable pitch control of offshore wind turbines.

[0057] Step 2: Offshore wind speeds vary rapidly, so the pitch control system often needs to respond to wind speed changes within seconds or even milliseconds to avoid power fluctuations or excessive mechanical loads. The PID control algorithm has strong adaptability and rapid response, allowing for timely response to offshore wind speed changes. Therefore, a PID controller is designed to control the pitch of offshore wind turbines.

[0058] The performance of the PID controller directly depends on the proportional gain K p , integral gain K i , differential gain K d With the proper setting of these three parameters, the Crow Search algorithm is more likely to find the globally optimal PID parameter combination than traditional PID parameter tuning methods. It also offers advantages over other intelligent algorithms, such as simplified parameter tuning and higher computational efficiency. The Crow Search algorithm allows for quick and accurate PID parameter tuning, resulting in an optimal PID controller and improving the pitch system's response to wind speed changes.

[0059] For the proportional gain K of the PID algorithm p , integral gain K i , differential gain K d Three parameters, use the crow search algorithm to adjust the PID parameters. The crow search algorithm simulates the two behaviors of crows in nature: hiding and stealing food. In the algorithm, each crow represents a group of K p , K i , K d Each crow represents a candidate solution, and the location of the hidden food represents the location of the solution. The crow updates its own location by memorizing and observing the behavior of other crows, thereby gradually optimizing the objective function. The algorithm steps are as follows:

[0060] Initialization: First define the objective function f(X) is a function of three parameters and response time, where X is the solution vector of the three parameters and defines the range of the search space. Set the number of crows N , maximum number of iterations T max , perception probability AP , flight length fl , randomly generated N The initial position of the crows X i (i=1,2,... N ), initialize the memory of each crow M i , the initial memory value is X i .

[0061] Iterative optimization: For each iteration t =1,2,..., T max :

[0062] 1) Randomly select a target to follow:

[0063] For each crow i , randomly select another crow j ( j ≠ i ) as the target to follow.

[0064] 2) Update location:

[0065] If the crow j The probability of being discovered is greater than the probability of being perceived AP ,crow i Will try to steal crows j Food:

[0066] (5)

[0067] in, r is a random number between [0,1], represents the position of crow i in the tth iteration; fl Indicates the flight length. It's a crow j Memory, otherwise, crow i Moves to a random new location.

[0068] 3) Boundary processing:

[0069] If the new location If it is outside the search space, it is adjusted to be within the boundaries.

[0070] 4) Update memory:

[0071] Calculate the fitness value of the new position If the fitness value of the new position is better than the fitness value in memory, update the memory Otherwise, the memory remains unchanged, i.e. .

[0072] Output result: When the maximum number of iterations is reached T When max or a satisfactory solution is found, the algorithm terminates and outputs the global optimal solution and its fitness value.

[0073] Since the model parameters of the offshore wind turbine transmission mechanism and pitch actuator are usually large, the parameter values ​​of the PID controller are also relatively large, which will result in a very large number of crows, and the perception probability in the algorithm is AP and flight length fl They determine the crow's exploration ability and search step size respectively. Now we construct a variable function to dynamically change the values ​​of the two parameters:

[0074]

[0075] in, and They are AP The maximum and minimum values ​​of the function are shown in Figure 2. The curve of the function is a concave descending curve. As the number of iterations t increases, the perception probability AP Decline, gradually changing from focusing on global exploration to focusing on local exploration; the constant coefficient α>1 in the formula, by changing the value of the constant coefficient α, the decreasing ability of the curve can be changed. Similarly, for the flight length fl :

[0076]

[0077] in, 、 Flight length fl The maximum and minimum values ​​of , t represents the current number of iterations.

[0078] Dynamically change the algorithm perception probability by introducing a gradual change function AP and flight length fl , which not only improves the global search capability of the algorithm in the early stage, ensuring the rapid determination of the optimal solution range when the number of crows N is large, but also ensures the local search capability in the later stage, and can select the optimal PID parameters. and A larger value should be taken to increase the global search ability in the early stage of the algorithm.

[0079] Step 3: Offshore wind conditions are very complex. To ensure smooth output from wind turbines under various wind conditions, the controller must be tolerant to disturbances. Fuzzy control is suitable for nonlinear systems and offers strong robustness. To handle the uncertainties and output fluctuations caused by nonlinear wind conditions, a fuzzy controller is designed to improve the robustness of pitch control.

