Variable pitch control method and device for wind turbine generator, storage medium and terminal equipment

Abstract

The invention provides a wind turbine generator variable pitch control method and device, a storage medium and terminal equipment, and relates to the technical field of wind turbine generator variable pitch control. The method comprises the steps that current wind resource information of the environment where a target wind turbine generator is located and current operation parameters of the target wind turbine generator are obtained; the wind resource information serves as input, and wind resource prediction information of the environment where the target wind turbine generator is located at the next unit moment is output through a preset wind resource prediction model; and the variable-pitch fatigue state of the target wind turbine generator is determined according to the operation parameters of the target wind turbine generator, and based on the variable-pitch fatigue state of the target wind turbine generator, the target wind turbine generator is controlled to execute the variable-pitch operation at the next unit moment at the first pitch angle, or the target wind turbine generator is controlled to execute the variable-pitch operation at the next unit moment at the second pitch angle. The service life of the blade and the variable pitch bearing can be effectively prolonged.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine pitch control, and specifically to a wind turbine pitch control method, a wind turbine pitch control device, a computer-readable storage medium and a terminal device. Background Art

[0002] At present, the wind power industry's control logic for variable pitch motors mainly relies on real-time monitoring of wind speed and wind turbine output power, aiming to maintain the predetermined power output by dynamically adjusting the blade angle. Under high wind speed conditions, the blade angle will be adjusted to a smaller angle to avoid wind turbine overload; in extreme wind speeds (such as storms or gusts), the variable pitch system will adjust the blades to the "stop" position to reduce the force on the wind turbine and ensure the safe operation of the equipment. In addition, traditional control logic will also optimize the blade angle in real time according to changes in wind speed and wind direction to maximize energy capture efficiency and reduce air resistance. However, in traditional variable pitch control logic, if the variable pitch motor runs at the maximum output point for a long time, or the variable pitch action is frequently performed, it may cause the blades or pitch bearings to be in a fatigue condition continuously, thereby affecting their service life. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a wind turbine pitch control method, a wind turbine pitch control device, a computer-readable storage medium and a terminal device to solve the above problems.

[0004] In order to achieve the above-mentioned object, the first aspect of the present application provides a wind turbine pitch control method, comprising: Acquire current wind resource information of the environment in which the target wind turbine is located and current operating parameters of the target wind turbine; Taking the wind resource information as input, outputting the wind resource prediction information of the environment where the target wind turbine is located at the next unit time through a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms with historical wind resource information of the target wind turbine; If it is determined according to the operating parameters of the target wind turbine generator set that the target wind turbine generator set is not in a pitch change fatigue state, determining a first pitch angle corresponding to the wind resource prediction information, and controlling the target wind turbine generator set to perform a pitch change operation at the first pitch angle at a next unit time; If it is determined that the target wind turbine group is in a pitch fatigue state based on the operating parameters of the target wind turbine group, a second pitch angle of the target wind turbine group is determined based on a comparison result between the wind resource prediction information and the wind resource information, and the target wind turbine group is controlled to perform a pitch operation at the second pitch angle at a next unit time.

[0005] Optionally, the wind resource information at least includes the inflow wind speed of the environment in which the target wind turbine is located; and the wind resource prediction model at least includes: A first wind speed prediction model and a second wind speed prediction model; Taking the wind resource information as input, the preset wind resource prediction model outputs the wind resource prediction information of the environment where the target wind turbine is located at the next unit time, including: Taking the inflow wind speed of the environment where the target wind turbine is located as input, the first wind speed prediction model outputs a first inflow wind speed of the environment where the target wind turbine is located at the next unit time, and taking the inflow wind speed of the environment where the target wind turbine is located as input, the second wind speed prediction model outputs a second inflow wind speed of the environment where the target wind turbine is located at the next unit time; Determine a first weight of the first wind speed prediction model and a second weight of the second wind speed prediction model, and perform weighted summation of the first inflow wind speed and the second inflow wind speed based on the first weight and the second weight to obtain a target inflow wind speed of the environment where the target wind turbine is located at the next unit time; Among them, the first wind speed prediction model is obtained by training a first deep learning algorithm based on the historical inflow wind speed of the target wind turbine group, and the second wind speed prediction model is obtained by training a second deep learning algorithm based on the historical inflow wind speed of the target wind turbine group, and the first deep learning algorithm and the second deep learning algorithm are different deep learning algorithms.

[0006] Optionally, determining a first pitch angle corresponding to the wind resource prediction information includes: A pitch angle corresponding to the target inflow wind speed in a preset pitch angle correspondence table is determined as a first pitch angle, wherein the pitch angle correspondence table at least includes pitch angles corresponding to different historical inflow wind speeds.

