互信息规范的卷积神经网络及其在轴承故障特征提取中的应用

doi:10.3901/JME.2024.12.137

机械工程学报 ›› 2024, Vol. 60 ›› Issue (12): 137-146.doi: 10.3901/JME.2024.12.137

• 特邀专栏：可解释可信AI驱动的智能监测与诊断 • 上一篇下一篇

扫码分享

互信息规范的卷积神经网络及其在轴承故障特征提取中的应用

王振亚^1,2, 刘韬^1,2, 伍星^2,3

1. 昆明理工大学机电工程学院昆明 650500;
2. 云南省先进装备智能制造技术重点实验室昆明 650500;
3. 云南机电职业技术学院昆明 650500

收稿日期:2023-11-21 修回日期:2024-02-25 出版日期:2024-06-20 发布日期:2024-08-23
作者简介:王振亚,男,1996年出生,博士研究生。主要研究方向为数据失衡情况下的机电系统故障状态监测,故障诊断领域的神经网络可解释性,迁移学习等。E-mail:zy1996w@163.com;刘韬(通信作者),男,1980年出生,博士,教授,博士研究生导师。主要研究方向为振动信号处理和故障诊断、设备的性能评估和健康预测。E-mail:kmliutao@aliyun.com
基金资助:
国家自然科学基金资助(52065030)、云南省重大科技专项计划(202202AC080008)和云南省教育厅重点(KKDA202001003)资助项目。

Convolutional Neural Network of Mutual Information Specification and Its Application in Bearing Fault Feature Extraction

WANG Zhenya^1,2, LIU Tao^1,2, WU Xing^2,3

1. Kunming University of Science and Technology Electromechanical Engineering School, Kunming 650500;
2. Yunnan Key Laboratory of Advanced Equipment Intelligent Manufacturing Technology, Kunming 650500;
3. Yunnan Mechanical and Electrical Vocational Technical College, Kunming 650500

Received:2023-11-21 Revised:2024-02-25 Online:2024-06-20 Published:2024-08-23

摘要/Abstract

摘要： 近年来，各种深度学习模型在故障诊断领域取得了突破性进展。该类方法能自动的从复杂的数据捕捉到设备在不同状态的规律，但其“不透明”特点导致了使用者对模型的不信任。从模型的拟合角度出发，提出一种通过互信息规则来规范模型输入输出之间关系的卷积神经网络模型。通过改进模型的损失，增强网络模型的特征提取能力，并将结果可视化。首先，将振动数据转换为包络谱作为模型第一层的输入；然后将用于特征提取的多层卷积视作一个系统，并设计该系统的输出与模型的输入大小一致使得模型便于理解；其次，添加注意力机制层以增强明显特征；最后，基于信号降噪前后之间的互信息规律设计了损失函数来驱动卷积系统可以提取更多故障特征频率成分。通过仿真信号与真实案例表明：所提方法的可视化结果不仅具有一定的解释性，并且在轴承的故障特征提取方面取得了一定的效果。

关键词: 卷积神经网络, 故障特征提取, 互信息, 滚动轴承, 特征可视化

Abstract: From the perspective of model fitting, we propose a convolutional neural networks model that regulates the relationship between model inputs and outputs through mutual information rules. The loss of the model is improved to enhance the feature extraction ability of the bearings and visualize the results. First, the vibration data is converted into an envelope spectrum as the input of the model so that the input layer has some physical meaning; then the multilayer convolution used for feature extraction is treated as a system and the output of the system is designed to be the same size as the input of the model so that the model is easy to understand; second, the attention mechanism layer is added to enhance the apparent features; finally, a loss function is designed to drive the convolutional system based on the mutual information law between the signal before and after noise reduction to extract more frequency components of the fault features. The simulated signals and real cases show that the visualization results of the proposed method are not only interpretable, but also effective in the extraction of fault features of bearings.

Key words: convolutional neural networks, fault feature extraction, mutual information, rolling bearing, feature visualization

中图分类号:

TG156

王振亚, 刘韬, 伍星. 互信息规范的卷积神经网络及其在轴承故障特征提取中的应用[J]. 机械工程学报, 2024, 60(12): 137-146.

