基于不平衡样本数据的轴承故障诊断模型与方法研究

张伟业; 缪维跑; 苏欢欢; 李春

doi:10.19805/j.cnki.jcspe.2025.240262

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于不平衡样本数据的轴承故障诊断模型与方法研究

数字化与智能化 | 更新时间：2026-10-10

- 基于不平衡样本数据的轴承故障诊断模型与方法研究
- Research on Bearing Fault Diagnosis Model and Method Based on Unbalanced Sample Data
- 动力工程学报 2025年45卷第6期页码：904-912
- 作者机构：
  
  上海理工大学能源与动力工程学院,上海,200093
- 作者简介：
  
  张伟业(1998—),男,江苏南通人,硕士研究生,研究方向为深度学习与旋转机械系统故障诊断
- 基金信息：
  
  国家自然科学基金资助项目(52375193,52376204,52106262,52006148,51976131);上海市IV类高峰学科-能源科学与技术-上海非碳基能源转换与利用研究院建设资助项目
- DOI：10.19805/j.cnki.jcspe.2025.240262
  中图分类号：
- 网络首发：2025-06-16，
  
  纸质出版：2025
- 稿件说明：
移动端阅览
张伟业,缪维跑,苏欢欢,李春. 基于不平衡样本数据的轴承故障诊断模型与方法研究动力工程学报, 2025, 45(6): 904-912 https://doi.

org/10.19805/j.cnki.jcspe.2025.240262
张伟业,缪维跑,苏欢欢,李春. 基于不平衡样本数据的轴承故障诊断模型与方法研究动力工程学报, 2025, 45(6): 904-912 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.240262.

org/10.19805/j.cnki.jcspe.2025.240262 DOI：

摘要

为解决滚动轴承不平衡样本的诊断问题

提出了将条件生成对抗网络与多尺度注意力机制卷积神经网络相融合的诊断方法

通过该方法填充不平衡样本

采用分形盒维数筛选最佳生成样本

输入多尺度注意力机制卷积神经网络完成故障特征提取

并与原不平衡数据和传统样本填充方法进行对比。结果表明:所提方法有较高的识别准确率

可扩充小样本故障数据

有效解决不平衡数据下轴承故障分类问题。

Abstract

In order to solve the problems of rolling bearing unbalance sample diagnosis

a diagnostic method integrating conditional generative adversarial networks with multi-scale attention mechanism convolutional neural networks was proposed. By using this method to fill the unbalanced samples

the best generated samples were screened through fractal box dimension. The multi-scale attention mechanism convolutional neural network was input to complete the fault feature extraction. Then it was compared with the original unbalanced data and the traditional sample filling methods. Results show that the method has a high recognition accuracy

can expand the small sample fault data

and solve the problem of bearing fault classification under the unbalanced data effectively.

关键词

Keywords

references

EL-THALJI I, JANTUNEN E. A summary of fault modelling and predictive health monitoring of rolling element bearings[J]. Mechanical Systems and Signal Processing, 2015, 60-61: 252-272.

SUN Xiaoyan, SHANG Shuwen, XU Zhihui, et al. Assessment of dependent performance shaping factors in SPAR-H based on pearson correlation coefficient[J]. Computer Modeling in Engineering & Sciences, 2024, 138(2): 1813-1826.

CHOUDHURY M D, BLINCOE K, DHUPIA J S. Deep learning based time-frequency image enhancement method for machinery health monitoring[C]//2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM). Seattle, USA: IEEE, 2023.

DENG Wu, YAO Rui, ZHAO Huimin, et al. A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm[J]. Soft Computing, 2019, 23(7): 2445-2462.

周文宣, 刘洋, 邓敏强, 等. 基于CAE和CNN的变工况下滚动轴承智能故障诊断研究[J]. 动力工程学报, 2022, 42(1): 43-48. ZHOU Wenxuan, LIU Yang, DENG Minqiang, et al. Research on intelligent fault diagnosis of rolling bearings under variable conditions based on CAE and CNN[J]. Journal of Chinese Society of Power Engineering, 2022, 42(1): 43-48.

CHEN Xiaohan, ZHANG Beike, GAO Dong. Bearing fault diagnosis base on multi-scale CNN and LSTM model[J]. Journal of Intelligent Manufacturing, 2021, 32(4): 971-987.