[0007] Optionally, the operating parameters include: a pitch bearing temperature, a pitch motor temperature, a number of pitch changes within a plurality of specified unit moments before a current unit moment, a pitch change mileage within a plurality of specified unit moments before a current unit moment, a total number of pitch changes, and a total pitch change mileage; determining that the target wind turbine is in a pitch fatigue state according to the operating parameters of the target wind turbine includes: Determine the pitch bearing temperature, the pitch motor temperature, the number of pitch changes within multiple specified unit moments before the current unit moment, the pitch mileage within multiple specified unit moments before the current unit moment, the total number of pitch changes and the pitch fatigue coefficient corresponding to the total pitch mileage by means of a preset fatigue coefficient table, wherein the fatigue coefficient table includes at least different pitch bearing temperatures, pitch motor temperatures, the number of pitch changes within multiple specified unit moments before the current unit moment, the pitch mileage within multiple specified unit moments before the current unit moment, the total number of pitch changes and the total pitch fatigue coefficient corresponding to the total pitch mileage; Determine the parameter weight of each operating parameter, and based on the parameter weight of each operating parameter, perform weighted summation of the pitch bearing temperature, the pitch motor temperature, the number of pitch changes within multiple specified unit moments before the current unit moment, the pitch mileage within multiple specified unit moments before the current unit moment, the total number of pitch changes, and the pitch fatigue coefficient of the total pitch mileage to obtain the pitch fatigue of the target wind turbine at the current unit moment. If the pitch fatigue is greater than a preset pitch fatigue threshold, it is determined that the target wind turbine is in a pitch fatigue state.

[0008] Optionally, determining the second pitch angle of the target wind turbine generator set based on a comparison result between the wind resource prediction information and the wind resource information includes: Determine a wind speed difference between a target inflow wind speed of the environment where the target wind turbine generator set is located at a next unit time and an inflow wind speed of the environment where the target wind turbine generator set is located at a current unit time; If the wind speed difference is less than a preset wind speed difference threshold, and the output power of the target wind turbine set at the pitch angle of the current unit time and the target inflow wind speed of the next unit time meets the preset wind turbine set output power constraint, the pitch angle of the target wind turbine set at the current unit time is used as the second pitch angle; If the wind speed difference is greater than the wind speed difference threshold, or the output power of the target wind turbine at the pitch angle of the current unit moment and the target inflow wind speed at the next unit moment does not meet the output power constraint of the wind turbine, the optimal pitch angle that satisfies the objective function and the output power constraint of the wind turbine at the target inflow wind speed at the next unit moment is obtained by optimizing the pre-constructed objective function, and the optimal pitch angle is used as the second pitch angle.

[0009] Optionally, the wind turbine output power constraint condition includes: the output power of the target wind turbine is not less than a preset minimum output power of the wind turbine, and the output power of the target wind turbine is not greater than a preset maximum output power of the wind turbine; the method for constructing the objective function includes: Constructing a first relationship function representing a first pitch angle difference between the pitch angle to be optimized at the next unit moment and the pitch angle at the current unit moment of the target wind turbine generator set, and constructing a second relationship function representing a second pitch angle difference between the optimal pitch angle at the next unit moment and the pitch angle at the current unit moment of the target wind turbine generator set, obtaining the actual cost of the variable pitch bearing, and establishing a third relationship function based on the actual cost of the variable pitch bearing and the ratio of the first relationship function to the second relationship function; Constructing a fourth relationship function representing the output power of the target wind turbine generator set at the pitch angle to be optimized at the next unit time and a fifth relationship function representing the output power of the target wind turbine generator set at the optimal pitch angle at the next unit time, obtaining the on-grid electricity price at the next unit time, and establishing a sixth relationship function based on the on-grid electricity price and the difference between the fourth relationship function and the fifth relationship function; Based on the actual cost of the variable pitch bearing, the third relationship function and the sixth relationship function, the objective function is constructed with the goal of maximizing the total benefit.

[0010] Optionally, optimizing and solving a pre-constructed objective function to obtain an optimal pitch angle that satisfies the objective function and the output power constraint of the wind turbine generator set at a target inflow wind speed at the next unit time includes: S10, initializing a particle swarm, determining the number of particles in the particle swarm and the initial position of each particle, and mapping the pitch angle to be optimized of the target wind turbine at the next unit time to the position of each particle; S20, determining the fitness value of each particle based on the objective function, and determining the individual extreme value and the group extreme value of each particle; S30, updating the speed and position of each particle based on the individual extreme value and group extreme value of each particle; S40, determining the individual extreme value and the group extreme value of each particle after update based on the objective function, if the convergence condition is not met, returning to step S30, if the convergence condition is met, stopping the search, and outputting the current group extreme value as the optimal pitch angle.

[0011] In a second aspect of the present application, a wind turbine pitch control device is provided, which applies the above-mentioned wind turbine pitch control method, and the device comprises: A data acquisition module is configured to obtain current wind resource information of the environment in which the target wind turbine is located and current operating parameters of the target wind turbine; A wind resource prediction module is configured to take the wind resource information as input and output the wind resource prediction information of the environment where the target wind turbine is located at the next unit time through a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms with historical wind resource information of the target wind turbine; a pitch control module configured to, if it is determined according to the operating parameters of the target wind turbine generator set that the target wind turbine generator set is not in a pitch fatigue state, determine a first pitch angle corresponding to the wind resource prediction information, and control the target wind turbine generator set to perform a pitch operation at the first pitch angle at a next unit time; and If it is determined that the target wind turbine group is in a pitch fatigue state based on the operating parameters of the target wind turbine group, a second pitch angle of the target wind turbine group is determined based on a comparison result between the wind resource prediction information and the wind resource information, and the target wind turbine group is controlled to perform a pitch operation at the second pitch angle at a next unit time.

