风力机齿轮箱无监督故障诊断方法研究

俎海东; 焦晓峰; 张万福; 孙康; 李春

doi:10.19805/j.cnki.jcspe.2025.230335

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 >

风力机齿轮箱无监督故障诊断方法研究

数字化与智能化 | 更新时间：2026-02-05

- 风力机齿轮箱无监督故障诊断方法研究
- Research on Unsupervised Fault Diagnosis Method for Wind Turbine Gearbox
- 动力工程学报 2025年45卷第1期页码：106-114
- 作者机构：
  
  1. 内蒙古电力科学研究院分公司,内蒙古,呼和浩特,010020
  2. 上海理工大学能源与动力工程学院,上海,200093
- 作者简介：
  
  [ "俎海东(1990—),男,内蒙古丰镇人,工程师,硕士,研究方向为旋转机械故障诊断" ]
  [ "张万福(通信作者),男,教授,博士,E-mail:wfzhang@usst.edu.cn" ]
- 基金信息：
  
  内蒙古电力科学研究院2022年自筹项目(510241220009);国家自然科学基金资助项目(52006148)
- DOI：10.19805/j.cnki.jcspe.2025.230335
  中图分类号： TM315
- 网络首发：2025-01-15，
  
  纸质出版：2025
- 稿件说明：
移动端阅览
俎海东,焦晓峰,张万福,孙康,李春. 风力机齿轮箱无监督故障诊断方法研究动力工程学报, 2025, 45(1): 106-114 https://doi.

org/10.19805/j.cnki.jcspe.2025.230335
俎海东,焦晓峰,张万福,孙康,李春. 风力机齿轮箱无监督故障诊断方法研究动力工程学报, 2025, 45(1): 106-114 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.230335.

org/10.19805/j.cnki.jcspe.2025.230335 DOI：

摘要

针对风力机齿轮箱振动信号具有强非线性特征

提出了改进变分模态分解方法对信号进行分解以提取特征分量

并以混沌相图及Lyapunov指数量化信号的非线性变化。采用随机近邻嵌入算法对多模态非线性故障特征集的冗余特征进行降维

以保证故障特征提取的可靠性并提升故障诊断准确率

所提出的无监督故障诊断框架无需人为对故障样本进行标注

更适合工程应用

并将所提方法应用于NREL GRC风力机齿轮箱故障。结果表明:改进变分模态分解方法可准确实现多模态特征提取

结合随机近邻嵌入算法

可有效消除冗余特征保证故障信息的可靠性

且同类样本聚集、异类样本差异增大

聚类表现更清晰

提升了故障分类的准确率。

Abstract

Aiming at strong nonlinear characteristics of wind turbine gearbox vibration signals

an improved variational mode decomposition method was proposed to decompose signals for extracting characteristic components

and the nonlinear changes of the signal were quantified by chaotic phase portraits and Lyapunov exponent. To ensure the reliability of fault feature extraction and improve the accuracy of fault diagnosis

the random nearest neighbor embedding algorithm was used to reduce redundant features of multi-modal nonlinear fault feature sets. The proposed method was applied to NREL GRC wind turbine gearbox faults due to the unsupervised fault diagnosis framework being more suitable for engineering applications without manual marking of fault samples. Results show that the improved variational mode decomposition method can accurately extract multi-modal features. Combined with the random nearest neighbor embedding algorithm

redundant features can be effectively eliminated to ensure the reliability of fault information. Moreover

the clustering of similar samples and the difference of heterogeneous samples increase

and the clustering performance is clearer

which improves the accuracy of fault classification.

关键词

Keywords

references

SUGUMARAN V, RAMACHANDRAN K I. Fault diagnosis of roller bearing using fuzzy classifier and histogram features with focus on automatic rule learning[J]. Expert Systems with Applications, 2011, 38(5): 4901-4907.

