基于训练干扰卷积神经网络的风轮不平衡识别方法研究

陈明阳; 邢作霞; 郭珊珊; 徐健; 刘洋

doi:doi:10.19912/j.0254-0096.tynxb.2024-0869

欢迎来到能源电力期刊网！

English Version 读者登录期刊登录

您当前的位置：

首页 >

文章列表页 >

基于训练干扰卷积神经网络的风轮不平衡识别方法研究

更新时间：2025-10-22

- 基于训练干扰卷积神经网络的风轮不平衡识别方法研究
- 暂无标题
- 太阳能学报 2025年46卷第9期页码：162-170
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-0869
  中图分类号： TM614
- 网络出版：2025-10-14，
  
  纸质出版：2025
- 稿件说明：
移动端阅览
陈明阳, 邢作霞, 郭珊珊, 等. 基于训练干扰卷积神经网络的风轮不平衡识别方法研究[J]. 太阳能学报, 2025,46(9):162-170.
陈明阳, 邢作霞, 郭珊珊, 等. 基于训练干扰卷积神经网络的风轮不平衡识别方法研究[J]. 太阳能学报, 2025,46(9):162-170. DOI： doi:10.19912/j.0254-0096.tynxb.2024-0869.

DOI：

摘要

针对对风工况下的风轮不平衡的识别问题

提出一种融合专家系统和卷积神经网络的风轮不平衡识别方法。首先

基于对风轮不平衡的响应分析

提出一种风轮不平衡检测的专家系统。甄别风轮不平衡的状态

隔离风轮不平衡类型

定位风轮不平衡叶片。其次

针对风况变化对识别准确率的影响

提出一种基于多层训练干扰卷积神经网络的风轮不平衡识别方法

融合变概率的Dropout方法和极小的Mini-batch两种训练干扰策略进行训练

模拟风况变化的不确定性。最后

建立交叉验证数据集

对所提出方法进行验证与测试

对风轮不平衡识别的平均准确率达到98%以上

证明了该方法的有效性。

Abstract

For identificating rotor imbalance in wind turbine under varying wind directions

a method based on expert system and convolutional neural networks is proposed. Firstly

based on the response of rotor imbalances

an expert system for detection of rotor imbalance is proposed. It includes the identification

isolation and location of the rotor imbalance. Secondly

to address the impact of varying wind conditions on identification accuracy

a identification method based on convolutional neural network with training interference is proposed. The wind condition interference problem is reduced to a domain adaptive problem in the neural network for the identification of rotor imbalance. A variable probability Dropout method and a small Mini-batch are combined for training to simulate the uncertainty of wind. Finally

the cross-validation data set is established to verify and test the proposed method. The average accuracy is more than 98%

which proves the effectiveness of the proposed method.

关键词

Keywords

references

MEHLAN F C, NEJAD A R.Rotor imbalance detection and diagnosis in floating wind turbines by means of drivetrain condition monitoring[J]. Renewable energy, 2023, 212: 70-81.

ASTOLFI D.A study of the impact of pitch misalignment on wind turbine performance[J]. Machines, 2019, 7(1): 8.

田德, 李贝, 吴晓璇, 等. 风轮不平衡载荷下超大型风电机组叶片颤振极限研究[J]. 太阳能学报, 2024, 45(2): 198-205.

赵丽军, 张璠, 厉伟, 等. 风电机组风轮不平衡机械载荷时域特性分析[J]. 太阳能学报, 2020, 41(8): 342-350.

BERTELÈ M, BOTTASSO C L, CACCIOLA S.Automatic detection and correction of pitch misalignment in wind turbine rotors[J]. Wind energy science, 2018, 3(2): 791-803.

SAATHOFF M, ROSEMEIER M, KLEINSELBECK T, et al.Effect of individual blade pitch angle misalignment on the remaining useful life of wind turbines[J]. Wind energy science, 2021, 6(5): 1079-1087.

XU J, DING X, GONG Y L, et al.Rotor imbalance detection and quantification in wind turbines via vibration analysis[J]. Wind engineering, 2022, 46(1): 3-11.

CHEN Y C, GRIFFITH D T.Blade mass imbalance identification and estimation for three-bladed wind turbine rotor based on modal analysis[J]. Mechanical systems and signal processing, 2023, 197: 110341.

秦思远, 李峥峰. 风轮不平衡的风电机组机械振动信号频域特性分析[J]. 可再生能源, 2022, 40(9): 1202-1208.

巫发明, 杨从新, 王清, 等. 大型风力机风轮气动不平衡的特性研究与验证[J]. 太阳能学报, 2021, 42(1): 192-197.

XING Z X, CHEN M Y, CUI J, et al.Detection of magnitude and position of rotor aerodynamic imbalance of wind turbines using convolutional neural network[J]. Renewable energy, 2022, 197: 1020-1033.

党建, 魏晋源, 贾嵘, 等. 基于Hilbert和CA-VMD的风电机组叶轮不平衡故障电信号特征提取方法[J]. 电网与清洁能源, 2021, 37(1): 112-118, 126.

周迎九, 秦岭, 王兰, 等. 海上陆上风电机组风轮不平衡的辨识方法[J]. 船舶工程, 2019, 41(增刊1): 319-322, 326.

曹沂风. 基于支持向量机的风轮不平衡故障诊断方法研究[J]. 太阳能学报, 2024, 45(8): 613-620.

CHO S, CHOI M, GAO Z, et al.Fault detection and diagnosis of a blade pitch system in a floating wind turbine based on Kalman filters and artificial neural networks[J]. Renewable energy, 2021, 169: 1-13.

FREEMAN B, TANG Y F, HUANG Y, et al.Rotor blade imbalance fault detection for variable-speed marine current turbines via generator power signal analysis[J]. Ocean engineering, 2021, 223: 108666.

HÜBNER G R, PINHEIRO H, DE SOUZA C E, et al. Detection of mass imbalance in the rotor of wind turbines using support vector machine[J]. Renewable energy, 2021, 170: 49-59.

CAO Z, XU J, XIAO W, et al.A novel method for detection of wind turbine blade imbalance based on multi-variable spectrum imaging and convolutional neural network[C]//2019 Chinese Control Conference (CCC). Guangzhou, China, 2019: 4925-4930.

NATH S, WU J X, ZHAO Y, et al.Low latency bearing fault detection of direct-drive wind turbines using stator current[J]. IEEE access, 2020, 8: 44163-44174.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于卷积神经网络的风电机组气动不平衡故障诊断方法研究