基于CNN-SVM的深度卷积神经网络轴承故障识别研究

PDF(2082 KB)

振动与冲击 ›› 2019, Vol. 38 ›› Issue (18) : 173-178.

论文

荆云建1,2，胡晓依2，宋志坤1，侯银庆1

作者信息 +

Bearing fault identification by using deep convolution neural networks based on CNN-SVM

JING Yunjian1,2, HU Xiaoyi2, SONG Zhikun1, HOU Yinqing 1

Author information +

文章历史 +

摘要

针对传统智能诊断方法过分依赖于信号处理和专家经验提取故障特征以及模型泛化能力差的问题，基于深度学习理论，提出将卷积神经网络算法结合SVM分类器搭建适于滚动轴承故障诊断的改进型深度卷积神经网络模型。从原始实测轴承振动信号出发，模型逐层学习实现特征提取与故障识别，引入批量归一化、Dropout处理并改进模型分类器来提升轴承故障识别准确率、模型收敛速度和泛化能力。实验结果表明，优化后的深度学习模型可快速准确地提取轴承故障特征，针对不同类型、不同损伤程度的轴承可实现99%的识别准确率，并且模型有较强的泛化能力和强化学习能力。

Abstract

Considering that the traditional intelligent diagnosis methods rely too much on the signal processing and expert experience to extract fault features and are of poor model generalization ability, based on the deep learning theory, a deep convolution neural network algorithm combined with SVM classifier was proposed to build an improved fault diagnosis model for rolling bearings.Starting from the original measured bearing vibration signals, the model learns from each layer to achieve feature extraction and fault recognition, and introduces the batch normalization, Dropout processing and improved model classifier to improve the bearing fault recognition accuracy, model convergence speed and generalization ability.The experimental results show that the optimized deep learning model can quickly and accurately extract the characteristics of bearing faults.99% recognition accuracy can be achieved for bearings of different types and degrees of damages, and the model has strong generalization ability and enhanced learning ability.

导出引用

荆云建1,2，胡晓依2，宋志坤1，侯银庆1. 基于CNN-SVM的深度卷积神经网络轴承故障识别研究[J]. 振动与冲击, 2019, 38(18): 173-178

JING Yunjian1,2, HU Xiaoyi2, SONG Zhikun1, HOU Yinqing 1. Bearing fault identification by using deep convolution neural networks based on CNN-SVM[J]. Journal of Vibration and Shock, 2019, 38(18): 173-178

参考文献

[1]雷亚国，何正嘉. 混合智能故障诊断与预示技术的应用进展[J]. 振动与冲击,2011，30(9)：129-135.
Lei Ya-guo，He Zheng-jia. Advances in applications of hybrid intelligent fault diagnosis and prognosis technique[J]. Journal of Vibration and Shock，2011,30(9):129-135.
[2] 雷亚国，贾峰.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 Ya-guo, Jia Feng．A deep learning-based method for machinery health monitoring with big data［J］．Journal of Mechanical Engineering，2015，51 ( 21) : 49-56.
[3]Feng Jia, Yaguo Lei. Deep normalized convolutional neural network for imbalanced fault classiﬁcation of machinery and its understanding via visualization[J]. Mechanical Systems and Signal Processing 110 (2018): 349–367.
[4] Shao Hai-dong, Jiang Hong-kai. A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders[J]. Mechanical Systems and Signal Processing 102 (2018) 278–297.
[5] 袁建虎.基于小波时频图和 CNN 的滚动轴承智能故障诊断方法[J].机械设计与研究,2017，33(2)93-97.
Yuan Jian-hu. An Approach to Intelligent Fault Diagnosis of rolling Bearing Using Wavelet Time-Frequency representations and CNN[J]. Machine Design and research,2017,33(2)93-97.
[6] 王丽华,谢阳阳. 基于卷积神经网络的异步电机故障诊断[J].振动、测试与诊断.2017,37(6)1209-1215.
Wang Li-hua, Xie Yang-yang. Motor Fault Diagnosis Based on Convolutional Neural Networks[J]. Journal ofVibration,Measurement &Dignosis,2017,37(6)1209-1215.
[7]杨宇.基于EMD和支持向量机的旋转机械故障诊断方法研究[D].湖南大学,2005.
Yang Yu. Researeh on Fault Diagnosis Methods for Rotating Maehiney Based on Empirical Mode Decomposition and Support Vector Machine[D], HunanUniversity,2005.
[8] Kingma D, Ba . Adam:A method for stochastic optimization[J]. ar Xiv preprint arXiv:1412.6980, 2014
[9] Hinton G E,S Rivastava N, Krizhevsky A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Research Gate, 2012,3(4):212-223.
[10] Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-resnet and the impact of residual connections on learning[J]. ar Xiv preprint arXiv:1602.07261, 2016.
[11] Bengio Y, Lamblin P, Popovici, et al. Greedy layer-wise training of deep networks [J]. Adances in Neural Information Processing Systems, 2007, 19:153-160.
[12] Kumar H S, Pai P S, Sriram N S, et al. Comparison of denoising schemes and dimensionality reduction techniques for fault diagnosis of rolling element bearing using wavelet transform [J].International Journal of Manufacturing Research, 2016, 11(3): 238-258.
[13] 朱霄珣. 基于支持向量机的旋转机械故障诊断与预测方法研究[D].华北电力大学,2013.
Zhu Xiao-xun. Research on Rotating Machine Fault Diagnosis and State Prediction Method Based on Support Vector Machine[D]. North China Electric Power University, 2013.
[14]赵志宏. 基于振动信号的机械故障特征提取与诊断研究[D].北京交通大学,2012.
Zhao Zhi-hong. Research on Vibration Signal Based Machinery Fault Feature Extraction and Diagnosis[D]. Beijing Jiaotong University,2012.
[15] Shen Z, Chen X, Zhang X, et al. A novel intelligent gear fault diagnosis model based on EMD and multi-class TSVM [J]. Measurement, 2012, 45(1):30-40.