张国银, 王雪, 王海瑞, 等. 基于EEMD和模糊BP神经网络的滚动轴承故障诊断[J]. 化工自动化及仪表, 2017, 44(1): 34-38, 72. ZHANG Guoyin, WANG Xue, WANG Hairui, et al. Rolling bearing fault diagnosis based on EEMD and fuzzy BP neural network[J]. Control and Instruments in Chemical Industry, 2017, 44(1): 34-38, 72.

WANG Ziwei, ZHANG Qinghua, XIONG Jianbin, et al. Fault diagnosis of a rolling bearing using wavelet packet denoising and random forests[J]. IEEE Sensors Journal, 2017, 17(17): 5581-5588.

DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.

YANG Kai, WANG Guofeng, DONG Yi, et al. Early chatter identification based on an optimized variational mode decomposition[J]. Mechanical Systems and Signal Processing, 2019, 115: 238-254.

许子非, 岳敏楠, 李春. 基于改进变分模态分解与支持向量机的风力机轴承故障诊断[J]. 热能动力工程, 2020, 35(6): 233-242. XU Zifei, YUE Minnan, LI Chun. Nonlinear characteristic analysis of wind turbine bearings by SVM based on optimized variational mode decomposition[J]. Journal of Engineering for Thermal Energy and Power, 2020, 35(6): 233-242.

WANG Xiang, ZHENG Yuan, ZHAO Zhenzhou. Bearing fault diagnosis based on statistical locally linear embedding[J]. Sensors, 2015, 15(7): 16225-16247.

王望望, 邓林峰, 赵荣珍, 等.集成KPCA与t-SNE的滚动轴承故障特征提取方法[J]. 振动工程学报,2021,34(2):431-440. WANG Wangwang, DENG Linfeng, ZHAO Rongzhen, et al. Fault feature extraction of rolling bearing integrating KPCA and t-SNE[J].Journal of Vibration Engineering,2021,34(2):431-440.

MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.

许凡, 方彦军, 张荣. 基于EEMD模糊熵的PCA-GG滚动轴承聚类故障诊断[J]. 计算机集成制造系统, 2016, 22(11): 2631-2642. XU Fan, FANG Yanjun, ZHANG Rong. PCA-GG rolling bearing clustering fault diagnosis based on EEMD fuzzy entropy[J]. Computer Integrated Manufacturing Systems, 2016, 22(11): 2631-2642.

HE Qingbo. Vibration signal classification by wavelet packet energy flow manifold learning[J]. Journal of Sound and Vibration, 2013, 332(7): 1881-1894.

VAN DER MAATEN L. Accelerating t-SNE using tree-based algorithms[J]. Journal of Machine Learning Research, 2014, 15(1): 3221-3245.

刘洋, 曹云东, 侯春光. 基于经验模态分解及维格纳威尔分布的电缆双端故障定位算法[J]. 中国电机工程学报, 2015, 35(16): 4086-4093. LIU Yang, CAO Yundong, HOU Chunguang. The cable two-terminal fault location algorithm based on EMD and WVD[J]. Proceedings of the CSEE, 2015, 35(16): 4086-4093.

NREL. Wind turbine gearbox vibration condition monitoring benchmarking datasets[R]. Colorado, USA: National Renewable Energy Laboratory, 2012.

宋锐. 基于混沌激励的结构损伤识别研究[D]. 南京: 东南大学, 2015.

ABARBANEL H D I, BROWN R, SIDOROWICH J J, et al. The analysis of observed chaotic data in physical systems[J]. Reviews of Modern Physics, 1993, 65(4): 1331-1392.

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

基于强化类级匹配网络的齿轮箱跨域故障诊断

基于不平衡样本数据的轴承故障诊断模型与方法研究

多分支时间序列预测与迁移学习相结合的齿轮箱状态监测

基于改进变分模态分解的飞轮储能辅助火电二次调频控制策略

Prototype of multi-filament electron curtain accelerator