CN-122014500-A - Yaw optimization control method, device and medium based on multi-source data fusion

CN122014500ACN 122014500 ACN122014500 ACN 122014500ACN-122014500-A

Abstract

The application relates to the technical field of wind turbines, in particular to a yaw optimization control method, equipment and medium based on multi-source data fusion, and aims to solve the technical problem that the traditional yaw optimization control method cannot realize accurate optimization control. The yaw optimization control method based on multi-source data fusion comprises the steps of constructing a tag data set of a wind turbine, wherein the tag data set comprises first yaw angles of the wind turbine under different wind conditions, acquiring a wind speed and wind direction prediction sequence of a future preset time period, determining a second yaw angle based on the first yaw angles and the wind speed and wind direction prediction sequence, and performing yaw optimization control on the wind turbine based on the second yaw angles. The wind turbine generator system has the advantages that the windward angle of the wind turbine generator system can be dynamically adjusted based on the optimal control of the second yaw angle, wind energy can be captured to the maximum extent to improve the power generation efficiency, the safe operation of the wind turbine generator system can be guaranteed through load constraint, and the yaw optimal control of the wind turbine generator system is effectively improved.

Inventors

ZHANG SHAOHUA
LI YAO
HU BIAO
BI JIANFENG
LAN Weibiao
YU JUNJIE
GE MINGWEI

Assignees

尚义县旭蓝新能源科技有限公司
华北电力大学

Dates

Publication Date: 20260512
Application Date: 20251217

Claims (10)

1. A yaw optimization control method based on multi-source data fusion, which is characterized by comprising the following steps: Constructing a tag data set of a wind turbine, wherein the tag data set comprises first yaw angles of the wind turbine under different wind conditions; acquiring a wind speed and direction prediction sequence of a future preset time period; determining a second yaw angle based on the first yaw angle and the wind speed and direction prediction sequence; And performing yaw optimization control on the wind turbine generator based on the second yaw angle.
2. The yaw optimization control method based on multi-source data fusion according to claim 1, wherein the constructing a tag dataset of a wind turbine generator includes: Acquiring attribute parameters of the wind turbine generator; building a wind turbine model based on the attribute parameters of the wind turbine; generating a turbulence dynamic wind file based on the wind turbine generator model; labeling the turbulence dynamic wind file to obtain a standard wind condition combination; Determining a first yaw angle corresponding to each standard wind condition; and integrating all standard wind conditions and corresponding first yaw angles to obtain the tag data set.
3. The method for yaw optimization control based on multi-source data fusion according to claim 2, wherein the turbulence dynamic wind file comprises an in-wind speed, an out-wind speed, a wind direction and a turbulence intensity, wherein the labeling the turbulence dynamic wind file comprises: Dividing wind speed intervals from cut-in wind speed to cut-out wind speed in the turbulence dynamic wind file at preset wind speed intervals, dividing wind direction intervals from wind direction in the turbulence dynamic wind file at preset wind direction intervals, and dividing turbulence intensity in the turbulence dynamic wind file into low, medium and high stages.
4. The method for yaw optimization control based on multi-source data fusion according to claim 2, wherein determining the first yaw angle corresponding to each of the standard wind conditions comprises: Iteratively calculating utility function values under different yaw angles by taking the yaw angles as iteration variables, wherein the utility function is determined based on the output power and load super-threshold penalty of the wind turbine under the standard wind conditions; Stopping calculation when the iteration times reach an iteration times threshold value, and obtaining an optimal utility function under the iteration times threshold value; And taking the yaw angle corresponding to the optimal utility function value as the first yaw angle.
5. The yaw optimization control method based on multi-source data fusion according to claim 1, wherein the acquiring the wind speed and direction prediction sequence of the future preset time period comprises: collecting a first wind speed and direction sequence; carrying out standardization processing on the first wind speed and direction sequence; and inputting the first wind speed and direction sequence after the standardization processing into a pre-trained echo state network to obtain a wind speed and direction prediction sequence in a future preset time period.
6. The yaw optimal control method based on multi-source data fusion according to claim 5, wherein the pre-trained echo state network is obtained by: Acquiring a second wind speed and direction sequence as a wind speed and direction training set; Preprocessing the data in the wind speed and direction training set to obtain a preprocessed data set; Constructing an echo state network model; and training the echo state network model by using the preprocessing data set to obtain a pre-trained echo state network.
7. The yaw optimal control method based on multi-source data fusion according to claim 1, wherein the acquiring a second yaw angle based on the first yaw angle and the wind speed and direction prediction sequence comprises: constructing a back propagation neural network model; Training the back propagation neural network model by utilizing the first yaw angle to obtain a pre-trained back propagation neural network; and inputting the wind speed and direction prediction sequence into the pre-trained back propagation neural network to obtain the second yaw angle.
8. The method of yaw optimization control based on multi-source data fusion according to claim 7, wherein the training the back propagation neural network using the first yaw angle comprises: obtaining constraint data of a wind turbine generator; Combining the historical wind speed and wind direction predicted value and the constraint data as sample input characteristic vectors, inputting a back propagation neural network and outputting a third yaw angle; calculating a prediction error between the first yaw angle and the third yaw angle; And adjusting network parameters of the back propagation neural network based on the prediction error until the prediction error between the first yaw angle and the third yaw angle is smaller than a preset threshold value or the iteration number is larger than a preset number of times, so as to obtain the pre-trained back propagation neural network.
9. An electronic device, comprising: At least one processor; And a memory communicatively coupled to the at least one processor; wherein the memory has stored therein a computer program which, when executed by the at least one processor, implements the multisource data fusion based yaw optimization control method of any one of claims 1 to 8.
10. A computer readable storage medium, in which a plurality of program codes are stored, characterized in that the program codes are adapted to be loaded and executed by a processor to perform the multisource data fusion based yaw optimization control method of any one of claims 1 to 8.

