CN-122014525-A - Maximum wind energy tracking method based on CAOA-Elman model and related equipment

CN122014525ACN 122014525 ACN122014525 ACN 122014525ACN-122014525-A

Abstract

The invention discloses a maximum wind energy tracking method and related equipment based on CAOA-Elman models, wherein the method comprises the steps of obtaining operation data of a wind turbine to be tested, wherein the operation data comprise wind wheel rotating speed, pitch angle and generator output power, inputting the operation data into the CAOA-Elman models for wind speed prediction to obtain a wind speed predicted value of the wind turbine to be tested, calculating a reference rotating speed corresponding to a maximum power point of the wind turbine to be tested according to the wind speed predicted value of the wind turbine to be tested and a preset tip speed ratio, and transmitting the reference rotating speed to a rotating speed control system of the wind turbine to be tested to achieve maximum wind energy tracking. The invention can realize high-efficiency operation control under the condition of randomly changing wind speed.

Inventors

ZHANG YU
HU BIAO
JI XIAO
WANG HE
LI DONG
XU CHANG
CHEN CHENG
XUE FEIFEI
YAN YAN
ZHANG YIZE

Assignees

盛东如东海上风力发电有限责任公司
华能国际电力江苏能源开发有限公司清洁能源分公司
河海大学

Dates

Publication Date: 20260512
Application Date: 20260204

Claims (10)

1. A method for maximum wind energy tracking based on CAOA-Elman model, comprising: Acquiring operation data of a wind turbine to be tested, wherein the operation data comprises wind wheel rotating speed, pitch angle and generator output power; inputting the operation data into CAOA-Elman model for wind speed prediction to obtain a wind speed predicted value of the wind turbine to be tested; Calculating a reference rotating speed corresponding to a maximum power point of the wind turbine to be tested according to the wind speed predicted value of the wind turbine to be tested and a preset tip speed ratio; and transmitting the reference rotation speed to a rotation speed control system of the wind turbine to be tested so as to realize maximum wind energy tracking.
2. The maximum wind energy tracking method based on CAOA-Elman model according to claim 1, further comprising preprocessing before inputting the operational data into the optimized wind speed prediction model, the preprocessing comprising: Cleaning operation data of the wind turbine to be tested, and processing missing values and abnormal values to obtain cleaned operation data; and carrying out normalization operation on the cleaned operation data, eliminating the influence of characteristic dimension, and obtaining the operation data after pretreatment.
3. The method for maximum wind energy tracking based on CAOA-Elman model according to claim 2, wherein the acquisition of CAOA-Elman model comprises: acquiring a historical operation data set of a wind turbine to be tested, and preprocessing the historical operation data set to obtain a preprocessed historical operation data set; Dividing the preprocessed historical operation data set into a training set and a testing set according to a preset proportion; Determining the structure of an Elman model, wherein the structure comprises an input layer, an hidden layer, a receiving layer, node numbers of an output layer and parameters to be optimized, and the parameters to be optimized comprise a receiving layer and hidden layer connection weight, an input layer and hidden layer connection weight, an output layer and hidden layer connection weight, a hidden layer threshold and an output layer threshold; initializing an alligator population, wherein the alligator population comprises a plurality of individuals, and the individuals represent a group of parameters to be optimized; Calculating an initial fitness value of each individual in the initial crocodile population by using a training set, and calculating an initial global optimal individual based on the initial fitness; according to the training set, the initial crocodile population and the initial global optimal individuals, iteratively updating the crocodile population until the iteration number is terminated, and obtaining the final updated global optimal individuals in the crocodile population; based on the last updated global optimal individual, a preliminary CAOA-Elman model is obtained; and performing index verification on the preliminary CAOA-Elman model by using a test set to obtain a CAOA-Elman model.
4. A maximum wind energy tracking method based on CAOA-Elman model as claimed in claim 3, wherein each iterative process comprises: Judging whether the method is in an exploration stage or a development stage according to the proportion of the current iteration times to the termination iteration times; If in the exploration stage, a land patrol mechanism is adopted to generate a new individual; if in the development stage, generating a new individual by adopting an underwater voltaic mechanism; calculating the fitness value of the new individual by using the training set, and comparing the fitness values of the new individual and the original individual, if the fitness value of the new individual is larger than the fitness value of the original individual, replacing the original individual by the new individual, otherwise, keeping the original individual; if the fitness value of an individual in the current crocodile population is higher than the fitness value of a historical global optimal individual, updating the individual to be the global optimal individual, otherwise, not updating the global optimal individual.
5. The method for tracking maximum wind energy based on CAOA-Elman model according to claim 4, wherein the determining whether in the exploration phase or the development phase according to the ratio of the current iteration number to the termination iteration number includes: If the ratio of the current iteration times to the ending iteration times is smaller than the preset proportionality coefficient, the method is in an exploration stage; If the ratio of the current iteration times to the ending iteration times is not less than the preset ratio coefficient, the method is in a development stage.
6. The method for tracking maximum wind energy based on CAOA-Elman model according to claim 5, wherein the calculation formula of the reference rotation speed is expressed as follows: ; Wherein omega ref is a reference rotation speed, lambda opt is a preset tip speed ratio, v pred is a wind speed predicted value of the wind turbine to be tested, and R is a wind wheel radius of the wind turbine to be tested.
7. A maximum wind energy tracking system based on CAOA-Elman model, comprising: the system comprises a data acquisition module, a control module and a control module, wherein the data acquisition module is used for acquiring operation data of a wind turbine to be tested, and the operation data comprises wind wheel rotating speed, pitch angle and generator output power; The wind speed prediction module is used for inputting the operation data into a CAOA-Elman model to perform wind speed prediction so as to obtain a wind speed predicted value of the wind turbine to be detected; The reference rotating speed calculating module is used for calculating the reference rotating speed corresponding to the maximum power point of the wind turbine to be measured according to the wind speed predicted value of the wind turbine to be measured and the preset tip speed ratio; and the transmission module is used for transmitting the reference rotating speed to a rotating speed control system of the wind turbine generator to be tested so as to realize maximum wind energy tracking.
8. An electronic device is characterized by comprising a memory and a processor; The memory is used for storing programs; The processor is configured to execute the program to implement the maximum wind energy tracking method based on CAOA-Elman model according to any one of claims 1-6.
9. A readable storage medium, on which a computer program is stored which, when being executed by a processor, implements a maximum wind energy tracking method based on CAOA-Elman model as claimed in any one of claims 1-6.
10. A computer program product comprising a computer program which, when executed by a processor, implements a maximum wind energy tracking method based on CAOA-Elman model as claimed in any one of claims 1-6.