WANG Zhenya, LIU Tao, WU Xing. Convolutional Neural Network of Mutual Information Specification and Its Application in Bearing Fault Feature Extraction[J]. Journal of Mechanical Engineering, 2024, 60(12): 137-146.

参考文献

[1] LEE J，WU F J，ZHAO W Y，et al. Prognostics and health management design for rotary machinery systems- Reviews，methodology and applications [J]. Mechanical Systems and Signal Processing，2014，42(1-2)：314-334.
[2] 雷亚国，贾峰，周昕，等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报，2015，51(21)：49-56. LEI Yaguo，JIA Feng，ZHOU Xin，et al. A deep learning-based method for machinery health monitoring with big data [J]. Journal of Mechanical Engineering，2015，51(21)：49-56.
[3] YANG D M，STRONACH A F，MACCONNELL P，et al. Third-order spectral techniques for the diagnosis of motor bearing condition using artificial neural networks [J]. Mechanical Systems and Signal Processing，2002，16(2-3)：391-411.
[4] XING S B，LEI Y G，WANG S H，et al. Distribution- invariant deep belief network for intelligent fault diagnosis of machines under new working conditions [J]. IEEE Transactions on Industrial Electronics，2021，68(3)：2617-2625.
[5] GUO S，ZHANG B，YANG T，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.
[6] YU W N，KIM I Y，MECHEFSKE C. Remaining useful life estimation using a bidirectional recurrent neural network based autoencoder scheme [J]. Mechanical Systems and Signal Processing，2019，129：764-780.
[7] QIN Y，XIANG S，CHAI Y，et al. Macroscopic- microscopic attention in LSTM networks based on fusion features for gear remaining life prediction [J]. IEEE Transactions on Industrial Electronics，2020，67(12)：10865-10875.
[8] LI X Q，JIANG H K，NIU M G，et al. An enhanced selective ensemble deep learning method for rolling bearing fault diagnosis with beetle antennae search algorithm [J]. Mechanical Systems and Signal Processing，2020，142：106752.
[9] QIN Y，WANG X，ZOU J Q. The optimized deep belief networks with improved logistic sigmoid units and their application in fault diagnosis for planetary gearboxes of wind turbines [J]. IEEE Transactions on Industrial Electronics，2019，66(5)：3814-3824.
[10] LIU S W，JIANG H K，WU Z H，et al. Data synthesis using deep feature enhanced generative adversarial networks for rolling bearing imbalanced fault diagnosis [J]. Mechanical Systems and Signal Processing，2022，163：108139.
[11] 邵海东，肖一鸣，颜深. 仿真数据驱动的改进无监督域适应轴承故障诊断[J]. 机械工程学报，2023，59(3)：76-85. SHAO Haidong，XIAO Yiming，YAN Shen. Simulation data-driven improvement unsupervised domain adaptive bearing fault diagnosis[J]. Journal of Mechanical Engineering，2023，59(3)：76-85.
[12] 陈祝云，钟琪，黄如意，等. 基于增强迁移卷积神经网络的机械智能故障诊断[J]. 机械工程学报，2021，57(21)：96-105. CHEN Zhuyun，ZHONG Qi，HUANG Ruyi，et al. Mechanical intelligent fault diagnosis based on enhanced migration convolutional neural network [J]. Journal of Mechanical Engineering，2021，57(21)：96-105.
[13] SELVARAJU R R，COGSWELL M，DAS A，et al. Grad-CAM：Visual explanations from deep networks via gradient-based localization [J]. International Journal of Computer Vision，2020，128(2)：336-359.
[14] LI T F，ZHAO Z B，SUN C，et al. WaveletKernelNet：An interpretable deep neural network for industrial intelligent diagnosis [J]. IEEE Transactions on Systems Man Cybernetics-Systems，2022，52(4)：2302-2312.
[15] WANG D，CHEN Y K，SHEN C Q，et al. Fully interpretable neural network for locating resonance frequency bands for machine condition monitoring [J]. Mechanical Systems and Signal Processing，2022，168：108673.
[16] WANG Z Y，LIU T，CHU W. A minimum mutual information optimized SSD and application in bearing fault detection [J]. Journal of Physics：Conference Series，2022，2203(1)：012012-012020.
[17] GU J X，WANG Z H，KUEN J，et al. Recent advances in convolutional neural networks [J]. Pattern Recognition，2018，77：354-377.
[18] LI X Y，CHANG D L，TIAN T，et al. Large-margin regularized softmax cross-entropy loss [J]. IEEE Access，2019，7(1)：19572-19578.
[19] 高强，杜小山，范虹，等. 滚动轴承故障的EMD诊断方法研究[J]. 振动工程学报，2007(1)：15-23. GAO Qiang，DU Xiaoshan，FAN Hong，et al. An empirical mode decomposition based method for rolling bearing fault diagnosis [J]. Journal of Vibration Engineering，2007(1)：15-23.
[20] JIANG F，ZHU Z，LI W. An improved VMD with empirical mode decomposition and its application in incipient fault detection of rolling bearing [J]. IEEE Access，2018，6：44483-44493.
[21] MIAO Y H，ZHAO M，LIN J，et al. Application of an improved maximum correlated kurtosis deconvolution method for fault diagnosis of rolling element bearings [J]. Mechanical Systems and Signal Processing，2017，92：173-195.