[0080] The output of a type fuzzy controller is the torque of the transmission system. This embodiment adopts the TS type fuzzy control method to calculate the feedback error E and the error change rate E. C As the input of a type fuzzy control system, the feedback error E refers to the reference value of the pitch angle With the current pitch angle The difference, error change rate E C is the differential of the feedback error E, E and E C The domains of the input variables are [-1, 1] and [-1.314, 1.314] respectively. The fuzzy sets are all represented by sets containing three fuzzy linguistic values: N (Negative), Z (Zero), and P (Positive). Trigonometric functions are selected as the membership functions of the input variables. The fuzzy linguistic value divisions of the input variables and the membership functions are shown in Figure 1 (a)-Figure 1 (b).

[0081] The fuzzy set of input variables is divided into five fuzzy language values: HN (High Negative), N (Negative), Z (Zero) P (Positive), and HP (High Positive). The output variable membership function of the TS-type fuzzy control can only be a linear or constant function of the input. To simplify the process, the output variable membership function is a constant function. The five fuzzy language values ​​correspond to the constant values ​​of -5.24e+06, -2.62e+06, 0, 2.62e+06, and 5.24e+06, respectively. The selection of fuzzy rules is based on expert experience. The fuzzy rules of the type I fuzzy controller are shown in Table 1 and Figures 2(a)-2(c). The fuzzy output surface of the type I fuzzy controller is shown in Figure 3 shown.

[0082] Table 1: Fuzzy rules table

[0083]

[0084] The commonly used defuzzification methods of TS fuzzy control method include weighted averaging and weighted summation. This design chooses weighted averaging as the controller defuzzification method.

[0085] Step 4: Based on the type-1 fuzzy controller, further design the interval type-2 fuzzy controller.

[0086] Interval type-2 fuzzy control is an extension of traditional type-1 fuzzy control. It is mainly used to deal with higher-level uncertainties and is more suitable for situations with large wind speed fluctuations. Interval type-2 fuzzy and type-1 fuzzy share the basis of fuzzy logic. Therefore, the uncertainty footprint FOU can be directly introduced on the basis of type-1 fuzzy membership function to form upper and lower membership functions. At the same time, the fuzzy rules of type-1 fuzzy are used, and the fuzzy sets are replaced with interval type-2 fuzzy sets. In addition, the reduction method is added to realize the conversion from interval type-2 fuzzy output to type-1 fuzzy output, thereby realizing the design of interval type-2 fuzzy controller. The input membership function of type-2 fuzzy controller is shown in Figure 4 (a)-Figure 4 (b), and the fuzzy output surface of type-2 fuzzy controller is shown in Figure 4 (a)-Figure 4 (b). Figure 5 shown.

[0087] The input of interval type-2 fuzzy control is an interval type-2 fuzzy set, an interval type-2 fuzzy set on the domain X It can be expressed as:

[0088] (6)

[0089] Where, x and u represent the main and secondary variables of the fuzzy set, respectively. J x express x The main membership interval of , 1 / u means the secondary membership is 1, and ∫ means the union or sum of the sets.

[0090] The uncertainty footprint FOU can be expressed as:

[0091] (7)

[0092] Where, and denote the lower membership function and the upper membership function respectively,

[0093] The FOU reflects the tolerance of the interval type-2 fuzzy system to input uncertainty. The size and shape of the FOU directly affect the performance of the interval type-2 fuzzy controller. For the FOU introduced in this embodiment, corresponding improvements have also been made based on the characteristics of the offshore wind environment: the variable offshore wind environment usually causes large changes in the input E of the interval type-2 fuzzy control system. Therefore, in order to improve the robustness of the system, the FOU of the membership function of the feedback error E is wider; and a narrower FOU is introduced for the membership function of the error change rate Ec to ensure the control accuracy and response speed of the controller.

[0094] The width of the FOU depends on the lower lag parameter, LowerLag, and the lower scaling parameter, LowerScale, of the membership function. LowerLag represents the lateral offset of the lower membership function (LMF) relative to the upper membership function (UMF). It describes the lag of the LMF peak or key feature point relative to the UMF. Its value range is [0, 1]. Larger values ​​indicate greater lag and a wider FOU. LowerScale represents the amplitude scaling ratio of the lower membership function relative to the upper membership function. It determines the overall height of the UMF. Its value range is [0, 1]. Smaller values ​​indicate a smaller lower membership function height and a wider FOU. The variable wind environment at sea usually causes large changes in the input E of the interval type-II fuzzy control system. Therefore, in order to improve the robustness of the system, the LowerLag and LowerScale of the membership function of the feedback error E are taken as 0.4 and 0.8 respectively to ensure a larger FOU width and a stronger ability to handle uncertainty; and the LowerLag and LowerScale of the membership function of the error change rate Ec are taken as 0.2 and 0.9 respectively to ensure the control accuracy and response speed of the controller.

[0095] The introduction of FOU improves the ability of fuzzy control method to deal with uncertainty problems. The membership function used in the input of interval type-2 fuzzy controller and the fuzzy output surface of interval type-2 fuzzy control method are shown in Figures 4(a), 4(b) and Figure 5 shown.