Description

Yaw optimization control method, device and medium based on multi-source data fusion Technical Field The invention relates to the technical field of wind turbines, and particularly provides a yaw optimization control method, equipment and medium based on multi-source data fusion. Background With the continuous development of the wind power industry, the yaw control system is increasingly critical to the improvement effect of the wind turbine generator system energy efficiency. Accurate yaw control can ensure that the rotor remains optimally aligned with the wind flow at all times, thereby maximizing wind energy capture efficiency. However, the traditional yaw optimization control method cannot realize accurate optimization control under the influence of variable meteorological factors such as wind speed, wind direction and the like, and the power generation performance is reduced due to response lag. Therefore, a yaw optimization control scheme which fuses multi-source data and combines simulation precision and real-time prediction capability is needed. Disclosure of Invention The application is proposed to solve or at least partially solve the technical problem that the conventional yaw optimization control method cannot realize accurate optimization control. The application provides a yaw optimization control method, equipment and medium based on multi-source data fusion. In a first aspect, the present application provides a yaw optimization control method based on multi-source data fusion, the method comprising: Constructing a tag data set of a wind turbine, wherein the tag data set comprises first yaw angles of the wind turbine under different wind conditions; acquiring a wind speed and direction prediction sequence of a future preset time period; determining a second yaw angle based on the first yaw angle and the wind speed and direction prediction sequence; And performing yaw optimization control on the wind turbine generator based on the second yaw angle. In one embodiment of the yaw optimization control method based on multi-source data fusion, the constructing the tag data set of the wind turbine includes: Acquiring attribute parameters of the wind turbine generator; building a wind turbine model based on the attribute parameters of the wind turbine; generating a turbulence dynamic wind file based on the wind turbine model, wherein the turbulence dynamic wind file comprises wind speed, wind direction and turbulence intensity; labeling the turbulence dynamic wind file to obtain a standard wind condition combination; Determining a first yaw angle corresponding to each standard wind condition; and integrating all standard wind conditions and corresponding first yaw angles to obtain the tag data set. In one embodiment of the yaw optimization control method based on multi-source data fusion, the labeling the turbulent dynamic wind file includes: Dividing wind speed intervals from cut-in wind speed to cut-out wind speed in the turbulence dynamic wind file at preset wind speed intervals, dividing wind direction intervals from wind direction in the turbulence dynamic wind file at preset wind direction intervals, and dividing turbulence intensity in the turbulence dynamic wind file into low, medium and high stages. In one embodiment of the yaw optimization control method based on multi-source data fusion of the present application, the determining the first yaw angle corresponding to each standard wind condition includes: iteratively calculating utility function values under different yaw angles by taking the yaw angles as iteration variables, wherein the utility function is determined based on the output power and load super-threshold penalty items of the wind turbine under the standard wind conditions; Stopping calculation when the iteration times reach an iteration times threshold value, and obtaining an optimal utility function under the iteration times threshold value; And taking the yaw angle corresponding to the optimal utility function value as the first yaw angle. In one embodiment of the yaw optimization control method based on multi-source data fusion of the present application, the obtaining a wind speed and wind direction prediction sequence of a preset time period in the future includes: collecting a first wind speed and direction sequence; carrying out standardization processing on the first wind speed and direction sequence; and inputting the first wind speed and direction sequence after the standardization processing into a pre-trained echo state network to obtain a wind speed and direction prediction sequence in a future preset time period. In one embodiment of the yaw optimization control method based on multi-source data fusion, the pre-trained echo state network is obtained through the following steps: Acquiring a second wind speed and direction sequence as a wind speed and direction training set; Preprocessing the data in the wind speed and direction training set to obtain a preprocess