融合多小波分解的深度卷积神经网络轴承故障诊断方法

陶唐飞; 周文洁; 况佳臣; 徐光华

doi:10.7652/xjtuxb202405004

您当前的位置：

首页 >

文章列表页 >

融合多小波分解的深度卷积神经网络轴承故障诊断方法

—————————————————————— | 更新时间：2025-07-28

- 融合多小波分解的深度卷积神经网络轴承故障诊断方法
- Bearing Fault Diagnosis Method of Deep Convolutional Neural Network Based on Multiwavelet Decomposition
- 西安交通大学学报 2024年58卷第5期页码：31-41
- 作者机构：
  
  1. 西安交通大学现代设计及转子轴承系统教育部重点实验室,西安,710049
  2. 西安交通大学机械工程学院,西安,710049
- 作者简介：
  
  : 2023-08-05。作者简介: 陶唐飞(1972—),男,副教授,博士生导师。基金项目: 国家重点研发计划资助项目(2019YFB2004400)。
- 基金信息：
  
  : 2023-08-05。作者简介: 陶唐飞(1972—),男,副教授,博士生导师。基金项目: 国家重点研发计划资助项目(2019YFB2004400)。
- DOI：10.7652/xjtuxb202405004
  中图分类号： TH17
- 网络首发：2024-05-10，
  
  纸质出版：2024
- 稿件说明：
移动端阅览
陶唐飞, 周文洁, 况佳臣, 等. 融合多小波分解的深度卷积神经网络轴承故障诊断方法[J]. 西安交通大学学报, 2024,58(5):31-41.

TAO Tangfei, ZHOU Wenjie, KUANG Jiachen, et al. Bearing Fault Diagnosis Method of Deep Convolutional Neural Network Based on Multiwavelet Decomposition[J]. 2024, 58(5): 31-41.
陶唐飞, 周文洁, 况佳臣, 等. 融合多小波分解的深度卷积神经网络轴承故障诊断方法[J]. 西安交通大学学报, 2024,58(5):31-41. DOI： 10.7652/xjtuxb202405004.

TAO Tangfei, ZHOU Wenjie, KUANG Jiachen, et al. Bearing Fault Diagnosis Method of Deep Convolutional Neural Network Based on Multiwavelet Decomposition[J]. 2024, 58(5): 31-41. DOI： 10.7652/xjtuxb202405004.

摘要

针对卷积神经网络及其与信号降噪预处理集成方法面临高噪声环境和低质量数据挑战时难以有效地提取信号有用特征的问题

提出了一种融合Geronimo-Hardin-Massopust多小波分解的深度卷积神经网络模型(GHMMD-DCNN)。该模型思想是将多小波包分解与卷积神经网络深度融合

即设计多个一级多小波分解层以提取信号的低频分量和高频分量

再将多个一级多小波分解层与卷积层交替联接

使模型能够多尺度地提取并学习信号有用的时频域信息

信号分解和特征学习交替执行

进而实现强噪声鲁棒特征提取。在不同工况下的航空高速轴承振动数据上进行测试

结果表明:所提模型训练时能够快速达到稳定收敛

并且识别准确率均能达到99.9%以上; 提出的方法在强噪声干扰下的故障辨识准确度和识别稳定性均优于对比方法

验证了其优秀的抗噪声干扰能力; 在少训练样本测试中

提出的方法在单类训练样本数量为60时的平均诊断准确率高达91.19%

相比于其他方法最低提升了13.19%

验证了GHMMD-DCNN模型具有更优的低样本泛化能力。

Abstract

To tackle the challenge of convolutional neural network and its integration methods with denoising preprocessing methods struggling to effectively extract useful signal features amidst high noise environments and low-quality data

a deep convolutional neural network model based on the Geronimo-Hardin-Massopust multiwavelet decomposition(GHMMD-DCNN)is proposed. The model's concept revolves around deeply integrating the multiwavelet packet decomposition with the convolutional neural network. In other words

this involves the creation of multiple first-level multiwavelet decomposition layers to extract the low-frequency and high-frequency signal components

and these layers are lined alternately with the convolutional layer. This approach enables the model to extract and learn the useful time-frequency information of the signal on a multiscale basis. The signal decomposition and the feature learning are executed alternately

and robust feature extraction is realized even under strong noise conditions. Tests are carried out using aerospace high-speed bearing vibration data under different working conditions. The results show that the proposed model is able to reach stable convergence quickly and the recognition accuracy surpasses 99.9%. The proposed method showcases superior fault recognition accuracy and stability in the presence of significant noise interference compared to contrast methods

which demonstrates its excellent anti-noise ability. In the test of fewer training samples

the proposed method achieves an impressive average diagnosis accuracy of 91.19% with only 60 training samples per class. This represents a 13.19% enhancement over alternative methods

verifying the GHMMD-DCNN's exceptional low-sample generalization ability.

关键词

Keywords

references

赵碧. “十四五”大数据产业发展规划发布 [J]. 中国产经新闻, 2021-12-02(2).

董凯. “十四五”智能制造发展规划解读及趋势研判 [J]. 中国工业和信息化, 2022(1): 24-29.

DONG Kai. Interpretation and trend analysis of the 14th Five Year Plan for the development of intelligent manufacturing China industry and information technology [J]. China Industry Information Technology, 2022(1): 24-29.

陈雪峰, 訾艳阳. 智能运维与健康管理 [M]. 北京: 机械工业出版社, 2018.

雷亚国, 贾峰, 孔德同, 等. 大数据下机械智能故障诊断的机遇与挑战 [J]. 机械工程学报, 2018, 54(5): 94-104.

LEI Yaguo, JIA Feng, KONG Detong, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era [J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104.