[0012] In a third aspect of the present application, a computer-readable storage medium is provided, which stores a computer program which, when executed by a processor, causes the processor to execute the wind turbine pitch control method as described above.

[0013] In a fourth aspect of the present application, a terminal device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned wind turbine pitch control method when executing the computer program.

[0014] The embodiments provided in this application have the following beneficial effects: The present application can optimize the control of the pitch motor by combining wind speed prediction with feedforward control, thereby reducing the time that the wind turbine blades are in fatigue conditions, ultimately extending the service life of the blades. At the same time, the present application can effectively increase the service life of the pitch bearing by judging the pitch fatigue state of the wind turbine and using different pitch angles for pitch control according to the different fatigue states of the wind turbine.

[0015] Other features and advantages of the embodiments or implementations of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings: Figure 1 The system structure diagram of the pitch motor feedforward control system according to the embodiment of the present application is schematically shown; Figure 2 The logical structure diagram of the pitch motor feedforward control system according to the embodiment of the present application is schematically shown; Figure 3 A method flow chart schematically shows a method for controlling a wind turbine pitch according to an embodiment of the present application; Figure 4A schematic block diagram of a wind turbine pitch control device according to an embodiment of the present application is schematically shown; Figure 5 A schematic diagram of the structure of a terminal device according to an embodiment of the present application is shown schematically.

[0017] Description of Reference Numerals 10-terminal device, 100-processor, 101-memory, 102-computer program. DETAILED DESCRIPTION

[0018] The specific implementation of the embodiment of the present application is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present application, and is not used to limit the embodiment of the present application.

[0019] It can be understood that the wind turbine pitch control method of the present application is applied to the pitch motor feedforward control system based on wind speed prediction constructed in the present application, such as Figure 1 As shown, the control system of the present application includes a power module, a data acquisition and input module, a control logic module, an execution device module, a data storage module and a communication device module. It can be understood that the data acquisition and input module, the control logic module and the execution device module can be different functional modules integrated in the same control chip. The functions of each module of the control system are as follows: The power module is used to supply power to the control system. The power module can provide the required power according to the specific needs of each module, thereby ensuring the stable operation of each part of the system and providing power guarantee for the entire system. The data acquisition and input module is used to collect wind resource data and operating parameters required by the control logic module, data storage and communication device module, such as wind speed, wind direction and blade angle. The collected data is transmitted to the control logic module, data storage module and communication device module in real time to support subsequent data processing and decision-making. The efficiency of this module directly affects the response speed and accuracy of the entire system; The control logic module undertakes the key data processing task. The control logic module receives information such as wind speed and wind direction from the data acquisition and input module, and also obtains data such as the speed, torque and power of the variable pitch motor from the data storage module. This module is responsible for reading, calculating and processing this data, and outputting the calculation results to the execution device module. This process requires not only efficient computing power, but also accurate logical judgment to ensure the optimal operation of the wind turbine under various conditions. The execution device module is used to receive the data analysis results of the control logic module, and combine the preset pitch control strategy to accurately control the pitch motor. In addition, the module will also collect data such as the speed, torque and power of the pitch motor in real time, and interact with the data storage module. This module can ensure that the pitch motor can respond quickly to control instructions and improve the overall performance and reliability of the wind turbine. The data storage module is used to store data from the data acquisition and input module, the control logic module and the execution device module. In order to manage information more efficiently, the module is logically divided into three parts: storing the acquisition results of the data acquisition and input module each time, the calculation results of the control logic module each time, and the acquisition results of the execution device module each time. In addition, the module is also equipped with a USB data interface, a network cable interface and a wireless communication interface, supporting Bluetooth and WIFI data transmission functions, so that when remote wired communication fails, the staff can export data on site to ensure timely acquisition and safe storage of information; The communication module has a common communication interface with the PLC of the main control system of each manufacturer to ensure seamless connection of information. Through this module, the main control system can remotely write or update the logic module of the feedforward control system. At the same time, designers can use the relevant data exported from the main control system to optimize the selection of the variable pitch motor of the unit; the communication module is used to transmit the instructions and data of the main control system to the control logic module, and feed back the collected data and calculation results in the data storage module to the main control system, thereby ensuring efficient data flow between the device and the main control system and promoting the collaborative work of the overall system.

[0020] like Figure 2 As shown, the logical function implementation of this application is as follows: 1. Data input: The data input part includes the data input by the control program, the data input by the wind speed prediction module, and the predicted data fed back by the actuator. The control program input part mainly transmits the relevant control data calculated by the PLC to the data logic processing module; the wind speed prediction module is used to input the collected environmental data (such as wind speed, wind direction, etc.) to the data logic processing module; the actuator input part transmits the operation data calculated by the future state prediction module to the data logic processing module.

[0021] 2. Data processing: The data processing module is used to perform preliminary calculations on the data input by the control program, the data input by the wind speed prediction module, and the predicted data fed back by the actuator, and convert them into the data required by the program controller. After data analysis, calculation, and logic execution, the program controller outputs the required control instructions to the actuator.