SHAO Haidong, XIA Min, HAN Guangjie, et al. Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images[J]. IEEE Transactions on Industrial Informatics, 2021, 17(5): 3488-3496.

肖俊青, 金江涛, 李春, 等. 基于CEEMDAN样本熵与卷积神经网络的轴承故障诊断[J]. 动力工程学报, 2022, 42(5): 429-436. XIAO Junqing, JIN Jiangtao, LI Chun, et al. Bearing fault diagnosis based on CEEMDAN sample entropy and convolutional neural network[J]. Journal of Chinese Society of Power Engineering, 2022, 42(5): 429-436.

GUO Sheng, ZHANG Bin, YANG Tao, et al. Multitask convolutional neural network with information fusion for bearing fault diagnosis and localization[J]. IEEE Transactions on Industrial Electronics, 2020, 67(9): 8005-8015.

金江涛, 许子非, 李春, 等. 基于变分模态分解与优化支持向量机的滚动轴承故障诊断[J]. 动力工程学报, 2021, 41(3): 214-220, 243. JIN Jiangtao, XU Zifei, LI Chun, et al. Fault diagnosis of rolling bearings based on variational mode decomposition and optimized of support vector machine[J]. Journal of Chinese Society of Power Engineering, 2021, 41(3): 214-220, 243.

ZHAO Bo, ZHANG Xianmin, LI Hai, et al. Intelligent fault diagnosis of rolling bearings based on normalized CNN considering data imbalance and variable working conditions[J]. Knowledge-Based Systems, 2020, 199: 105971.

WEN Long, LI Xinyu, GAO Liang, et al. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998.

曹洁, 何智栋, 余萍, 等. 数据不平衡分布下轴承故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(11): 2523-2531. CAO Jie, HE Zhidong, YU Ping, et al. Bearing fault diagnosis method under unbalanced data distribution[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(11): 2523-2531.

CRESWELL A, WHITE T, DUMOULIN V, et al. Generative adversarial networks: an overview[J]. IEEE Signal Processing Magazine, 2018, 35(1): 53-65.

MENG Anbo, ZHANG Haitao, YIN Hao, et al. A novel multi-gradient evolutionary deep learning approach for few-shot wind power prediction using time-series GAN[J]. Energy, 2023, 283: 129139.

汪美琴, 袁伟伟, 张继业. 生成对抗网络GAN的研究综述[J]. 计算机工程与设计, 2021, 42(12): 3389-3395. WANG Meiqin, YUAN Weiwei, ZHANG Jiye. Overview of research on generative adversarial network GAN[J]. Computer Engineering and Design, 2021, 42(12): 3389-3395.

QI Y, SU L, GU J, et al. CE-CGAN: classification enhanced conditional generative adversarial networks for bearing fault diagnosis[C]//12th International Conference on Quality, Reliabily, Risk, Maintenance, and Safety Engineering (QRZMSE 2022). Emeishan: IET Conference Proceedings, 2022, 1777-1783.

FALCONER K J. The geometry of fractal sets[M]. London, UK: Cambridge University Press, 1985.

孙康, 金江涛, 李春, 等. 优化变分模态分解与深度学习融合的滚动轴承故障诊断策略[J]. 动力工程学报, 2023, 43(6): 749-758. SUN Kang, JIN Jiangtao, LI Chun, et al. Fault diagnosis strategy for rolling bearing based on optimal fusion of variational modal decomposition and deep learning[J]. Journal of Chinese Society of Power Engineering, 2023, 43(6): 749-758.

TIAN Yuling, LIU Xiangyu. A deep adaptive learning method for rolling bearing fault diagnosis using immunity[J]. Tsinghua Science and Technology, 2019, 24(6): 750-762.

XU Zifei, LI Chun, YANG Yang. Fault diagnosis of rolling bearings using an improved multi-scale convolutional neural network with feature attention mechanism[J]. ISA Transactions, 2021, 110: 379-393.

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

基于特征相似日和CNN-BiLSTM-Attention模型的风电短期出力预测

基于强化类级匹配网络的齿轮箱跨域故障诊断

煤-氨混燃锅炉建模及近邻传播-最小支持向量机多模态验证优化

基于WOA的循环流化床锅炉SO2排放浓度VMD-Transformer预测模型

计入工业园区电热负荷需求的源网荷储优化调度方法研究