基于WLT-GAN的轴承不平衡数据故障诊断方法

焦华超; 孙文磊; 王宏伟; 万晓静

doi:doi:10.19912/j.0254-0096.tynxb.2024-2035

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

基于WLT-GAN的轴承不平衡数据故障诊断方法

更新时间：2026-04-08

- 基于WLT-GAN的轴承不平衡数据故障诊断方法
- Vol. 47, Issue 3, Pages: 392-401(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-2035
  CLC： TP181
- Online First：07 April 2026，
  
  Published：2026
- 稿件说明：
移动端阅览
焦华超, 孙文磊, 王宏伟, et al. 基于WLT-GAN的轴承不平衡数据故障诊断方法[J]. 2026, 47(3): 392-401.
DOI：

焦华超, 孙文磊, 王宏伟, et al. 基于WLT-GAN的轴承不平衡数据故障诊断方法[J]. 2026, 47(3): 392-401. DOI： doi:10.19912/j.0254-0096.tynxb.2024-2035.

摘要

针对因轴承故障数据不平衡导致故障诊断模型准确率下降的问题

提出一种基于类小波变换生成对抗网络（WLT-GAN）的故障诊断方法。该方法将类小波变换神经网络嵌入生成器

并结合双判别器架构

使WLT-GAN能够深度学习信号的时域和频域特征

生成高质量的故障数据

从而有效缓解数据不平衡问题。此外

还引入集成学习构建故障诊断模型

通过软投票机制融合多源特征提高诊断精度。实验结果表明

WLT-GAN生成的样本在时域和频域特征分布上与真实数据高度相似

且该模型凭借集成学习优势

展现出较高的准确性与鲁棒性

可为风电机组轴承故障诊断提供高效、可靠的解决方案。

Abstract

To address the degradation in fault diagnosis accuracy caused by the imbalance of bearing fault data

this paper proposes a fault diagnosis method based on a wavelet-like transform generative adversarial network （WLT-GAN）. In the proposed method

the wavelet-like transform neural network is embedded into the generator and combined with a dual-discriminator architecture

enabling the WLT-GAN to jointly learn time-domain and frequency-domain features from vibration signals and generate high-quality fault samples to effectively alleviate data imbalance. In addition

an ensemble learning strategy is employed to construct the fault diagnosis model

where a soft-voting mechanism integrates multi-source features to improve diagnostic accuracy. Experimental results demonstrate that the samples generated by WLT-GAN exhibit high similarity to real data in both time- and frequency-domain feature distributions. Leveraging the advantages of ensemble learning

the proposed method achieves high accuracy and robustness

providing an efficient and reliable solution for bearing fault diagnosis in wind turbine generators.

关键词

Keywords

references

司伟伟, 岑健, 伍银波, 等. 小样本轴承故障诊断研究综述[J]. 计算机工程与应用, 2023, 59(6): 45-56.

CHEN X H, YANG R, XUE Y H, et al.Deep transfer learning for bearing fault diagnosis: a systematic review since 2016[J]. IEEE transactions on instrumentation and measurement, 2023, 72: 3508221.

和林芳, 王道涵, 田淼, 等. 基于IBCAN的风力发电机轴承故障诊断方法研究[J]. 太阳能学报, 2025, 46(1): 97-104.

陈强, 钱洵. 基于谐波消除和谱峭度的风电机组主轴承故障诊断[J]. 太阳能学报, 2025, 46(1): 1-8.

GAO S Z, SHI S, ZHANG Y M.Rolling bearing compound fault diagnosis based on parameter optimization MCKD and convolutional neural network[J]. IEEE transactions on instrumentation and measurement, 2022, 71: 3508108.

刘俊孚, 岑健, 黄汉坤, 等. 零小样本旋转机械故障诊断综述[J]. 计算机工程与应用, 2024, 60(15): 42-54.

苏元浩, 孟良, 许同乐, 等. 不平衡数据集下优化WGAN的风电机组齿轮箱故障诊断方法[J]. 太阳能学报, 2022, 43(11): 148-155.

