Research on intelligent fault diagnosis of wind turbine based on WOA-KELM algorithm

AN Liuming; SHA Desheng; ZHANG Qing; LI Qian; LIU Xiaobo; ZHANG Xinyun

doi:10.19666/j.rlfd.202303091

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Research on intelligent fault diagnosis of wind turbine based on WOA-KELM algorithm

更新时间：2025-09-28

- Research on intelligent fault diagnosis of wind turbine based on WOA-KELM algorithm
- Thermal Power Generation Vol. 52, Issue 12, Pages: 131-139(2023)
- 作者机构：
  
  中国华能集团清洁能源技术研究院有限公司
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202303091
  CLC： TP18;TM315
- Published：2023
- 稿件说明：
移动端阅览
AN Liuming, SHA Desheng, ZHANG Qing, et al. Research on intelligent fault diagnosis of wind turbine based on WOA-KELM algorithm[J]. Thermal power generation, 2023, 52(12): 131-139.
DOI：

AN Liuming, SHA Desheng, ZHANG Qing, et al. Research on intelligent fault diagnosis of wind turbine based on WOA-KELM algorithm[J]. Thermal power generation, 2023, 52(12): 131-139. DOI： 10.19666/j.rlfd.202303091.

摘要

针对风电机组存在的典型故障进行了归纳，选取某风场风电机组故障频次较高的变流系统、发电机系统、变桨系统、辅助电源系统故障数据和非故障数据进行故障诊断研究，分别采用极限学习机（ELM）、最小二乘支持向量机（SVM）、核极限学习机（KELM）和鲸鱼群优化算法（WOA）的WOA-KELM算法建立了故障诊断模型，同时采用拉普拉斯分数对模型特征变量重要程度进行排序和选取，WOA-KELM算法通过优化KELM算法的正则化参数C与核参数γ取得了更好的诊断效果。研究表明：不同样本数量下4种算法4对非故障类型的诊断准确率均为100%；采用拉普拉斯分数对WOA-KELM算法进行特征筛选后测试样本的平均诊断准确率从88.0%提高到93.2%;WOA-KELM算法在样本数量为250～500内进行特征筛选后的诊断准确率达到最大值96.0%。这证明该模型可以有效实现风电机组的故障诊断，为现场运维人员提供指导与参考。

Abstract

The typical faults of wind turbines are summarized. The fault data and non-fault data of converter system

generator system

variable propeller system and auxiliary power system with high fault frequency of wind turbines in a wind farm are selected for fault diagnosis research. The fault diagnosis model is established by ELM

SVM

KELM and WOA-KELM algorithms respectively. At the same time

Laplacian scores are used to sort and select the importance degree of model characteristic variables. WOA-KELM algorithm achieves better diagnostic effect by optimizing the regularization parameter C and kernel parameter γ of KELM algorithm. The results show that

the diagnostic accuracy of the four algorithms for non-fault types is 100% under different sample numbers. The average diagnostic accuracy of WOA-KELM algorithm improves from 88.0% to 93.2% after feature screening by using Laplace scores. In the range of 250～500 samples

the diagnostic accuracy of WOA-KELM algorithm reaches the maximum of 96.0% after feature screening. It is proved that this model can effectively realize the fault diagnosis of wind turbine

and provide guidance and reference for field operation and maintenance personnel.

关键词

Keywords

references

Views

305

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

MULTISENSOR INFORMATION MERGING TECHNOLOGY AND IT'S APPLICATION IN VIBRITION FAULT DIAGNOSIS OF ROTARY MACHINES

APPLICATION OF EXTENDED Petri NETWORK INTO FAULT DIAGNOSIS OF THERMAL POWER UNITS

APPLICATION OF MULTI-DIMENSIONAL BP NEURAL NETWORK IN FAULT DIAGNOSIS OF BOILERS

RESIDUAL SPACE OF KERNEL PRINCIPAL COMPONENT ANALYSIS BASED SENSOR FAULT DIAGNOSIS

Kernel principal component analysis based fault diagnosis for condenser systems

Related Author

JIN Fenghua

LI Luping

LUO Yi

CHEN Yu-fei

MA Zeng-huiNorth China Electric Power University

GAO Jianqiang

CHEN Peng College of Energy

ZHOU Weiqing1

Related Institution

Changsha University of Science and Technology

North China Electric Power University

College of Energy, Power and Mechanical Engineering, North China Electric Power University

Huaneng International Power Co., Ltd

AI问答

⁰