Skip to main content
Top
Published in: Chinese Journal of Mechanical Engineering 6/2017

01-11-2017 | Original Article

Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network

Authors: Li-Hua Wang, Xiao-Ping Zhao, Jia-Xin Wu, Yang-Yang Xie, Yong-Hong Zhang

Published in: Chinese Journal of Mechanical Engineering | Issue 6/2017

Login to get access

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

With the rapid development of mechanical equipment, the mechanical health monitoring field has entered the era of big data. However, the method of manual feature extraction has the disadvantages of low efficiency and poor accuracy, when handling big data. In this study, the research object was the asynchronous motor in the drivetrain diagnostics simulator system. The vibration signals of different fault motors were collected. The raw signal was pretreated using short time Fourier transform (STFT) to obtain the corresponding time-frequency map. Then, the feature of the time-frequency map was adaptively extracted by using a convolutional neural network (CNN). The effects of the pretreatment method, and the hyper parameters of network diagnostic accuracy, were investigated experimentally. The experimental results showed that the influence of the preprocessing method is small, and that the batch-size is the main factor affecting accuracy and training efficiency. By investigating feature visualization, it was shown that, in the case of big data, the extracted CNN features can represent complex mapping relationships between signal and health status, and can also overcome the prior knowledge and engineering experience requirement for feature extraction, which is used by traditional diagnosis methods. This paper proposes a new method, based on STFT and CNN, which can complete motor fault diagnosis tasks more intelligently and accurately.
Literature
1.
go back to reference Chuan Li, R V Sanchez, G Zurita, et al. Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals. Mechanical Systems and Signal Processing, 2016, 76–77: 283–293. Chuan Li, R V Sanchez, G Zurita, et al. Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals. Mechanical Systems and Signal Processing, 2016, 76–77: 283–293.
2.
go back to reference Ya-Guo Lei, Nai-Peng Li, Jing Lin, et al. Two new features for condition monitoring and fault diagnosis of planetary gearboxes. Journal of Vibration & Control, 2013, 21(4): 755–764. Ya-Guo Lei, Nai-Peng Li, Jing Lin, et al. Two new features for condition monitoring and fault diagnosis of planetary gearboxes. Journal of Vibration & Control, 2013, 21(4): 755–764.
3.
go back to reference Jun-Jian Hou, Wei-Kang Jiang, Wen-Bo Lu. Application of a near-field acoustic holography-based diagnosis technique in gearbox fault diagnosis. Journal of Vibration & Control, 2013, 19(1): 3–13. Jun-Jian Hou, Wei-Kang Jiang, Wen-Bo Lu. Application of a near-field acoustic holography-based diagnosis technique in gearbox fault diagnosis. Journal of Vibration & Control, 2013, 19(1): 3–13.
4.
go back to reference A M D Younus, B S Yang. Intelligent fault diagnosis of rotating machinery using infrared thermal image. Expert Systems with Applications, 2012, 39(2): 2082–2091. A M D Younus, B S Yang. Intelligent fault diagnosis of rotating machinery using infrared thermal image. Expert Systems with Applications, 2012, 39(2): 2082–2091.
5.
go back to reference J. R Ottewill, M Orkisz. Condition monitoring of gearboxes using synchronously averaged electric motor signals. Mechanical Systems & Signal Processing, 2013, 38(2): 482–498. J. R Ottewill, M Orkisz. Condition monitoring of gearboxes using synchronously averaged electric motor signals. Mechanical Systems & Signal Processing, 2013, 38(2): 482–498.
6.
go back to reference A Contin, S D’orlando, G Fenu, et al. Experiments on actuator fault diagnosis: the case of a nonlinearly controlled AC motor. Control Conference, 2015: 2747–2752. A Contin, S D’orlando, G Fenu, et al. Experiments on actuator fault diagnosis: the case of a nonlinearly controlled AC motor. Control Conference, 2015: 2747–2752.
7.
go back to reference A Glowacz. DC motor fault analysis with the use of acoustic signals, Coiflet wavelet transform, and K-nearest neighbor classifier. Archives of Acoustics, 2015, 40(3): 321–327. A Glowacz. DC motor fault analysis with the use of acoustic signals, Coiflet wavelet transform, and K-nearest neighbor classifier. Archives of Acoustics, 2015, 40(3): 321–327.
