Wind turbine variable pitch control method and device, storage medium and terminal equipment

Abstract

The application provides a wind turbine variable pitch control method and device, a storage medium and a terminal device, relates to the technical field of wind turbine variable pitch control, and the method comprises the following steps: obtaining current wind resource information of an environment where a target wind turbine is located and current operating parameters of the target wind turbine; taking the wind resource information as input, outputting wind resource prediction information of the environment where the target wind turbine is located at a next unit time through a preset wind resource prediction model; determining a variable pitch fatigue state of the target wind turbine according to the operating parameters of the target wind turbine, and controlling the target wind turbine to perform a variable pitch operation at a first pitch angle at the next unit time or controlling the target wind turbine to perform a variable pitch operation at a second pitch angle at the next unit time based on the variable pitch fatigue state of the target wind turbine. The application can effectively improve the service life of the blade and the variable pitch bearing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind turbine variable pitch control, in particular to a wind turbine variable pitch control method, a wind turbine variable pitch control device, a computer readable storage medium and a terminal device. BACKGROUND

[0002] Currently, the control logic of the variable pitch motor in the wind power industry 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 pitch angle. In high wind speed conditions, the pitch angle is adjusted to be smaller to avoid overloading of the wind turbine. In extreme wind speed conditions (such as gale or sudden wind), the variable pitch system adjusts the pitch to the "shutdown" position to reduce the stress on the wind turbine and ensure safe operation of the equipment. In addition, the traditional control logic also optimizes the pitch angle in real time according to the changes in wind speed and direction to maximize energy capture efficiency and reduce air resistance. However, in the traditional variable pitch control logic, if the variable pitch motor is operated at the maximum output point for a long time or performs variable pitch action frequently, it may cause the blade or variable pitch bearing to be in a fatigue working condition for a long time, thereby affecting its service life. SUMMARY

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

[0004] To achieve the above purpose, the first aspect of the present application provides a wind turbine variable pitch control method, comprising:

[0005] obtaining current wind resource information of an environment where a target wind turbine is located and current operating parameters of the target wind turbine;

[0006] inputting the wind resource information, and outputting wind resource prediction information of the environment where the target wind turbine is located at a next unit time through a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms based on historical wind resource information of the target wind turbine;

[0007] if it is determined that the target wind turbine is not in a variable pitch fatigue state according to the operating parameters of the target wind turbine, determining a first pitch angle corresponding to the wind resource prediction information, and controlling the target wind turbine to perform a variable pitch operation at the first pitch angle at the next unit time;

[0008] If it is determined according to the operating parameter of the target wind turbine that the target wind turbine is in a variable pitch fatigue state, a second pitch angle of the target wind turbine is determined based on the comparison result of the wind resource prediction information and the wind resource information, and the target wind turbine is controlled to perform a variable pitch operation at the second pitch angle at the next unit time.

[0009] Optionally, the wind resource information at least includes an inflow wind speed of an environment where the target wind turbine is located; and the wind resource prediction model at least includes:

[0010] a first wind speed prediction model and a second wind speed prediction model;

[0011] The wind resource prediction information of the environment where the target wind turbine is located at the next unit time is output by the preset wind resource prediction model with the wind resource information as input, including:

[0012] The first inflow wind speed of the environment where the target wind turbine is located at the next unit time is output by the first wind speed prediction model with the inflow wind speed of the environment where the target wind turbine is located as input, and the second inflow wind speed of the environment where the target wind turbine is located at the next unit time is output by the second wind speed prediction model with the inflow wind speed of the environment where the target wind turbine is located as input;

[0013] A first weight of the first wind speed prediction model and a second weight of the second wind speed prediction model are determined, and the first inflow wind speed and the second inflow wind speed are weighted and summed 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;

[0014] The first wind speed prediction model is obtained by training a first deep learning algorithm with historical inflow wind speeds 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 speeds of the target wind turbine, and the first deep learning algorithm and the second deep learning algorithm are different deep learning algorithms.

[0015] Optionally, determining the first pitch angle corresponding to the wind resource prediction information includes:

[0016] The pitch angle corresponding to the target inflow wind speed in a preset pitch angle corresponding relationship table is determined as the first pitch angle, and the pitch angle corresponding relationship table at least includes pitch angles corresponding to different historical inflow wind speeds.

