CNN-LSTM method with batch normalization for rolling bearing fault diagnosis

被引：0
|
作者：
Shen T. [1 ]
Li S. [1 ]
机构：
[1] College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing
来源：
Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2022年 / 28卷 / 12期
基金：
中国国家自然科学基金;
关键词：
batch normalization; convolutional neural networks; fault diagnosis; long short term memory neural networks; rolling bearing;
D O I：
10.13196/j.cims.2022.12.021
中图分类号：
学科分类号：
摘要：
The real-time monitoring of rotating machinery health is very important, and the rolling bearing fault is the focus of research. It is difficult to diagnose the machinery with complex structure efficiently and accurately by traditional fault diagnosis method. Deep learning develops rapidly in the field of mechanical fault diagnosis due to its strong ability of data analysis and learning. To improve the diagnosis accuracy of traditional Convolutional Neural Network (CNN), a CNN-LSTM model with Batch Normalization (BN) was proposed by considering the defects of Long Short Term Memory Network (LSTM) in diagnosis. Through testing with the CWRU bearing dataset, the results demonstrated that the diagnosis accuracy and efficiency of the hybrid model by batch normalization improved. The proposed method obtained a diagnosis result superior to the traditional deep learning fault diagnosis methods and could efficiently and accurately diagnose faults at various positions and degrees under various loads. © 2022 CIMS. All rights reserved.
引用
收藏
页码：3946 / 3955
页数：9
相关论文
共 22 条
  • [11] LECUN Y, BENGIO Y, HINTON G, Et al., Deep learning, Nature, 521, 7553, pp. 436-440, (2015)
  • [12] TAMILSELVAN P, WANG P., Failure diagnosis using deep belief learning based health state classification, Reliability Engineering & System Safety, 115, pp. 124-135, (2013)
  • [13] KIM Y., Convolutional neural networks for sentence classification
  • [14] LIPTON Z C, BERKOWITZ J, ELKAN C., A critical review of recurrent neural networks for sequence learning
  • [15] HOCHREITER S, SCHMIDHUBER J., Long short-term memory, Neural Computation, 9, 8, pp. 1735-1780, (1997)
  • [16] DU Yongping, ZHAO Xiaozheng, PEI Bingbing, Short text sentiment classification based on CNN-LSTM model, Journal of Beijing University of Technology, 45, 7, pp. 662-670, (2019)
  • [17] HUI Wenshan, LI Huijun, CHEN Meng, Et al., Robotic tactile recognition and adaptive grasping control based on CNN-LSTM, Chinese Journal of Scientific Instrument, 40, 1, pp. 211-218, (2019)
  • [18] QIAN Y M, BI M X, TIAN T, Et al., Very deep convolutional neural networks for noise robust speech recognition, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 24, 12, pp. 2263-2276, (2016)
  • [19] KANJO E, YOUNIS E M, ANG C S., Deep learning analysis of mobile physiological, environmental and location sensor data for emotion detection, Information Fusion, 49, pp. 46-56, (2019)
  • [20] IOFFE S, SZEGEDY C., Batch normalization: Accelerating deep network training by reducing internal covariate shift, Proceedings of Machine Learning Research, 37, pp. 448-456, (2015)
123