8.
go back to reference Hui-Min Zhao, Cai-Hua Fang, Deng Wu. Research on motor fault diagnosis model for support vector machine based on Intelligent optimization methods. Journal of Dalian Jiaotong University, 2016, 37(1): 92–96. (in Chinese). Hui-Min Zhao, Cai-Hua Fang, Deng Wu. Research on motor fault diagnosis model for support vector machine based on Intelligent optimization methods. Journal of Dalian Jiaotong University, 2016, 37(1): 92–96. (in Chinese).
9.
go back to reference Ping Li, Xue-Jun Li, Ling-Li Jiang, et al. Fault diagnosis of asynchronous motor based on KPCA and PSOSVM. Journal of Vibration Measurement & Diagnosis, 2014, 34(4): 616–620. (in Chinese). Ping Li, Xue-Jun Li, Ling-Li Jiang, et al. Fault diagnosis of asynchronous motor based on KPCA and PSOSVM. Journal of Vibration Measurement & Diagnosis, 2014, 34(4): 616–620. (in Chinese).
10.
go back to reference D H Pandya, S H Upadhyay, S P Harsha. Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform. Soft Computing, 2014, 18(2): 255–266. D H Pandya, S H Upadhyay, S P Harsha. Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform. Soft Computing, 2014, 18(2): 255–266.
11.
go back to reference M Khazaee, H Ahmadi, M Omid, et al. Classifier fusion of vibration and acoustic signals for fault diagnosis and classification of planetary gears based on dempster-shafer evidence theory. ARCHIVE Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering, 2014, 228(1): 21–32. M Khazaee, H Ahmadi, M Omid, et al. Classifier fusion of vibration and acoustic signals for fault diagnosis and classification of planetary gears based on dempster-shafer evidence theory. ARCHIVE Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering, 2014, 228(1): 21–32.
12.
go back to reference G E Hinton, S Osindero, Y W Teh. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527–1554. G E Hinton, S Osindero, Y W Teh. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527–1554.
13.
go back to reference G Hinton, Deng Li, Yu Dong, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of fourresearch groups. IEEE Signal Processing Magazine, 2012, 29(6): 82–97. G Hinton, Deng Li, Yu Dong, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of fourresearch groups. IEEE Signal Processing Magazine, 2012, 29(6): 82–97.
14.
go back to reference A Krizhevsky, I Sutskever, G E Hinton. Imagenet classification with deep convolutional neural networks. International Conference on Neural Information Processing Systems, 2012, 25(2): 1097–1105. A Krizhevsky, I Sutskever, G E Hinton. Imagenet classification with deep convolutional neural networks. International Conference on Neural Information Processing Systems, 2012, 25(2): 1097–1105.
15.
go back to reference Yan-Feng Li, Xin-Qing Wang, Mei-Jun Zhang, et al. An approach to fault diagnosis of rolling bearing using SVD and multiple DBN classifiers. Journal of Shanghai Jiaotong University, 2015, 49(5): 681–686. (in Chinese). Yan-Feng Li, Xin-Qing Wang, Mei-Jun Zhang, et al. An approach to fault diagnosis of rolling bearing using SVD and multiple DBN classifiers. Journal of Shanghai Jiaotong University, 2015, 49(5): 681–686. (in Chinese).
16.
go back to reference Jia Feng, Ya-Guo Lei, Jing Lin, et al. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems & Signal Processing, 2016, 72–73: 303–315. Jia Feng, Ya-Guo Lei, Jing Lin, et al. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems & Signal Processing, 2016, 72–73: 303–315.
17.
go back to reference I Arel, D C Rose, T P Karnowski. Research frontier: deep machine learning–a new frontier in artificial intelligence research. IEEE Computational Intelligence Magazine, 2010, 5(4): 13–18. I Arel, D C Rose, T P Karnowski. Research frontier: deep machine learning–a new frontier in artificial intelligence research. IEEE Computational Intelligence Magazine, 2010, 5(4): 13–18.
18.
go back to reference P Tamilselvan, Ping-Peng Wang. Failure diagnosis using deep belief learning based health state classification. Reliability Engineering & Systems Safety, 2013, 115(7): 124–135. P Tamilselvan, Ping-Peng Wang. Failure diagnosis using deep belief learning based health state classification. Reliability Engineering & Systems Safety, 2013, 115(7): 124–135.
19.
go back to reference P Vincent, H Larochelle, I Lajoie, et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 2010, 11(12): 3371–3408. P Vincent, H Larochelle, I Lajoie, et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 2010, 11(12): 3371–3408.
