基于双树复小波和深度信念网络的轴承故障诊断

中国机械工程

基于双树复小波和深度信念网络的轴承故障诊断

张淑清1;胡永涛1;姜安琦2;李军锋1;宿新爽1;姜万录3

1.燕山大学电气工程学院,秦皇岛，066004
2. 中南大学信息科学与工程学院，长沙，410006
3. 燕山大学机械工程学院,秦皇岛，066004

出版日期:2017-03-10 发布日期:2017-03-03
基金资助:
国家自然科学基金资助项目(51475405，61077071);
河北省自然科学基金资助项目(F2015203413, F2016203496, F2015203392)

Bearing Fault Diagnosis Based on DTCWT and DBN

ZHANG Shuqing1;HU Yongtao1;JIANG Anqi2;LI Junfeng1;SU Xinshuang1;JIANG Wanlu3

1.Institute of Electrical Engineering, Yanshan University, Qinhuangdao,Hebei ,066004
2.School of Information Science and Engineering, Central South University,Changsha,410006
3.Institute of Mechanical Engineering, Yanshan University, Qinhuangdao,Hebei ,066004

Online:2017-03-10 Published:2017-03-03

摘要/Abstract

摘要： 提出了一种基于双树复小波(DTCWT)和深度信念网络(DBN)的轴承故障诊断新方法。采用DTCWT对轴承振动信号进行分解实验，结果表明DTCWT能够很好地将信号分解到不同频带。进而提取能量熵作为故障特征，采用DBN小样本分类模型对轴承故障进行分类，并与传统分类器进行比较，结果表明该方法能准确识别不同故障类型，扩展了DBN在机械故障诊断中的应用。

关键词: 双树复小波, 深度信念网络, 受限波尔兹曼机, 故障诊断

Abstract: Based on DTCWT and DBN, a new method of bearing fault diagnosis was proposed. Experiments on bearing vibration signals decomposition show that the signals may be well decomposed into different frequency bands by DTCWT. Then, power entropy of different frequency bands were taken as the fault features and input to the model for classification and the traditional classifiers were taken as the comparison. Results show that the method may identify different fault types accurately, which expands the applications of DBN.

Key words: dual-tree complex wavelet transform (DTCWT), deep belief network (DBN), restricted Boltzmann machine (RBM), fault diagnosis

中图分类号:

TN911.6

张淑清, 胡永涛, 姜安琦, 李军锋, 宿新爽, 姜万录. 基于双树复小波和深度信念网络的轴承故障诊断[J]. 中国机械工程.

ZHANG Shuqing, HU Yongtao, JIANG Anqi, LI Junfeng, SU Xinshuang, JIANG Wanlu. Bearing Fault Diagnosis Based on DTCWT and DBN[J]. China Mechanical Engineering.

参考文献

[1]秦大力, 于德介. 基于本体的机械故障诊断贝叶斯网络[J]. 中国机械工程, 2013, 24(9): 1195-1209.
QIN Dali, YU Dejie.Ontology-based Diagnostic Bayesian Networks for Mechanical Fault Diagnosis[J].China Mechanical Engineering, 2013, 24(9): 1195-1209.

[2]艾树峰. 基于双树复小波变换的轴承故障诊断研究[J]. 中国机械工程, 2011, 22(20): 2446-2451.
AI Shufeng. Research on Bearing Fault Diagnosis Based on Dual-tree Complex Wavelet Transform[J].China Mechanical Engineering, 2011, 22(20): 2446-2451.
[3]李鑫滨, 陈云强, 张淑清. 基于改进ABC算法优化的 LSSVM 多分类器组机械故障诊断模型[J].中国机械工程, 2013, 24(16): 2157-2164.
LI Xinbin, CHEN Yunqiang, ZHANG Shuqing.Mechanical Fault Diagnosis Model Based on Improved ABC Algorithm Optimized Multiple LSSVM Classifier Group[J]. China Mechanical Engineering, 2013, 24(16): 2157-2164.
[4]HARISH N, LOKESH A, MANDAL S, et al. Parameter Optimization Using GA in SVM to Predict Damage Level of Non-reshaped Berm Breakwater[J]. The International Journal of Ocean and Climate Systems, 2014, 5(2)：79-88.
[5]AREL I, ROSE D C, KARNOWSKI T P. Deep Machine Learning—a New Frontier in Artificial Intelligence Research[J].IEEE Computational Intelligence Magazine,2010, 5(4): 13-18.
[6]BENGIO Y. Deep Learning of Representations for Unsupervised and Transfer Learning[J]. Unsupervised and Transfer Learning Challenges in Machine Learning, 2012(27): 17-36.