[0017] Optionally, the operation parameters include: pitch bearing temperature, pitch motor temperature, pitch frequency in a plurality of specified unit instants before the current unit instant, pitch mileage in the plurality of specified unit instants before the current unit instant, total pitch frequency and total pitch mileage; determining that the target wind turbine is in a pitch fatigue state according to the operation parameters of the target wind turbine includes:

[0018] determining, by a preset fatigue coefficient table, pitch fatigue coefficients corresponding to the pitch bearing temperature, the pitch motor temperature, the pitch frequency in the plurality of specified unit instants before the current unit instant, the pitch mileage in the plurality of specified unit instants before the current unit instant, the total pitch frequency and the total pitch mileage, wherein the fatigue coefficient table at least includes different pitch fatigue coefficients corresponding to different pitch bearing temperatures, different pitch motor temperatures, different pitch frequencies in the plurality of specified unit instants before the current unit instant, different pitch mileages in the plurality of specified unit instants before the current unit instant, different total pitch frequencies and different total pitch mileages;

[0019] determining parameter weights of the operation parameters, performing weighted summation on the pitch fatigue coefficients of the pitch bearing temperature, the pitch motor temperature, the pitch frequency in the plurality of specified unit instants before the current unit instant, the pitch mileage in the plurality of specified unit instants before the current unit instant, the total pitch frequency and the total pitch mileage based on the parameter weights of the operation parameters, to obtain a pitch fatigue degree of the target wind turbine at the current unit instant, and determining that the target wind turbine is in a pitch fatigue state if the pitch fatigue degree is greater than a preset pitch fatigue degree threshold.

[0020] Optionally, determining the second pitch angle of the target wind turbine based on the comparison result of the wind resource prediction information and the wind resource information includes:

[0021] determining a wind speed difference between a target inflow wind speed of an environment in which the target wind turbine is located at a next unit instant and an inflow wind speed of the environment in which the target wind turbine is located at the current unit instant;

[0022] if the wind speed difference is less than a preset wind speed difference threshold, and an output power of the target wind turbine at the pitch angle of the target wind turbine at the current unit instant and the target inflow wind speed at the next unit instant satisfies a preset wind turbine output power constraint condition, taking the pitch angle of the target wind turbine at the current unit instant as the second pitch angle;

[0023] If the wind speed difference value is greater than the wind speed difference threshold value, or the output power of the target wind turbine at the current unit time and the target inflow wind speed at the next unit time does not satisfy the wind turbine output power constraint condition, the pre-constructed target function is optimized and solved to obtain the optimal pitch angle of the target wind turbine at the target inflow wind speed at the next unit time, which satisfies the target function and the wind turbine output power constraint condition, and the optimal pitch angle is taken as the second pitch angle.

[0024] Optionally, the wind turbine output power constraint condition comprises: the output power of the target wind turbine is not less than a preset minimum wind turbine output power, and the output power of the target wind turbine is not greater than a preset maximum wind turbine output power; and the construction method of the target function comprises:

[0025] a first relationship function representing a first pitch angle difference value between the to-be-optimized pitch angle of the target wind turbine at the next unit time and the pitch angle at the current unit time is constructed, a second relationship function representing a second pitch angle difference value between the optimal pitch angle of the target wind turbine at the next unit time and the pitch angle at the current unit time is constructed, the actual cost of the variable pitch bearing is obtained, a third relationship function is established based on the ratio of the actual cost of the variable pitch bearing to the first relationship function and the second relationship function;

[0026] a fourth relationship function representing the output power of the target wind turbine at the to-be-optimized pitch angle at the next unit time and a fifth relationship function representing the output power of the target wind turbine at the optimal pitch angle at the next unit time are constructed, the on-grid electricity price at the next unit time is obtained, and a sixth relationship function is established based on the difference between the on-grid electricity price and the difference between the fourth relationship function and the fifth relationship function;

[0027] The target function is constructed based on the actual cost of the variable pitch bearing, the third relationship function and the sixth relationship function, with the maximum total revenue as the target.