Description

Maximum wind energy tracking method based on CAOA-Elman model and related equipment Technical Field The invention relates to the technical field of wind power control, in particular to a CAOA-Elman model-based maximum wind energy tracking method and related equipment. Background The wind energy is used as a clean and renewable energy form, has the advantages of being free from geopolitical influence and the restriction of traditional energy price fluctuation, and has important strategic significance for reducing the dependence on fossil energy and improving the national energy safety. In wind power generation systems, maximum wind energy tracking control is one of core technologies for improving wind energy capturing efficiency. The maximum wind energy tracking method is also called MPPT (Maximum Power Point Tracking) method, and the basic principle is that the wind turbine always operates at the optimal power output point under different wind speed conditions by adjusting the operation parameters such as the rotating speed, the pitch angle and the like of the wind generating set in real time, so that wind energy resources are utilized to the maximum extent. At present, the rapid development of the wind power industry puts higher demands on the wind energy utilization rate, so that the research and optimization of MPPT technology becomes the focus of industry attention. Despite the extensive research performed by students at home and abroad in the field of MPPT, the existing methods still face a series of challenges and limitations. Firstly, most control strategies are designed mainly aiming at working conditions with gentle wind speed change or below rated wind speed, have insufficient adaptability to random and abrupt wind speeds commonly existing in nature, and are difficult to maintain high-precision tracking performance when wind speeds rapidly or greatly fluctuate. Second, many advanced MPPT methods rely on real-time accurate measurements of wind speed sensors, which not only increase system cost and complexity, but also the measurement delay, error and risk of failure of the sensors are more likely to directly impact the reliability of the control. In addition, the traditional control strategy generally adopts sectional logic between different operation intervals of 'cut-in wind speed-rated wind speed-cut-out wind speed', the control algorithm needs to be forcedly switched when the wind speed crosses a critical point, abrupt changes of the torque and the output power of the generator are easily caused, fatigue of mechanical parts is aggravated, and stable operation of a power grid is influenced. In general, in the prior art, there is still a significant improvement in terms of self-adaptive capacity at high dynamic wind speeds, response speed, tracking accuracy under the condition of no sensor, and the like. Therefore, research on a novel intelligent control method which is independent of a wind speed sensor, strong in self-adaption, high in response speed and capable of realizing smooth and accurate wind energy tracking in a full wind speed range is needed, so that the operation efficiency, reliability and economy of a wind power generation system are fundamentally improved. Disclosure of Invention The invention aims to provide a CAOA-Elman model-based maximum wind energy tracking method and related equipment, which can be used for efficiently controlling operation under the condition of randomly changing wind speeds. In order to achieve the above purpose, the invention adopts the following technical scheme: in a first aspect, the present invention provides a method for maximum wind energy tracking based on CAOA-Elman model, comprising: Acquiring operation data of a wind turbine to be tested, wherein the operation data comprises wind wheel rotating speed, pitch angle and generator output power; inputting the operation data into CAOA-Elman model for wind speed prediction to obtain a wind speed predicted value of the wind turbine to be tested; Calculating a reference rotating speed corresponding to a maximum power point of the wind turbine to be tested according to the wind speed predicted value of the wind turbine to be tested and a preset tip speed ratio; and transmitting the reference rotation speed to a rotation speed control system of the wind turbine to be tested so as to realize maximum wind energy tracking. Optionally, the operation data is input into an optimized wind speed prediction model, and the preprocessing comprises: Cleaning operation data of the wind turbine to be tested, and processing missing values and abnormal values to obtain cleaned operation data; and carrying out normalization operation on the cleaned operation data, eliminating the influence of characteristic dimension, and obtaining the operation data after pretreatment. Optionally, the obtaining of CAOA-Elman model includes: acquiring a historical operation data set of a wind turbine to be tested, and preprocessing the his