[0022] 3. Actuator: Receives control instructions from the program controller and the predicted future unit operation data after the previous control cycle, and processes the above two types of data; converts the processed data into control instructions and transmits them to the actuator to achieve control; collects the status data of the actuator after executing the instructions, and transmits these data to the future status prediction module. 4. Future state prediction: The main function of the future state prediction module is to receive the state data of the actuator and predict the future state of the unit in combination with the preset future state prediction program. At the same time, the data calculated by the future state prediction module will be input into the data processing module and the actuator to realize feedforward control.

[0023] It is understandable that the above modules, such as the wind speed prediction module, the data processing module, the actuator and the future state prediction module, can be functional modules in the control logic module, which is not limited here. Through the collaborative work of the above modules, the wind speed prediction feedforward control strategy of the present application provides a more efficient and accurate control solution for the variable pitch system, which helps to improve the overall performance and safety of the wind turbine.

[0024] Among them, Figure 3 As shown, the first aspect of the present application provides a wind turbine pitch control method, comprising: S100, obtaining current wind resource information of the environment in which the target wind turbine generator set is located and current operating parameters of the target wind turbine generator set; S200, taking wind resource information as input, outputting wind resource prediction information of the environment where the target wind turbine is located at the next unit time through a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms with historical wind resource information of the target wind turbine; S300, if it is determined according to the operating parameters of the target wind turbine generator set that the target wind turbine generator set is not in a pitch change fatigue state, determining a first pitch angle corresponding to the wind resource prediction information, and controlling the target wind turbine generator set to perform a pitch change operation at the first pitch angle at the next unit time; S400: If it is determined that the target wind turbine is in a pitch fatigue state according to the operating parameters of the target wind turbine, a second pitch angle of the target wind turbine is determined based on a comparison result between the wind resource prediction information and the wind resource information, and the target wind turbine is controlled to perform a pitch operation at the second pitch angle at the next unit time.

[0025] In this way, the present application can optimize the control of the pitch motor by combining wind speed prediction with feedforward control, thereby reducing the time that the wind turbine blades are in fatigue conditions, ultimately extending the service life of the blades. At the same time, the present application can effectively improve the service life of the pitch bearing by judging the pitch fatigue state of the wind turbine and using different pitch angles for pitch control according to the different fatigue states of the wind turbine.

[0026] In step S100, the wind resource information includes at least the inflow wind speed of the environment in which the target wind turbine is located; the operating parameters include: pitch bearing temperature, pitch motor temperature, number of pitch changes within multiple specified unit moments before the current unit moment, pitch mileage within multiple specified unit moments before the current unit moment, total number of pitch changes and total pitch mileage.

[0027] In step S200, the wind resource prediction model of the present application at least includes: a first wind speed prediction model and a second wind speed prediction model; taking wind resource information as input, outputting wind resource prediction information of the environment where the target wind turbine is located at the next unit time through a preset wind resource prediction model, including: taking the inflow wind speed of the environment where the target wind turbine is located as input, outputting the first inflow wind speed of the environment where the target wind turbine is located at the next unit time through the first wind speed prediction model, and taking the inflow wind speed of the environment where the target wind turbine is located as input, outputting the first inflow wind speed of the environment where the target wind turbine is located at the next unit time through the second wind speed prediction model. second inflow wind speed; determine a first weight of the first wind speed prediction model and a second weight of the second wind speed prediction model, and perform weighted summation of the first inflow wind speed and the second inflow wind speed based on the first weight and the second weight to obtain the target inflow wind speed of the environment in which the target wind turbine is located at the next unit time; wherein, the first wind speed prediction model is obtained by training a first deep learning algorithm with the historical inflow wind speed of the target wind turbine, and the second wind speed prediction model is obtained by training a second deep learning algorithm with the historical inflow wind speed of the target wind turbine, and the first deep learning algorithm and the second deep learning algorithm are different deep learning algorithms. For example, the first deep learning algorithm is a long short-term memory neural network, and the second deep learning algorithm is a convolutional neural network. The short-term memory neural network and the convolutional neural network are trained with the historical wind speed data of the target wind turbine, for example, the historical wind speed data of the past year. For example, the wind speed of the past N unit moments in the historical wind speed data is used to predict the wind speed of the N+1th unit moment. The network parameters of the long short-term memory neural network or the convolutional neural network are adjusted by the error between the collected historical measured wind speed and the prediction result until the convergence condition is reached, and the first wind speed prediction model and the second wind speed prediction model are obtained. In this way, by coupling the prediction results of different wind speed prediction models, the accuracy of wind speed prediction can be effectively improved.

[0028] In step S300, determining the first pitch angle corresponding to the wind resource prediction information includes: determining the pitch angle corresponding to the target inflow wind speed in a preset pitch angle correspondence table as the first pitch angle, wherein the pitch angle correspondence table at least includes pitch angles corresponding to different historical inflow wind speeds. It can be understood that the correspondence between wind speed and pitch angle can be pre-configured, wherein the pitch angle corresponding to different wind speeds is the optimal pitch angle under the wind speed.