[0028] Optionally, the pre-constructed target function is optimized and solved to obtain the optimal pitch angle of the target wind turbine at the target inflow wind speed at the next unit time, which satisfies the target function and the wind turbine output power constraint condition, comprising:

[0029] S10, initializing a particle swarm, determining the number of particles of the particle swarm and the initial position of each particle, and mapping the to-be-optimized pitch angle of the target wind turbine at the next unit time to the position of each particle;

[0030] S20, determining the fitness value of each particle based on the target function, and determining the individual extreme value and the group extreme value of each particle;

[0031] S30, updating the speed and position of each particle based on the individual extreme value and group extreme value of each particle;

[0032] S40. Determine 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, return to step S30. If the convergence condition is met, stop searching and output the current group extreme value as the optimal pitch angle.

[0033] 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 includes:

[0034] 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;

[0035] a wind resource prediction module, configured to take the wind resource information as input and output wind resource prediction information for the environment of the target wind turbine at the next unit time via a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms based on historical wind resource information of the target wind turbine;

[0036] a pitch control module configured to, if it is determined based on 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

[0037] If it is determined based on the operating parameters of the target wind turbine generator set that the target wind turbine generator set is in a pitch fatigue state, a second pitch angle of the target wind turbine generator set is determined based on a comparison result between the wind resource prediction information and the wind resource information, and the target wind turbine generator set is controlled to perform a pitch operation at the second pitch angle at a next unit time.

[0038] In a third aspect of the present application, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, causes the processor to execute the wind turbine pitch control method as described above.

[0039] 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.

[0040] The embodiments provided in this application have the following beneficial effects:

[0041] The application can optimize the control of the variable pitch motor by combining wind speed prediction with feedforward control, thereby reducing the time of the wind turbine blade in a fatigue working condition, ultimately prolonging the service life of the blade. Meanwhile, the application can effectively improve the service life of the variable pitch bearing by judging the variable pitch fatigue state of the wind turbine, and adopting different pitch angles for variable pitch control according to different fatigue states of the wind turbine.

[0042] Other features and advantages of the embodiments or implementations of the application will be described in detail in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0043] The accompanying drawings are included to provide a further understanding of the embodiments of the application, and constitute a part of the specification, and are used together with the following detailed description to explain the embodiments of the application, but do not constitute a limitation of the embodiments of the application. In the drawings:

[0044] Figure 1 The system structure schematic diagram of the variable pitch motor feedforward control system of the embodiments of the application is schematically shown;

[0045] Figure 2 The logic structure schematic diagram of the variable pitch motor feedforward control system of the embodiments of the application is schematically shown;

[0046] Figure 3 The method flowchart of the wind turbine variable pitch control method of the embodiments of the application is schematically shown;

[0047] Figure 4 The schematic block diagram of the wind turbine variable pitch control device of the embodiments of the application is schematically shown;

[0048] Figure 5 The schematic block diagram of the terminal device structure of the embodiments of the application is schematically shown.

[0049] Explanation of reference signs

[0050] 10-terminal device, 100-processor, 101-memory, 102-computer program. DETAILED DESCRIPTION

[0051] The specific embodiments of the embodiments of the application are described in detail below in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the embodiments of the application, and are not used to limit the embodiments of the application.

[0052] It can be understood that the wind turbine variable pitch control method of the application is applied to the variable pitch motor feedforward control system based on wind speed prediction constructed by the application, such as Figure 1As 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 the modules of the control system are as follows:

[0053] The power module is used to power 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 support for the entire system.

[0054] The data acquisition and input module is used to acquire wind resource data and operating parameters required by the control logic module, the data storage module and the communication device module, such as wind speed, wind direction and blade angle. The acquired data is transmitted to the control logic module, the data storage module and the communication device module in real time to support subsequent data processing and decision-making. The efficiency of this module directly affects the reaction speed and accuracy of the entire system.

[0055] 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 these data and outputs the calculation results to the execution device module. This process not only requires efficient computing power, but also requires accurate logical judgment to ensure the optimal operating state of the wind turbine under various conditions.

[0056] The execution device module is used to receive the data analysis results of the control logic module and accurately control the variable pitch motor in combination with the preset variable pitch control strategy. In addition, this module also acquires data such as the speed, torque and power of the variable pitch motor in real time and interacts with the data storage module. This module can ensure that the variable pitch motor can quickly respond to control instructions, thereby improving the overall performance and reliability of the wind turbine.