郭伟, 邢晓松. 基于改进卷积生成对抗网络的少样本轴承智能诊断方法[J]. 中国机械工程, 2022, 33(19): 2347-2355.

李俊卿, 胡晓东, 王罗, 等. 考虑数据不足和基于合作博弈模型融合的风电机组轴承故障诊断方法[J]. 太阳能学报, 2024, 45(1): 234-241.

张永宏, 张中洋, 赵晓平, 等. 基于VAE-GAN和FLCNN的不均衡样本轴承故障诊断方法[J]. 振动与冲击, 2022, 41(9): 199-209.

何强, 唐向红, 李传江, 等. 负载不平衡下小样本数据的轴承故障诊断[J]. 中国机械工程, 2021, 32(10): 1164-1171, 1180.

郭俊锋, 王淼生, 孙磊, 等. 基于生成对抗网络的滚动轴承不平衡数据集故障诊断新方法[J]. 计算机集成制造系统, 2022, 28(9): 2825-2835.

LIAO W Q, YANG K, FU W L, et al.A review: the application of generative adversarial network for mechanical fault diagnosis[J]. Measurement science and technology, 2024, 35(6): 062002.

RUAN D W, CHEN X R, GÜHMANN C, et al. Improvement of generative adversarial network and its application in bearing fault diagnosis: a review[J]. Lubricants, 2023, 11(2): 74.

陈鹏. 基于振动信号的滚动轴承故障诊断方法综述[J]. 轴承, 2022(6): 1-6.

CERRADA M, SÁNCHEZ R V, LI C, et al. A review on data-driven fault severity assessment in rolling bearings[J]. Mechanical systems and signal processing, 2018, 99: 169-196.

WANG H Y, LI P, LANG X, et al.FTGAN: a novel GAN-based data augmentation method coupled time-frequency domain for imbalanced bearing fault diagnosis[J]. IEEE transactions on instrumentation and measurement, 2023, 72: 3502614.

李川, 伍依凡, 杨帅. 不平衡分布的数据驱动故障诊断的研究进展[J]. 仪器仪表学报, 2023, 44(8): 181-197.

钟宏宇. 面间小样本和轻量化的轴承智能故障诊断方法研究[D]. 武汉: 武汉科技大学, 2024.

张志明. 游梁式抽油机电机滚动轴承故障诊断方法研究[D]. 大庆: 东北石油大学, 2024.

STENGER M, LEPPICH R, FOSTER I, et al.Evaluation is key: a survey on evaluation measures for synthetic time series[J]. Journal of big data, 2024, 11(1): 66.

YIN W Z, XIA H, HUANG X Y, et al.A fault diagnosis method for nuclear power plants rotating machinery based on deep learning under imbalanced samples[J]. Annals of nuclear energy, 2024, 199: 110340.

闫向彤, 罗嘉伟, 曹现刚. WGAN-GP结合CBAM-VGG16轻量化网络滚动轴承故障诊断[J]. 噪声与振动控制, 2024, 44(5): 120-127.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

融合PCC-LSTM-XGBoost的中长期光伏功率预测模型

基于ISSA-RF算法的光伏阵列故障诊断研究

基于VMD-COMTBO-BiLSTM光伏阵列故障诊断研究

基于振动和转子电流深度融合的风电机组转频估计及故障诊断方法

考虑流动时滞效应的风电场偏航协同控制研究

Related Author

苏元浩

孟良

许同乐

孔晓佳

兰孝升

李云凤

密伟

蒋旭

Related Institution

Marketing Service Center of State Grid Liaoning Electric Power Co., Ltd.

School of Electrical Engineering and Information Engineering, Lanzhou University of Technology

School of Information Engineering, Lanzhou City University

Guangxi Power Grid Dispatching Control Center

Beihai Power Supply Bureau, Guangxi Power Grid

AI问答

⁰