[0029] In step S300, determining that the target wind turbine is in a pitch fatigue state according to the operating parameters of the target wind turbine includes: S310. Determine the pitch bearing temperature, pitch motor temperature, number of pitch changes within multiple specified unit moments before the current unit moment, pitch mileage within multiple specified unit moments before the current unit moment, total number of pitch changes and total pitch mileage corresponding to the pitch fatigue coefficient through a preset fatigue coefficient table, wherein the fatigue coefficient table includes at least different pitch bearing temperatures, pitch motor temperatures, number of pitch changes within multiple specified unit moments before the current unit moment, pitch mileage within multiple specified unit moments before the current unit moment, total number of pitch changes and total pitch mileage corresponding to the pitch fatigue coefficient; it can be understood that the rated life of the bearing is the number of revolutions or hours that the bearing experiences before pitting occurs under a certain load, and the number of bearing revolutions has a direct corresponding relationship with the total angle of rotation of the bearing. At the same time, during the pitch change process, components such as the pitch bearing and the pitch motor may frequently and repeatedly move. Long-term operation in this way may cause fatigue damage to components such as the pitch bearing and the pitch motor. Therefore, the present application pre-configures the correspondence between different operating parameters and non-fatigue coefficients. For example, when the pitch bearing temperature is in different temperature ranges, it corresponds to different fatigue coefficients. The higher the temperature, the higher the corresponding fatigue coefficient; the more pitch changes in the multiple specified unit moments before the current unit moment, the more frequent the pitch change action of the wind turbine in the recent period of time. Therefore, the more pitch changes, the higher the corresponding fatigue coefficient. Similarly, the larger the values ​​of parameters such as the pitch motor temperature, the pitch mileage in the multiple specified unit moments before the current unit moment, the total number of pitch changes and the total pitch mileage, the higher the corresponding fatigue coefficient.

[0030] S320. Determine the parameter weights of each operating parameter, and perform weighted summation of the pitch bearing temperature, the pitch motor temperature, the number of pitch changes within multiple specified unit moments before the current unit moment, the pitch mileage within multiple specified unit moments before the current unit moment, the total number of pitch changes, and the pitch fatigue coefficient of the total pitch mileage based on the parameter weights of each operating parameter to obtain the pitch fatigue degree of the target wind turbine at the current unit moment. If the pitch fatigue degree is greater than a preset pitch fatigue degree threshold, it is determined that the target wind turbine is in a pitch fatigue state. For example, the pitch mileage, total number of pitch changes and total pitch mileage within multiple specified unit moments before the current unit moment are used to represent the pitch frequency of the wind turbine in the recent period of time. When the wind turbine is in a frequent pitch state for a long time, the wind turbine pitch-related components will be more prone to fatigue damage. Therefore, the pitch mileage, total number of pitch changes and total pitch mileage within multiple specified unit moments before the current unit moment can be configured with a higher weight. The pitch bearing temperature and pitch motor temperature are also real-time state responses to the pitch process, which have a direct impact on pitch fatigue. Therefore, a higher weight can also be configured. The total number of pitch changes and the total pitch mileage are representations of the cumulative fatigue damage of the pitch, which have little impact on the real-time fatigue damage of the pitch process, so a lower weight can be configured. The pitch fatigue threshold can be pre-configured, and the pitch fatigue threshold can be determined by simulation or experiment, etc., which is not limited here.

[0031] In step S400, determining the second pitch angle of the target wind turbine generator system based on the comparison result between the wind resource prediction information and the wind resource information includes: S410, determining the wind speed difference between the target inflow wind speed of the environment where the target wind turbine is located at the next unit time and the inflow wind speed of the environment where the target wind turbine is located at the current unit time; wherein the inflow wind speed at the current unit time may be the actual wind speed collected by an anemometer.

[0032] S420. If the wind speed difference is less than the preset wind speed difference threshold, and the pitch angle of the target wind turbine at the current unit moment and the output power of the target inflow wind speed at the next unit moment meet the preset wind turbine output power constraint, the pitch angle of the target wind turbine at the current unit moment is used as the second pitch angle; wherein, the wind turbine output power constraint includes: the output power of the target wind turbine is not less than the preset minimum output power of the wind turbine, and the output power of the target wind turbine is not greater than the preset maximum output power of the wind turbine, which can be expressed as Pmin≤Pi≤Pmax, wherein Pmin represents the minimum output power of the wind turbine, kw, Pmax represents the maximum output power of the wind turbine, kw, and Pi represents the output power of the wind turbine at the i-th unit moment. Among them, if the wind speed difference is less than the preset wind speed difference threshold, it means that the wind speed change is small. At this time, the output power of the target wind turbine at the next unit time is calculated based on the pitch angle of the target wind turbine at the current unit time and the predicted target inflow wind speed at the next unit time. If the constraint conditions can be met, the current pitch angle is kept unchanged, thereby avoiding too frequent pitch changes and extending the service life of pitch-related components. Among them, the power calculation formula of the wind turbine is: , where CP is the wind energy utilization coefficient, ρ is the air density, kg / m3, A is the wind rotor swept area, m2, and v is the wind speed, m / s. The wind energy utilization coefficient can be expressed as , where B is the pitch angle, is the tip speed ratio, where , is the impeller speed, rad / s, and R is the impeller radius, m. It can be understood that parameters such as the wind wheel swept area, impeller speed, and impeller radius can be obtained in advance or monitored in real time.