[0057] The data storage module is used to save data from the data acquisition and input module, the control logic module and the execution device module. In order to more efficiently manage information, this 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, this module is also equipped with a USB data interface, a network interface and a wireless communication interface, supporting Bluetooth and WIFI data transmission functions. Therefore, when remote wired communication fails, the staff can export data on site to ensure timely acquisition and safe storage of information.

[0058] The communication module has a communication interface common to PLCs of main control systems of various manufacturers, to ensure seamless connection of information. Through the module, the main control system can remotely write or update the logic module of the feedforward control system. Meanwhile, designers can use relevant data derived from the main control system to optimize the selection of the 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, so as to ensure efficient data flow between the device and the main control system, and promote the collaborative work of the overall system.

[0059] As shown in Figure 2 The logic function implementation manner of the present application is as follows:

[0060] 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 is mainly used to transmit 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 operating data calculated by the future state prediction module to the data logic processing module.

[0061] 2. Data processing: The data processing module is used to preliminarily calculate 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, etc., the program controller outputs the required control instructions to the actuator.

[0062] 3. Actuator: receiving the control instructions of the program controller, and the operating data of the unit at the future time predicted after the completion of the last control cycle, and processing the above two kinds of data; converting the processed data into control instructions, and transmitting them to the execution device to realize control; collecting the state data of the execution device after receiving the execution instructions, and transmitting these data to the future state prediction module.

[0063] 4. Future state prediction: The main function of the future state prediction module is to receive the state data of the execution device, and predict the future state of the unit in combination with the preset future state prediction program. Meanwhile, the data calculated by the future state prediction module will be input to the data processing module and the actuator to realize feedforward control.

[0064] It can be understood 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 cooperative work of the above modules, the wind speed prediction feedforward control strategy of the application provides a more efficient and accurate control scheme for the variable pitch system, which helps to improve the overall performance and safety of the wind turbine.

[0065] As shown in the above formula, the first aspect of the application provides a wind turbine variable pitch control method, comprising: Figure 3

[0066] S100, obtaining current wind resource information of an environment where a target wind turbine is located and current operating parameters of the target wind turbine;

[0067] S200, taking the wind resource information as input, outputting wind resource prediction information of the environment where the target wind turbine is located at a next unit time through a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms based on historical wind resource information of the target wind turbine;

[0068] S300, if it is determined that the target wind turbine is not in a variable pitch fatigue state according to the operating parameters of the target wind turbine, determining a first pitch angle corresponding to the wind resource prediction information, and controlling the target wind turbine to perform a variable pitch operation at the first pitch angle at the next unit time;

[0069] S400, if it is determined that the target wind turbine is in a variable pitch fatigue state according to the operating parameters of the target wind turbine, determining a second pitch angle of the target wind turbine based on a comparison result of the wind resource prediction information and the wind resource information, and controlling the target wind turbine to perform a variable pitch operation at the second pitch angle at the next unit time.

[0070] In this way, the application can optimize the control of the variable pitch motor by combining wind speed prediction with feedforward control, thereby reducing the time of the wind turbine blade in a fatigue working condition, ultimately prolonging the service life of the blade. At the same time, the application can effectively improve the service life of the variable pitch bearing by judging the variable pitch fatigue state of the wind turbine and adopting different pitch angles for variable pitch control according to different fatigue states of the wind turbine.

[0071] In step S100, the wind resource information at least includes the inflow wind speed of the environment where the target wind turbine is located; the operating parameters include: the variable pitch bearing temperature, the variable pitch motor temperature, the number of variable pitches within a plurality of specified unit times before the current unit time, the variable pitch mileage within a plurality of specified unit times before the current unit time, the total number of variable pitches and the total variable pitch mileage.