[0096] For the membership function of the interval type-2 fuzzy controller input, the fuzzy sets corresponding to the three fuzzy language values ​​N, Z, and P are defined as follows: , , , then the membership function corresponding to E can be expressed as:

[0097]

[0098]

[0099] in, x Indicates the actual input value of the system. max and min represent the maximum and minimum operations respectively. Represent fuzzy sets The corresponding upper membership function and lower membership function. Represent fuzzy sets , The corresponding upper membership function and lower membership function.

[0100] The membership function is used to quantitatively describe the degree to which an element belongs to a fuzzy set. The letters and formulas in the formula are only used to describe the shape of the membership function and have only mathematical meanings.

[0101] You can use E C The corresponding membership function is expressed as:

[0102]

[0103] in, Indicates input E C Fuzzy set , , The corresponding upper membership function and lower membership function.

[0104] For the type reduction method of interval type-2 fuzzy controller, the Karnik-Mendel algorithm is used. The core idea of ​​the KM algorithm is to achieve accurate type reduction by iteratively calculating the upper and lower bounds of the center of mass. The calculation process is as follows:

[0105] (8)

[0106] (9)

[0107] (10)

[0108] Where y represents the interval type-II fuzzy output obtained by the fuzzy controller after fuzzy inference, and is also the input of the KM algorithm; and They represent the upper membership value and lower membership value corresponding to y respectively; n represents the number of algorithm input y, and k represents the dividing point of the y value corresponding to the upper membership and the y value corresponding to the lower membership; since the membership of the interval type II fuzzy set is an interval, its centroid is also an interval, y l Indicates the minimum centroid, which is the left endpoint of the interval, y r Indicates the maximum centroid, which is the right endpoint of the interval. It is a type fuzzy set output. represents the set of all membership values, Represents the set of all interval type-2 fuzzy output values.

[0109] The fuzzy controller cannot directly process the interval type-2 fuzzy output set. The KM algorithm can complete the type reduction operation of the interval type-2 fuzzy system and convert the type-2 fuzzy set into a type-1 fuzzy set so that the clear output can be obtained through defuzzification.

[0110] Step 5: Combine the designed PID controller and interval type-2 fuzzy controller in parallel to form an interval type-2 fuzzy PID parallel controller, and apply it to the established mathematical model of the wind turbine pitch actuator and transmission mechanism to complete the design of the pitch control method based on interval type-2 fuzzy PID parallel control.

[0111] The outputs of the PID controller and the interval type-2 fuzzy controller are both the torque of the transmission system , summing the outputs of the two, and changing the torque of the transmission system To change the pitch angle of the pitch actuator To achieve parallel control. In the parallel control method adopted in this embodiment, the PID controller plays a major role when the offshore wind speed changes rapidly, ensuring the rapid responsiveness of the pitch control. In addition, for complex and changeable offshore wind conditions, the interval type-2 fuzzy controller can make timely compensation for the output according to the disturbance, thereby improving the adaptability and robustness of the pitch control.

[0112] Figure 6 It is a simulation comparison diagram of PID control, fuzzy control, fuzzy PID control, and interval type-2 fuzzy PID parallel control.

[0113] The present invention proposes a method for offshore wind turbine pitch control based on interval type-2 fuzzy PID parallel control. For the parameter setting of the PID algorithm, an improved crow search algorithm (CSA) is used to find appropriate parameters, thereby improving the accuracy and controllability of the PID algorithm. Moreover, on the basis of type-1 fuzzy control, an interval type-2 fuzzy control method is used to further improve the rapidity and robustness of the fuzzy control method. Compared with the traditional fuzzy PID controller, the present invention proposes a parallel method for wind turbine pitch control, further combining the advantages of the PID algorithm and the interval type-2 fuzzy control method. Simulation proves that compared with the fuzzy PID controller, the interval type-2 fuzzy PID parallel controller reduces the response time and overshoot of pitch control, enables wind turbines to better adapt to the complex and changeable environment at sea, and quickly and accurately adjusts the pitch angle according to the wind conditions, thereby reducing the damage to the wind turbine blades and extending the service life of the wind turbine.

[0114] Example 2

[0115] The purpose of this embodiment is to provide an offshore wind turbine pitch control system, comprising:

[0116] a determination module configured to: determine a wind turbine pitch control parameter based on a wind turbine actuator model and a transmission mechanism model;

[0117] A building module is configured to: build an interval type-II fuzzy controller and a PID controller for wind turbine pitch control, and optimize the PID controller parameters using a crow search algorithm;

[0118] The control module is configured to adjust the wind turbine pitch control parameters by using the optimized PID controller and the interval type-II fuzzy controller to realize the wind turbine pitch control.