[0033] S430, if the wind speed difference is greater than the wind speed difference threshold, or the output power of the target wind turbine at the pitch angle of the current unit time and the target inflow wind speed of the next unit time does not meet the output power constraint of the wind turbine, the pre-constructed objective function is optimized to obtain the optimal pitch angle that meets the objective function and the output power constraint of the wind turbine at the target inflow wind speed of the next unit time, and the optimal pitch angle is used as the second pitch angle. If the wind speed difference is greater than the preset wind speed difference threshold, it means that the wind speed fluctuates greatly. If the pitch angle is kept unchanged at this time, it will have a greater impact on the power generation loss and may cause damage to the wind turbine. Therefore, in this case, in order to minimize the power generation loss and damage to the wind turbine, and reduce the fatigue damage of the variable pitch bearing, this application is based on optimizing the pre-constructed objective function and constraints to obtain the optimal pitch angle of the target wind turbine at the next unit time.

[0034] In step S430, the method for constructing the objective function includes: S431, constructing a first relational function representing the first pitch angle difference between the pitch angle to be optimized at the next unit time and the pitch angle at the current unit time of the target wind turbine generator set: B i+1 -B i , where B i+1 represents the pitch angle to be optimized at the i+1th unit time, B i represents the pitch angle of the i-th unit time; and constructs a second relationship function representing the difference between the optimal pitch angle of the target wind turbine at the next unit time and the second pitch angle of the pitch angle at the current unit time: B' i+1 -B i , where B' i+1 represents the optimal pitch angle of the target wind turbine at the target inflow wind speed at the next unit time, and the optimal pitch angle can be obtained through the pitch angle correspondence table; the actual cost of the variable pitch bearing is obtained, and the third relationship function is established based on the actual cost of the variable pitch bearing and the ratio of the first relationship function to the second relationship function: C bear (Bi+1-Bi) / (B' i+1 -B i ), where C bear represents the actual cost of the pitch bearing, which can be determined in advance.

[0035] S432, constructing a fourth relationship function representing the output power of the target wind turbine generator set at the pitch angle to be optimized at the next unit time and a fifth relationship function representing the output power of the target wind turbine generator set at the optimal pitch angle at the next unit time, obtaining the on-grid electricity price at the next unit time, and establishing a sixth relationship function based on the on-grid electricity price and the difference between the fourth relationship function and the fifth relationship function; wherein the fourth relationship function and the fifth relationship function can be determined based on the power calculation formula of the above-mentioned wind turbine generator set, and the fourth relationship function is expressed as P i , the fifth relationship function is expressed as P' i , then the sixth relationship function can be expressed as c(P i -P' i ), where c represents the on-grid electricity price.

[0036] S433, based on the actual cost of the variable pitch bearing, the third relationship function and the sixth relationship function, an objective function is constructed with the goal of maximizing the total benefit, and the objective function can be expressed as maxF=C bear -C bear (Bi+1-Bi) / (B' i+1 -B i )+c(P i -P' i ).

[0037] In step S400, the pre-constructed objective function is optimized and solved to obtain the optimal pitch angle that satisfies the objective function and the wind turbine output power constraint conditions at the target inflow wind speed at the next unit time, including optimizing and solving the objective function by a particle swarm algorithm, the steps comprising: S10, initializing a particle swarm, determining the number of particles in the particle swarm and the initial position of each particle, and mapping the pitch angle to be optimized of the target wind turbine generator set at the next unit time to the position of each particle.

[0038] S20, determining the fitness value of each particle based on the objective function, and determining the individual extreme value and the group extreme value of each particle, and taking the objective function value as the fitness value of each particle.

[0039] S30, updating the speed and position of each particle based on the individual extreme value and group extreme value of each particle; wherein the speed update formula is:

[0040] The position update formula is:

[0041] Where, j represents the dimension of the particle, i represents the i-th particle, t represents the current number of iterations, c1 and c2 are acceleration constants, usually in the interval (0, 2), r1 and r2 are two independent random numbers in the range [0, 1], and p best represents individual extreme value, g best Represents the extreme value of the group.

[0042] S40. Determine the individual extreme value and group extreme value of each particle after update based on the objective function. For each particle, compare its current fitness value with its historical optimal fitness value. If it is better, it will be used as the new individual extreme value of the historical optimal value. At the same time, for each particle, compare its current fitness value with the fitness value of the optimal position experienced by the group. If it is better, the current fitness value will be used as the global optimal value, that is, the group extreme value. If the convergence condition is not met, return to step S30. If the convergence condition is met, stop searching and output the current group extreme value as the optimal pitch angle, where the convergence condition may be reaching the maximum number of iterations.

[0043] like Figure 4 As shown, in a second aspect of the present application, a wind turbine pitch control device is provided, and the wind turbine pitch control method mentioned above is applied, and the device includes: A data acquisition module is configured to obtain current wind resource information of the environment in which the target wind turbine is located and current operating parameters of the target wind turbine; The wind resource prediction module is configured to take wind resource information as input and output wind resource prediction information of the environment where the target wind turbine is located at the next unit time through a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms with historical wind resource information of the target wind turbine; The pitch control module is configured to, if it is determined based on the operating parameters of the target wind turbine group that the target wind turbine group is not in a pitch fatigue state, determine the first pitch angle corresponding to the wind resource prediction information, and control the target wind turbine group to perform a pitch operation at the first pitch angle at a next unit time; and if it is determined based on the operating parameters of the target wind turbine group that the target wind turbine group is in a pitch fatigue state, determine the second pitch angle of the target wind turbine group based on a comparison result between the wind resource prediction information and the wind resource information, and control the target wind turbine group to perform a pitch operation at the second pitch angle at a next unit time.