[0072] ​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, the wind resource prediction information of the environment where the target wind turbine is located at the next unit time is output through the preset wind resource prediction model, including: taking the inflow wind speed of the environment where the target wind turbine is located as input, the first inflow wind speed of the environment where the target wind turbine is located at the next unit time is output through the first wind speed prediction model, and the inflow wind speed of the environment where the target wind turbine is located is taken as input, and the second inflow wind speed of the environment where the target wind turbine is located at the next unit time is output through the second wind speed prediction model; the first weight of the first wind speed prediction model and the second weight of the second wind speed prediction model are determined, the first inflow wind speed and the second inflow wind speed are weighted and summed based on the first weight and the second weight, and the target inflow wind speed of the environment where the target wind turbine is located at the next unit time is obtained; wherein the first wind speed prediction model is obtained by training the first deep learning algorithm with the historical inflow wind speed of the target wind turbine, the second wind speed prediction model is obtained by training the 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 historical wind speed data of the target wind turbine, for example, the historical wind speed data of the past year, is used to train the long short-term memory neural network and the convolutional neural network, for example, the wind speed at the N+1 unit time is predicted by the wind speed at the past N unit time in the historical wind speed data. The network parameters of the long short-term memory neural network or the convolutional neural network are adjusted through 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.

[0073] In step S300, the first pitch angle corresponding to the wind resource prediction information is determined, including: determining the pitch angle corresponding to the target inflow wind speed in the preset pitch angle corresponding relationship table as the first pitch angle, wherein the pitch angle corresponding relationship table at least includes the pitch angle corresponding to different historical inflow wind speed. It can be understood that the corresponding relationship between wind speed and pitch angle can be pre-configured, wherein the pitch angle corresponding to different wind speed is the optimal pitch angle under the wind speed.

[0074] In step S300, it is determined that the target wind turbine is in the variable pitch fatigue state according to the operating parameters of the target wind turbine, including:

[0075] S310, determine the pitch bearing temperature, the pitch motor temperature, the number of pitches in the plurality of specified unit instants before the current unit instant, the pitch mileage in the plurality of specified unit instants before the current unit instant, the total number of pitches and the total pitch mileage corresponding to the pitch fatigue coefficient through the preset fatigue coefficient table, wherein the fatigue coefficient table at least includes different pitch bearing temperatures, pitch motor temperatures, numbers of pitches in the plurality of specified unit instants before the current unit instant, pitch mileages in the plurality of specified unit instants before the current unit instant, total numbers of pitches and total pitch mileages corresponding to the pitch fatigue coefficient. It can be understood that the bearing rated life is the number of revolutions or hours experienced by the bearing before pitting occurs under the action of a certain load, and the bearing revolutions have a direct correspondence with the total angle of bearing rotation. At the same time, in the process of executing the pitch, components such as the pitch bearing and the pitch motor may be frequently repeated, and long-time operation in this way may cause fatigue damage to the pitch bearing and the pitch motor and the like. Therefore, the present application pre-configures the correspondence between different operating parameters and the fatigue coefficient, for example, when the pitch bearing temperature is in different temperature intervals, different fatigue coefficients are corresponded, the higher the temperature, the higher the corresponding fatigue coefficient; the more the number of pitches in the plurality of specified unit instants before the current unit instant, the more frequent the pitch action of the fan in the recent period of time, and therefore the more the number of pitches, the higher the corresponding fatigue coefficient. Similarly, the larger the values of the pitch motor temperature, the pitch mileage in the plurality of specified unit instants before the current unit instant, the total number of pitches and the total pitch mileage, the higher the corresponding fatigue coefficient.

[0076] S320, determine the parameter weight of each operating parameter, and perform weighted summation on the pitch bearing temperature, the pitch motor temperature, the pitch frequency in the plurality of specified unit instants before the current unit instant, the pitch mileage in the plurality of specified unit instants before the current unit instant, the pitch fatigue coefficient of the pitch total frequency and the pitch total mileage based on the parameter weight of each operating parameter, to obtain the pitch fatigue degree of the target wind turbine at the current unit instant, and 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 in the plurality of specified unit instants before the current unit instant, the pitch total frequency and the pitch total mileage are used to represent the pitch frequency of the wind turbine in the recent period of time, and when the wind turbine is in a frequent pitch state for a long time, the pitch-related components of the wind turbine are more likely to be fatigued and damaged, so a higher weight can be configured for the pitch mileage in the plurality of specified unit instants before the current unit instant, the pitch total frequency and the pitch total mileage. The pitch bearing temperature and the pitch motor temperature are also the real-time state reactions to the pitch process, and have a direct impact on the pitch fatigue, so a higher weight can also be configured. The pitch total frequency and the pitch total mileage represent the cumulative fatigue damage of the pitch, and have a smaller impact on the real-time fatigue damage of the pitch process, so a lower weight can be configured. The pitch fatigue degree threshold can be preconfigured, and the pitch fatigue degree threshold can be determined by simulation or experiment, which is not limited here.