[0119] In further embodiments, there is also provided:

[0120] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed by the processor. When the computer instructions are executed by the processor, the method described in Example 1 is performed. For the sake of brevity, no further details are given here.

[0121] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0122] The memory may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0123] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in embodiment 1 is performed.

[0124] The method in Example 1 can be directly implemented as being executed by a hardware processor, or by a combination of hardware and software modules within the processor. The software module can be located in a storage medium well-established in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not given here.

[0125] Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0126] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A method for controlling the pitch of an offshore wind turbine, characterized in that: include: Determining wind turbine pitch control parameters based on a wind turbine actuator model and a transmission mechanism model; An interval type-II fuzzy controller and PID controller for wind turbine pitch control are constructed, and the PID controller parameters are optimized using an improved crow search algorithm. The improved crow search algorithm dynamically adjusts the perception probability and flight length during the search process through a ramp function. The interval type-2 fuzzy controller for wind turbine pitch control is constructed as follows: Using TS type fuzzy control method, a type I fuzzy controller is constructed; Based on the type-I fuzzy membership function, the uncertainty footprint FOU is introduced to form the upper and lower membership functions, the fuzzy sets are replaced by interval type-II fuzzy sets, and the type reduction method is added to realize the conversion from interval type-II fuzzy output to type-I fuzzy output, thus realizing the construction of interval type-II fuzzy controller for wind turbine pitch control. The dynamic adjustment of the perception probability and flight length during the search process by the variable function is specifically as follows: ； ； in, and are the maximum and minimum values ​​of the perception probability AP, respectively, and α is the coefficient; 、 Flight length The maximum and minimum values ​​of , t represents the current number of iterations; The optimized PID controller and interval type-II fuzzy controller are used to adjust the wind turbine pitch control parameters to achieve wind turbine pitch control. Specifically, the torque of the transmission system output by the optimized PID controller and the torque of the transmission system output by the interval type-II fuzzy controller are summed, and the pitch angle of the pitch actuator is changed according to the summed result of the transmission system torque, thereby achieving parallel control of the wind turbine pitch control.

2. The offshore wind turbine pitch control method according to claim 1, wherein: Using the TS fuzzy control method, a fuzzy controller is constructed, specifically: Feedback error E and error change rate E C As the input variable of a type fuzzy control controller; The fuzzy set of input variables is divided into different fuzzy linguistic values, trigonometric functions are selected as the membership functions of input variables, constant functions are selected as the membership functions of output variables, and a type I fuzzy controller is constructed.

3. The offshore wind turbine pitch control method according to claim 1, wherein: The introduced uncertainty footprint FOU width is determined by the lower bound lag parameter and the lower bound scaling parameter of the membership function.

4. The offshore wind turbine pitch control method according to claim 1, wherein: The Karnik-Mendel algorithm is used to reduce the interval type-2 fuzzy controller.

5. A pitch control system for an offshore wind turbine, characterized in that: include: a determination module configured to: determine a wind turbine pitch control parameter based on a wind turbine actuator model and a transmission mechanism model; A building module is configured to: construct an interval type-II fuzzy controller and a PID controller for wind turbine pitch control, and optimize the PID controller parameters using an improved crow search algorithm; the improved crow search algorithm dynamically adjusts the perception probability and flight length during the search process through a ramp function; The interval type-2 fuzzy controller for wind turbine pitch control is constructed as follows: Using TS type fuzzy control method, a type I fuzzy controller is constructed; Based on the type-I fuzzy membership function, the uncertainty footprint FOU is introduced to form the upper and lower membership functions, the fuzzy sets are replaced by interval type-II fuzzy sets, and the type reduction method is added to realize the conversion from interval type-II fuzzy output to type-I fuzzy output, thus realizing the construction of interval type-II fuzzy controller for wind turbine pitch control. The dynamic adjustment of the perception probability and flight length during the search process by the variable function is specifically as follows: ； ； in, and are the maximum and minimum values ​​of the perception probability AP, respectively, and α is the coefficient; 、 Flight length The maximum and minimum values ​​of , t represents the current number of iterations; The control module is configured to adjust the wind turbine pitch control parameters using an optimized PID controller and an interval type-II fuzzy controller to achieve wind turbine pitch control, specifically by summing the torque of the transmission system output by the optimized PID controller and the torque of the transmission system output by the interval type-II fuzzy controller, and changing the pitch angle of the pitch actuator according to the summed result of the transmission system torque to achieve parallel control of the wind turbine pitch control.

6. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method according to any one of claims 1 to 4 is completed.

7. A computer-readable storage medium, characterized in that Used to store computer instructions, which, when executed by a processor, complete the method according to any one of claims 1 to 4.

Images