20.
go back to reference Zhao-Feng Zhang, Long-Biao Wang, A Kai, et al. Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification. Eurasip Journal on Audio, Speech, and Music Processing, 2015, 2015(1): 1–13. Zhao-Feng Zhang, Long-Biao Wang, A Kai, et al. Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification. Eurasip Journal on Audio, Speech, and Music Processing, 2015, 2015(1): 1–13.
21.
go back to reference Chen Lu, Zhen-Ya Wang, Wei-Li Qin, et al. Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification. Signal Processing, 2017, 130: 377–388. Chen Lu, Zhen-Ya Wang, Wei-Li Qin, et al. Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification. Signal Processing, 2017, 130: 377–388.
22.
go back to reference S H Nawab, T F Quatieri. Short-time fourier transform. Advanced Topics in Signal Processing, 1988, 32(2): 289–337. S H Nawab, T F Quatieri. Short-time fourier transform. Advanced Topics in Signal Processing, 1988, 32(2): 289–337.
23.
go back to reference S Lawrence, C L Giles, A C Tsoi, et al. Face recognition: a convolutional neural-network approach. IEEE Transactions on Neural Networks, 1997, 8(1): 98–113. S Lawrence, C L Giles, A C Tsoi, et al. Face recognition: a convolutional neural-network approach. IEEE Transactions on Neural Networks, 1997, 8(1): 98–113.
24.
go back to reference Wei-Yang Liu, Yan-Dong Wen, Zhi-Ding Wen, et al. Large-margin softmax loss for convolutional neural networks. International Conference on International Conference on Machine Learning, 2016: 507–516. Wei-Yang Liu, Yan-Dong Wen, Zhi-Ding Wen, et al. Large-margin softmax loss for convolutional neural networks. International Conference on International Conference on Machine Learning, 2016: 507–516.
25.
go back to reference D Erhan, Y Bengio, A Courville, et al. Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research, 2010, 11(3): 625–660. D Erhan, Y Bengio, A Courville, et al. Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research, 2010, 11(3): 625–660.
26.
go back to reference I Daubechies. The wavelet transform, time-frequency localisation and signal analysis. IEEE Transactions on Information Theory, 1990, 36(5): 961–1005. I Daubechies. The wavelet transform, time-frequency localisation and signal analysis. IEEE Transactions on Information Theory, 1990, 36(5): 961–1005.
27.
go back to reference S Ioffe, C Szegedy. Batch normalization: accelerating deep network training by reducing internal covariate shift. Computer Science, 2015: 448–456. S Ioffe, C Szegedy. Batch normalization: accelerating deep network training by reducing internal covariate shift. Computer Science, 2015: 448–456.
28.
go back to reference P Ahlgren, B Jarneving, P B R Ahlgren. Requirements for a cocitation similarity measure, with special reference to Pearson’s correlation coefficient. Journal of the American Society for Information Science & Technology, 2003, 54(6): 550–560. P Ahlgren, B Jarneving, P B R Ahlgren. Requirements for a cocitation similarity measure, with special reference to Pearson’s correlation coefficient. Journal of the American Society for Information Science & Technology, 2003, 54(6): 550–560.
29.
go back to reference Shu-Fang Li, Wei-Dong Zhou, Qi Yuan, et al. Feature extraction and recognition of ictal EEG using EMD and SVM. Computers in Biology & Medicine, 2013, 43(7): 807–816. Shu-Fang Li, Wei-Dong Zhou, Qi Yuan, et al. Feature extraction and recognition of ictal EEG using EMD and SVM. Computers in Biology & Medicine, 2013, 43(7): 807–816.
30.
go back to reference Neng Ren. PCA-SVM-based automated fault detection and diagnosis (AFDD) for vapor-compression refrigeration systems. Hvac & R Research, 2010, 16(3): 295–313. Neng Ren. PCA-SVM-based automated fault detection and diagnosis (AFDD) for vapor-compression refrigeration systems. Hvac & R Research, 2010, 16(3): 295–313.
Metadata
Title
Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network
Authors
Li-Hua Wang
Xiao-Ping Zhao
Jia-Xin Wu
Yang-Yang Xie
Yong-Hong Zhang
Publication date
01-11-2017
Publisher
Chinese Mechanical Engineering Society
Published in
Chinese Journal of Mechanical Engineering / Issue 6/2017
Print ISSN: 1000-9345
Electronic ISSN: 2192-8258
DOI
https://doi.org/10.1007/s10033-017-0190-5

Other articles of this Issue 6/2017

Chinese Journal of Mechanical Engineering 6/2017 Go to the issue

Premium Partners