互信息规范的卷积神经网络及其在轴承故障特征提取中的应用

Convolutional Neural Network of Mutual Information Specification and Its Application in Bearing Fault Feature Extraction

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[2]	高帅, 韩勤锴, 褚福磊. 具备实时动态稳定性监测特性的高速混合陶瓷摩擦电滚动轴承[J]. 机械工程学报, 2024, 60(15): 80-88.
[3]	黄包裕, 张永祥. 一种基于三步法的轴承故障诊断方法[J]. 机械工程学报, 2024, 60(14): 51-68.
[4]	袁静, 任港星, 蒋会明, 赵倩, 魏臣隽, 朱骏. 基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J]. 机械工程学报, 2024, 60(12): 51-64.
[5]	陈钱, 陈康康, 董兴建, 皇甫一樊, 彭志科, 孟光. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65-76.
[6]	邓磊鑫, 谢清林, 陶功权, 温泽峰. 基于轴箱振动与动力学模型驱动的高速列车车轮失圆状态识别方法[J]. 机械工程学报, 2023, 59(3): 110-121.
[7]	王宇, 刘秋发, 彭一真. 非均匀监测条件下滚动轴承剩余寿命预测方法[J]. 机械工程学报, 2023, 59(23): 96-104.
[8]	苗永浩, 石惠芳, 李晨辉, 王南飞. 谐波特征模式分解方法在轴承故障诊断中的应用[J]. 机械工程学报, 2023, 59(21): 234-244.
[9]	孙凤山, 范孟豹, 曹丙花, 刘林. 基于时频关键信息融合的热障涂层太赫兹准确测厚方法[J]. 机械工程学报, 2023, 59(14): 10-22.
[10]	胡文扬, 王天杨, 张飞斌, 褚福磊. 仿真驱动下基于Ramanujan周期变换的轴承早期故障特征提取[J]. 机械工程学报, 2023, 59(13): 148-156.
[11]	郑琛, 丁康, 何国林, 林慧斌, 蒋飞. 冲击响应机理驱动稀疏表示自编码网络的滚动轴承故障特征提取[J]. 机械工程学报, 2023, 59(13): 175-183.
[12]	沈天浩, 丁康, 黎杰, 黄如意, 李巍华. 图结构联合时序数据驱动的装备剩余使用寿命预测方法[J]. 机械工程学报, 2023, 59(12): 183-194.
[13]	杨超颖, 刘颉, 周凯波. 基于路图注意力网络的轴承剩余寿命预测方法[J]. 机械工程学报, 2023, 59(12): 195-201.
[14]	卞文彬, 邓艾东, 刘东川, 赵敏, 刘洋, 李晶. 基于改进深度残差收缩网络的风电机组滚动轴承故障诊断方法[J]. 机械工程学报, 2023, 59(12): 202-214.
[15]	李建乐, 张佳奇, 黄念, 李腾腾, 徐浩, 夏梓旭, 武湛君. 基于深度学习的分布式光纤损伤识别方法[J]. 机械工程学报, 2022, 58(8): 88-95.