[0077] In step S400, the second pitch angle of the target wind turbine is determined based on the comparison result of the wind resource prediction information and the wind resource information, including:

[0078] S410, determine the wind speed difference between the target inflow wind speed of the environment where the target wind turbine is located at the next unit instant and the inflow wind speed of the environment where the target wind turbine is located at the current unit instant; wherein the inflow wind speed at the current unit instant can be the actual wind speed collected by the anemometer.

[0079] S420, if the wind speed difference value is less than the preset wind speed difference threshold value and the output power of the target wind turbine at the current unit time and the target incoming wind speed at the next unit time meets the preset wind turbine output power constraint condition, taking the pitch angle of the target wind turbine at the current unit time as the second pitch angle; wherein the wind turbine output power constraint condition includes that 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 time. Wherein, if the wind speed difference value is less than the preset wind speed difference threshold value, it means that the wind speed changes little, at this time, the output power of the target wind turbine at the next unit time is calculated by taking the pitch angle of the target wind turbine at the current unit time and the target incoming wind speed at the next unit time predicted, if the constraint condition can be met, the current pitch angle is kept unchanged, thereby avoiding the pitch action too frequent, prolonging the service life of the pitch related components. Wherein, the power calculation formula of the wind turbine is , wherein CP is the wind energy utilization coefficient, ρ is the air density, kg / m3, A is the wind wheel sweeping area, m2, and v is the wind speed, m / s, wherein the wind energy utilization coefficient can be expressed as , wherein B is the pitch angle, is the tip speed ratio, wherein , is the impeller speed, rad / s, and R is the impeller radius, m. It can be understood that the wind wheel sweeping area, the impeller speed, the impeller radius and other parameters can be obtained in advance or monitored in real time.

[0080] S430, if the wind speed difference value is greater than the wind speed difference threshold value or the output power of the target wind turbine at the current unit time and the target incoming wind speed at the next unit time does not meet the wind turbine output power constraint condition, the optimal pitch angle that meets the target function and the wind turbine output power constraint condition under the target incoming wind speed at the next unit time is obtained by optimizing and solving the target function constructed in advance, and the optimal pitch angle is taken as the second pitch angle. If the wind speed difference value is greater than the preset wind speed difference threshold value, it means that the wind speed fluctuates greatly, at this time, if the pitch angle is kept unchanged, the power generation will be greatly affected, and the wind turbine may be damaged, therefore, in this case, in order to minimize the power generation loss and the damage to the wind turbine, and reduce the fatigue damage of the pitch bearing, the optimal pitch angle of the target wind turbine at the next unit time is obtained by optimizing the target function and the constraint condition constructed in advance.

[0081] In step S430, the construction method of the target function includes:

[0082] S431, a first relationship function B is constructed, which represents the first pitch angle difference value between the to-be-optimized pitch angle of the target wind turbine at the next unit time and the pitch angle at the current unit time. i+1 -B i , wherein B i+1 represents the to-be-optimized pitch angle at the i+1th unit time, B i represents the pitch angle at the ith unit time; and a second relationship function B' is constructed, which represents the second pitch angle difference value between the optimal pitch angle of the target wind turbine at the next unit time and the pitch angle at the current unit time. i+1 -B i , wherein B' i+1 represents the optimal pitch angle of the target wind turbine at the next unit time under the target inflow wind speed, which can be obtained through the pitch angle corresponding relationship table; an actual cost of the variable pitch bearing is obtained, and a third relationship function C 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. bear (Bi+1-Bi) / (B' i+1 -B i ), wherein C bear represents the actual cost of the variable pitch bearing, which can be determined in advance.

[0083] S432, a fourth relationship function and a fifth relationship function are constructed, which represent the output power of the target wind turbine at the next unit time under the to-be-optimized pitch angle and the optimal pitch angle respectively, an on-grid electricity price at the next unit time is obtained, and a sixth relationship function is established 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 above-mentioned power calculation formula of the wind turbine, the fourth relationship function is represented as P i , and the fifth relationship function is represented as P' i , and the sixth relationship function can be represented as c(P i -P' i ), wherein c represents the on-grid electricity price.