[0044] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0045] In a third aspect of the present application, a computer-readable storage medium is provided, which stores a computer program which, when executed by a processor, causes the processor to execute the wind turbine pitch control method as described above.

[0046] In a fourth aspect of the present application, a terminal device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned wind turbine pitch control method when executing the computer program.

[0047] like Figure 5 FIG. 1 is a schematic diagram of a terminal device provided in an embodiment of the present application. Figure 5As shown, the terminal device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps in the above method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of each module / unit in the above device embodiments are implemented.

[0048] Exemplarily, the computer program 102 may be divided into one or more modules / units, one or more modules / units are stored in the memory 101, and are executed by the processor 100 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 102 in the terminal device 10.

[0049] The terminal device 10 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device 10 may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art will appreciate that Figure 5 It is only an example of the terminal device 10 and does not constitute a limitation of the terminal device 10. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0050] The processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0051] The memory 101 may be an internal storage unit of the terminal device 10, such as a hard disk or memory of the terminal device 10. The memory 101 may also be an external storage device of the terminal device 10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the terminal device 10. Further, the memory 101 may also include both an internal storage unit of the terminal device 10 and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the terminal device 10. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0052] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0053] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0054] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A wind turbine pitch control method, characterized in that: include: Acquire current wind resource information of the environment in which the target wind turbine is located and current operating parameters of the target wind turbine; Taking the wind resource information as input, outputting the wind resource prediction information of the environment where the target wind turbine is located at the next unit time through a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms with historical wind resource information of the target wind turbine; If it is determined according to the operating parameters of the target wind turbine generator set that the target wind turbine generator set is not in a pitch change fatigue state, determining a first pitch angle corresponding to the wind resource prediction information, and controlling the target wind turbine generator set to perform a pitch change operation at the first pitch angle at a next unit time; If it is determined that the target wind turbine group is in a pitch fatigue state based on the operating parameters of the target wind turbine group, a second pitch angle of the target wind turbine group is determined based on a comparison result between the wind resource prediction information and the wind resource information, and the target wind turbine group is controlled to perform a pitch operation at the second pitch angle at a next unit time.

2. The wind turbine pitch control method according to claim 1, characterized in that: The wind resource information at least includes the inflow wind speed of the environment where the target wind turbine is located; the wind resource prediction model at least includes: A first wind speed prediction model and a second wind speed prediction model; Taking the wind resource information as input, the preset wind resource prediction model outputs the wind resource prediction information of the environment where the target wind turbine is located at the next unit time, including: Taking the inflow wind speed of the environment where the target wind turbine is located as input, the first wind speed prediction model outputs a first inflow wind speed of the environment where the target wind turbine is located at the next unit time, and taking the inflow wind speed of the environment where the target wind turbine is located as input, the second wind speed prediction model outputs a second inflow wind speed of the environment where the target wind turbine is located at the next unit time; Determine a first weight of the first wind speed prediction model and a second weight of the second wind speed prediction model, and perform weighted summation of the first inflow wind speed and the second inflow wind speed based on the first weight and the second weight to obtain a target inflow wind speed of the environment where the target wind turbine is located at the next unit time; Among them, the first wind speed prediction model is obtained by training a first deep learning algorithm based on the historical inflow wind speed of the target wind turbine group, and the second wind speed prediction model is obtained by training a second deep learning algorithm based on the historical inflow wind speed of the target wind turbine group, and the first deep learning algorithm and the second deep learning algorithm are different deep learning algorithms.

3. The wind turbine pitch control method according to claim 2, characterized in that: Determining a first pitch angle corresponding to the wind resource prediction information includes: A pitch angle corresponding to the target inflow wind speed in a preset pitch angle correspondence table is determined as a first pitch angle, wherein the pitch angle correspondence table at least includes pitch angles corresponding to different historical inflow wind speeds.

4. The wind turbine pitch control method according to claim 1, characterized in that: The operating parameters include: pitch bearing temperature, pitch motor temperature, pitch times within multiple specified unit times before the current unit time, pitch mileage within multiple specified unit times before the current unit time, total pitch times and total pitch mileage; determining that the target wind turbine is in a pitch fatigue state based on the operating parameters of the target wind turbine includes: Determine the pitch bearing temperature, the pitch motor temperature, the number of pitch changes within multiple specified unit moments before the current unit moment, the pitch mileage within multiple specified unit moments before the current unit moment, the total number of pitch changes and the pitch fatigue coefficient corresponding to the total pitch mileage by means of a preset fatigue coefficient table, wherein the fatigue coefficient table includes at least different pitch bearing temperatures, pitch motor temperatures, the number of pitch changes within multiple specified unit moments before the current unit moment, the pitch mileage within multiple specified unit moments before the current unit moment, the total number of pitch changes and the total pitch fatigue coefficient corresponding to the total pitch mileage; Determine the parameter weight of each operating parameter, and based on the parameter weight of each operating parameter, perform weighted summation of the pitch bearing temperature, the pitch motor temperature, the number of pitch changes within multiple specified unit moments before the current unit moment, the pitch mileage within multiple specified unit moments before the current unit moment, the total number of pitch changes, and the pitch fatigue coefficient of the total pitch mileage to obtain the pitch fatigue of the target wind turbine at the current unit moment. If the pitch fatigue is greater than a preset pitch fatigue threshold, it is determined that the target wind turbine is in a pitch fatigue state.