[7]JIN N, ZHANG J S, ZHANG C X. A Sparse-response Deep Belief Network Based on Rate Distortion Theory[J]. Pattern Recognition, 2014, 47(9): 3179-3191.

[8]LAROCHELLE H, MANDEL M, PASCANU R, et al. Learning Algorithms for the Classification Restricted Boltzmann Machine[J]. The Journal of Machine Learning Research, 2012, 13(1): 643-669.

[9]HINTON G E, OSINDERO S, TEH Y W. A Fast Learning Algorithm for Deep Belief Nets[J]. Neural Computation, 2006, 18(7):1527-54.

[10]TOMCZAK J M, ZIEBA M. Classification Restricted Boltzmann Machine for Comprehensible Credit Scoring Model[J]. Expert Systems with Applications, 2015, 42(4): 1789-1796.

[11]SHERI A M, RAFIQUE A, PEDRYCZ W, et al. Contrastive Divergence for Memristor-based Restricted Boltzmann Machine[J].Engineering Applications of Artificial Intelligence, 2015, 37: 336-342.

[1]	罗洁思, 于德介, 史美丽. 基于SVD和线调频小波路径追踪的转速波动齿轮箱故障诊断 [J]. J4, 201016, 21(16): 1947-1951.
[2]	郑近德, 王兴龙, 潘海洋, 童靳于, 刘庆运. 基于自适应自相关谱峭度图的滚动轴承故障诊断方法[J]. 中国机械工程, 2021, 32(07): 778-785，792.
[3]	陈换过, 刘培君, 俞杭, 肖雪. 基于改进PCA-SOM的电静压伺服作动器油滤堵塞故障诊断[J]. 中国机械工程, 2021, 32(07): 799-805.
[4]	丁嘉鑫;王振亚;姚立纲;蔡永武. 广义复合多尺度加权排列熵与参数优化支持向量机的滚动轴承故障诊断[J]. 中国机械工程, 2021, 32(02): 147-155.
[5]	杨路航1;李宝庆1;王平2,3;王健2,3;杨宇1. 基于概率输出弹性凸包的滚动轴承故障诊断方法[J]. 中国机械工程, 2021, 32(01): 40-46.
[6]	万书亭;彭勃;王晓龙. 基于双时域变换和稀疏编码收缩的滚动轴承早期故障诊断方法[J]. 中国机械工程, 2020, 31(23): 2829-2836.
[7]	孟宗;刘子涵;吕蒙. 基于改进奇异值分解滤波和谱峭度的滚动轴承故障诊断[J]. 中国机械工程, 2020, 31(20): 2420-2428.
[8]	王振亚;姚立纲. 广义精细复合多尺度样本熵与流形学习相结合的滚动轴承故障诊断方法[J]. 中国机械工程, 2020, 31(20): 2463-2471.
[9]	蔡艳平;范宇;陈万;张金明. 改进时频分析和特征融合在内燃机故障诊断中的应用[J]. 中国机械工程, 2020, 31(16): 1901-1911.
[10]	姜少飞;邬天骥;彭翔;李吉泉;李治;孙涛. 基于XGBoost特征提取的数据驱动故障诊断方法[J]. 中国机械工程, 2020, 31(10): 1232-1239.
[11]	陈雪峰, 郭艳婕, 许才彬, 商红兵. [学科发展]风电装备故障诊断与健康监测研究综述[J]. 中国机械工程, 2020, 31(02): 175-189.
[12]	刘洋;刘晓波;梁珊. 基于傅里叶分解方法的航空发动机转子故障诊断[J]. 中国机械工程, 2019, 30(18): 2156-2163.
[13]	李从志;郑近德;潘海洋;刘庆运. 基于精细复合多尺度散布熵与支持向量机的滚动轴承故障诊断方法[J]. 中国机械工程, 2019, 30(14): 1713-1719,1726.
[14]	刘兆伦1,2;张春兰2;武尤2;王海羽2;刘彬1,2. 一种增量式贝叶斯算法及篦冷机故障诊断[J]. 中国机械工程, 2019, 30(10): 1163-1171.
[15]	时中朝;郝伟娜;董红召. 基于朴素贝叶斯分类器的公共自行车系统故障诊断方法[J]. 中国机械工程, 2019, 30(08): 983-987.