[0084] S433, based on the actual cost of the variable pitch bearing, the third relationship function and the sixth relationship function, a target function is constructed with the maximum total revenue as the target, and the target function can be represented as maxF=C bear -C bear (Bi+1-Bi) / (B' i+1 -B i )+c(P i -P' i ).

[0085] In step S400, the pre-constructed objective function is optimized and solved to obtain the optimal pitch angle that meets the objective function and the wind turbine output power constraint condition under the target inflow wind speed at the next unit time, including optimizing and solving the objective function by a particle swarm algorithm, and the steps include:

[0086] S10, initializing the particle swarm, determining the particle number of the particle swarm and the initial position of each particle, and mapping the to-be-optimized pitch angle of the target wind turbine at the next unit time to the position of each particle.

[0087] 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, taking the objective function value as the fitness value of each particle.

[0088] S30, updating the speed and position of each particle based on the individual extreme value and the group extreme value of each particle; wherein the speed updating formula is:

[0089]

[0090] The position updating formula is:

[0091]

[0092] wherein, j represents the dimension of the particle, i represents the i-th particle, t represents the current iteration number, c1 and c2 are acceleration constants, usually taking values in the interval (0, 2), r1 and r2 are two random numbers with values in the range of [0, 1], p best represents the individual extreme value, g best represents the group extreme value.

[0093] S40, determining the individual extreme value and the group extreme value of each particle after updating based on the objective function, for each particle, comparing its current fitness value with its historical optimal fitness value, if better, then the historical optimal value is taken as the new individual extreme value, and for each particle, comparing its current fitness value with the fitness value of the optimal position experienced by the group, if better, then the current fitness value is taken as the global optimal value, i.e. the group extreme value; 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, wherein the convergence condition can be reaching the maximum iteration number.

[0094] As shown in FIG. Figure 4 The second aspect of the present application provides a wind turbine variable pitch control device applying the wind turbine variable pitch control method described above, and the device includes:

[0095] A data acquisition module configured to acquire current wind resource information of an environment where a target wind turbine is located and current operating parameters of the target wind turbine.

[0096] a wind resource prediction module configured to take the wind resource information as input, and output, via a preset wind resource prediction model, wind resource prediction information of an environment where the target wind turbine is located at a next unit time, wherein the wind resource prediction model is obtained by training different deep learning algorithms based on historical wind resource information of the target wind turbine;

[0097] a pitch control module configured to, if it is determined that the target wind turbine is not in a pitch fatigue state according to the operating parameters of the target wind turbine, determine a first pitch angle corresponding to the wind resource prediction information, and control the target wind turbine to perform a pitch operation at the first pitch angle at the next unit time; and 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, determine a second pitch angle of the target wind turbine based on a comparison result of the wind resource prediction information and the wind resource information, and control the target wind turbine to perform a pitch operation at the second pitch angle at the next unit time.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0099] In a third aspect, the present application provides a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the wind turbine pitch control method as described above.

[0100] In a fourth aspect, the present application provides a terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the wind turbine pitch control method as described above when executing the computer program.

[0101] As Figure 5 shown is a schematic diagram of a terminal device provided by an embodiment of the present application. As 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. The processor 100 implements the steps in the above method embodiments when executing the computer program 102. Alternatively, the processor 100 implements the functions of the modules / units in the above apparatus embodiments when executing the computer program 102.

[0102] For example, the computer program 102 can be divided into one or more modules / units, one or more of which are stored in the memory 101 and executed by the processor 100 to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 102 in the terminal device 10.

[0103] The terminal device 10 can be a desktop computer, a notebook computer, a palm computer, a cloud server, and the like. The terminal device 10 can include, but is not limited to, the processor 100 and the memory 101. Those skilled in the art can understand that the terminal device 10 can include more or less components, or combine certain components, or different components, for example, the terminal device can also include an input / output device, a network access device, a bus, and the like. Figure 5 The terminal device 10 is only an example and does not constitute a limitation on the terminal device 10, and can include more or less components than those shown, or combine certain components, or different components, for example, the terminal device can also include an input / output device, a network access device, a bus, and the like.