何正嘉, 陈进, 王太勇, 等. 机械故障诊断理论及应用 [M]. 北京: 高等教育出版社, 2010.

时献江, 王桂荣, 司俊山. 机械故障诊断及典型案例解析 [M]. 北京: 化学工业出版社, 2013.

LEI Yaguo, YANG Bin, JIANG Xinwei, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap [J]. Mechanical Systems and Signal Processing, 2020, 138: 106587.

LIU Xiaozhi, XIE Jie, LUO Yanhong, et al. A novel power transformer fault diagnosis method based on data augmentation for KPCA and deep residual network [J]. Energy Reports, 2023, 9(8): 620-627.

徐统, 王红军, 宋智勇, 等. 基于K-L散度的VMD瞬时能量与PNN的滚动轴承故障诊断 [J]. 电子测量与仪器学报, 2019, 33(8): 117-123.

XU Tong, WANG Hongjun, SONG Zhiyong, et al. Rolling bearing fault diagnosis using VMD energy feature and PNN based on Kullback-Leibler divergence [J]. Journal of Electronic Measurement and Instrumentation, 2019, 33(8): 117-123.

UNAL M, ONAT M, DEMETGUL M, et al. Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network [J]. Measurement, 2014, 58: 187-196.

LÓPEZ C, NARANJO Á, LU Siliang, et al. Hidden Markov model based stochastic resonance and its application to bearing fault diagnosis [J]. Journal of Sound and Vibration, 2022, 528: 116890.

张鑫, 赵建民, 李海平, 等. 基于NIC-DWT-WOASVM的齿轮箱混合故障诊断 [J]. 振动与冲击, 2020, 39(11): 146-151, 164.

ZHANG Xin, ZHAO Jianmin, LI Haiping, et al. Compound fault diagnosis for gearbox based on NIC-DWT-WOASVM [J]. Journal of Vibration and Shock, 2020, 39(11): 146-151, 164.

HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-507.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84-90.

MCAULEY J J, RAMISA A, CAETANO T S. Optimization of robust loss functions for weakly-labeled image taxonomies [J]. International Journal of Computer Vision, 2013, 104(3): 343-361.

ZHANG Wei, PENG Gaoliang, LI Chuanhao, et al. A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals [J]. Sensors, 2017, 17(2): 425.

康涛, 段蓉凯, 杨磊, 等. 融合多注意力机制的卷积神经网络轴承故障诊断方法 [J]. 西安交通大学学报, 2022, 56(12): 68-77.

KANG Tao, DUAN Rongkai, YANG Lei, et al. Bearing fault diagnosis using convolutional neural network based on a multi-attention mechanism [J]. Journal of Xi'an Jiaotong University, 2022, 56(12): 68-77.

ZHAO Minghang, ZHONG Shisheng, FU Xuyun, et al. Deep residual shrinkage networks for fault diagnosis [J]. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4681-4690.

LI Tianfu, ZHAO Zhibin, SUN Chuang, et al. Wavelet KernelNet: an interpretable deep neural network for industrial intelligent diagnosis [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022, 52(4): 2302-2312.

WANG Huan, LIU Zhiliang, PENG Dandan, et al. Interpretable convolutional neural network with multilayer wavelet for noise-robust machinery fault diagnosis [J]. Mechanical Systems and Signal Processing, 2023, 195: 110314.

刘志刚, 钱清泉. 自适应阈值多小波故障暂态信号去噪方法 [J]. 系统工程与电子技术, 2004, 26(7): 878-880.

LIU Zhigang, QIAN Qingquan. Adaptive shrinkage value de-noising method of fault transient signals with multiwavelets [J]. Systems Engineering and Electronics, 2004, 26(7): 878-880.

袁静, 何正嘉, 王晓东, 等. 平移不变多小波相邻系数降噪方法及其在监测诊断中的应用 [J]. 机械工程学报, 2009, 45(4): 155-160.

YUAN Jing, HE Zhengjia, WANG Xiaodong, et al. Translation-invariant multiwavelets denoising using neighboring coefficients and its application to monitoring and diagnosis [J]. Journal of Mechanical Engineering, 2009, 45(4): 155-160.

洪连环. 面向航空发动机转子系统故障识别的多小波方法研究 [D]. 南京: 南京航空航天大学, 2020.

陈景龙. 自适应多小波的时频域优化构造与机械故障特征提取方法 [D]. 西安: 西安交通大学, 2014.

GERONIMO J S, HARDIN D P, MASSOPUST P R. Fractal functions and wavelet expansions based on several scaling functions [J]. Journal of Approximation Theory, 1994, 78(3): 373-401.[26] BUI T D, CHEN Guangyi. Translation-invariant denoising using multiwavelets [J]. IEEE Transactions on Signal Processing, 1998, 46(12): 3414-3420.

SUN Hailiang, HE Zhengjia, ZI Yanyang, et al. Multiwavelet transform and its applications in mechanical fault diagnosis: a review [J]. Mechanical Systems and Signal Processing, 2014, 43(1/2): 1-24.

李东敏. 基于多小波包和人工神经网络的电力系统故障类型识别研究 [D]. 成都: 西南交通大学, 2008.

DAGA A P, FASANA A, MARCHESIELLO S, et al. The Politecnico di Torino rolling bearing test rig: description and analysis of open access data [J]. Mechanical Systems and Signal Processing, 2019, 120: 252-273.

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

一种基于FPGA的卷积神经网络协处理器设计

融合多注意力机制的卷积神经网络轴承故障诊断方法

采用多尺度自适应选择卷积神经网络的轴承故障诊断研究

深度学习驱动的碳纤维管壁缺陷镜面红外检测无损定量评估方法

面向模型预测控制的风电机组深度Koopman全局线性建模方法