5. The wind turbine pitch control method according to claim 3, characterized in that: Determining a second pitch angle of the target wind turbine generator set based on a comparison result between the wind resource prediction information and the wind resource information includes: Determine a wind speed difference between a target inflow wind speed of the environment where the target wind turbine generator set is located at a next unit time and an inflow wind speed of the environment where the target wind turbine generator set is located at a current unit time; If the wind speed difference is less than a preset wind speed difference threshold, and the output power of the target wind turbine set at the pitch angle of the current unit time and the target inflow wind speed of the next unit time meets the preset wind turbine set output power constraint, the pitch angle of the target wind turbine set at the current unit time is used as the second pitch angle; If the wind speed difference is greater than the wind speed difference threshold, or the output power of the target wind turbine at the pitch angle of the current unit moment and the target inflow wind speed at the next unit moment does not meet the output power constraint of the wind turbine, the optimal pitch angle that satisfies the objective function and the output power constraint of the wind turbine at the target inflow wind speed at the next unit moment is obtained by optimizing the pre-constructed objective function, and the optimal pitch angle is used as the second pitch angle.

6. The wind turbine pitch control method according to claim 5, characterized in that: The wind turbine output power constraint condition includes: the output power of the target wind turbine is not less than the preset minimum output power of the wind turbine, and the output power of the target wind turbine is not greater than the preset maximum output power of the wind turbine; the method for constructing the objective function includes: Constructing a first relationship function representing a first pitch angle difference between the pitch angle to be optimized at the next unit moment and the pitch angle at the current unit moment of the target wind turbine generator set, and constructing a second relationship function representing a second pitch angle difference between the optimal pitch angle at the next unit moment and the pitch angle at the current unit moment of the target wind turbine generator set, obtaining the actual cost of the variable pitch bearing, and establishing a third relationship function based on the actual cost of the variable pitch bearing and the ratio of the first relationship function to the second relationship function; Constructing a fourth relationship function representing the output power of the target wind turbine generator set at the pitch angle to be optimized at the next unit time and a fifth relationship function representing the output power of the target wind turbine generator set at the optimal pitch angle at the next unit time, obtaining the on-grid electricity price at the next unit time, and establishing a sixth relationship function based on the on-grid electricity price and the difference between the fourth relationship function and the fifth relationship function; Based on the actual cost of the variable pitch bearing, the third relationship function and the sixth relationship function, the objective function is constructed with the goal of maximizing the total benefit.

7. The wind turbine pitch control method according to claim 6, characterized in that: The pre-constructed objective function is optimized and solved to obtain the optimal pitch angle that satisfies the objective function and the output power constraint of the wind turbine generator set at the target inflow wind speed at the next unit time, including: S10, initializing a particle swarm, determining the number of particles in the particle swarm and the initial position of each particle, and mapping the pitch angle to be optimized of the target wind turbine at the next unit time to the position of each particle; S20, determining the fitness value of each particle based on the objective function, and determining the individual extreme value and the group extreme value of each particle; S30, updating the speed and position of each particle based on the individual extreme value and group extreme value of each particle; S40, determining the individual extreme value and the group extreme value of each particle after update based on the objective function, if the convergence condition is not met, returning to step S30, if the convergence condition is met, stopping the search, and outputting the current group extreme value as the optimal pitch angle.

8. A wind turbine pitch control device, using the wind turbine pitch control method according to any one of claims 1 to 7, characterized in that: The device comprises: A data acquisition module is configured to obtain current wind resource information of the environment in which the target wind turbine is located and current operating parameters of the target wind turbine; A wind resource prediction module is configured to take the wind resource information as input and output the wind resource prediction information of the environment where the target wind turbine is located at the next unit time through a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms with historical wind resource information of the target wind turbine; The pitch control module is configured to, if it is determined based on the operating parameters of the target wind turbine group that the target wind turbine group is not in a pitch fatigue state, determine a first pitch angle corresponding to the wind resource prediction information, and control the target wind turbine group to perform a pitch operation at the first pitch angle at a next unit time; and if it is determined based on the operating parameters of the target wind turbine group that the target wind turbine group is in a pitch fatigue state, determine a second pitch angle of the target wind turbine group based on a comparison result of the wind resource prediction information and the wind resource information, and control the target wind turbine group to perform a pitch operation at the second pitch angle at a next unit time.

9. A computer-readable storage medium, characterized in that: A computer program is stored which, when executed by a processor, enables the processor to execute the wind turbine pitch control method according to any one of claims 1 to 7.

10. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the wind turbine pitch control method according to any one of claims 1 to 7 is implemented.

Images