[0104] The processor 100 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0105] The storage 101 can be an internal storage unit of the terminal device 10, such as a hard disk or a memory of the terminal device 10. The storage 101 can 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, or the like equipped on the terminal device 10. Further, the storage 101 can include both an internal storage unit and an external storage device of the terminal device 10. The storage 101 is used to store a computer program and other programs and data required by the terminal device 10. The storage 101 can also be used to temporarily store data that has been output or will be output.

[0106] Those skilled in the art will appreciate that embodiments of the present application can be realized in association with methods, apparatus, or computer program products. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, and the like) embodying computer-readable program code.

[0107] It should also be noted that the terms "comprising", "comprises", "including", "includes" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0108] The above merely provides an example of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, and the like within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A wind turbine pitch control method, characterized in that: include: Obtaining 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, a preset wind resource prediction model outputs wind resource prediction information for the environment in which the target wind turbine is located at the next unit time, wherein the wind resource prediction information includes a target inflow wind speed, wherein the wind resource prediction model is obtained by training different deep learning algorithms based on 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 according to the operating parameters of the target wind turbine generator set that the target wind turbine generator set is in a pitch change fatigue state, determining a second pitch angle of the target wind turbine generator set based on a comparison result of the wind resource prediction information and the wind resource information, and controlling the target wind turbine generator set to perform a pitch change operation at the second pitch angle at a next unit time; Determining a first pitch angle corresponding to the wind resource prediction information includes: Determining a pitch angle corresponding to the target inflow wind speed in a preset pitch angle correspondence table as a first pitch angle, wherein the pitch angle correspondence table at least includes pitch angles corresponding to different historical inflow wind speeds; Determining a second pitch angle of the target wind turbine generator system 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 generator 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 generator set output power constraint, the pitch angle of the target wind turbine generator 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 pre-constructed objective function is optimized and solved 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 at the next unit moment, and the optimal pitch angle is used as the second pitch angle.

2. The wind turbine pitch control method according to claim 1, characterized in that: The wind resource information includes at least the inflow wind speed of the environment in which the target wind turbine is located; and the wind resource prediction model includes at least: a first wind speed prediction model and a second wind speed prediction model; Taking the wind resource information as input, a preset wind resource prediction model outputs 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 a 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 a next unit time; Determining a first weight of the first wind speed prediction model and a second weight of the second wind speed prediction model, and performing a 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 in which the target wind turbine is located at a 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, 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. 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 1, characterized in that: The operating parameters include: pitch bearing temperature, pitch motor temperature, number of pitch changes within multiple specified unit times before the current unit time, pitch change mileage within multiple specified unit times before the current unit time, total number of pitch changes, and total pitch change 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 fatigue coefficients corresponding to 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 total pitch mileage by using 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 mileage; Determine the parameter weight of each operating parameter, and based on the parameter weight of each operating parameter, perform weighted summation on 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 the preset pitch fatigue threshold, determine that the target wind turbine is in a pitch fatigue state.

4. The wind turbine pitch control method according to claim 1, characterized in that: 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 target wind turbine generator set's pitch angle to be optimized at the next unit time and the pitch angle at the current unit time, and constructing a second relationship function representing a second pitch angle difference between the target wind turbine generator set's optimal pitch angle at the next unit time and the pitch angle at the current unit time, obtaining an actual cost of a variable pitch bearing, and establishing a third relationship function based on the actual cost of the variable pitch bearing and a 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 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 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 pitch bearing, the third relationship function, and the sixth relationship function, the objective function is constructed with the goal of maximizing total benefit.

5. The wind turbine pitch control method according to claim 4, 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 wind turbine output power constraint 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. Determine 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, return to step S30. If the convergence condition is met, stop searching and output the current group extreme value as the optimal pitch angle.

6. A wind turbine pitch control device, applying the wind turbine pitch control method according to any one of claims 1 to 5, 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, configured to take the wind resource information as input and output wind resource prediction information for the environment of the target wind turbine at the next unit time via a preset wind resource prediction model, wherein the wind resource prediction model is obtained by training different deep learning algorithms based on 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 the 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 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 the next unit time.

7. A computer-readable storage medium, characterized in that The computer program is stored, which, when executed by a processor, causes the processor to execute the wind turbine pitch control method according to any one of claims 1 to 5.

8. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the wind turbine pitch control method according to any one of claims 1 to 5 is implemented.

Images