Call for Paper - September 2020 Edition
IJCA solicits original research papers for the September 2020 Edition. Last date of manuscript submission is August 20, 2020. Read More

Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2017
Authors:
Ahmad Shaheryar, Xu-Cheng Yin, Waheed Yousuf Ramay
10.5120/ijca2017914249

Ahmad Shaheryar, Xu-Cheng Yin and Waheed Yousuf Ramay. Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines. International Journal of Computer Applications 167(4):37-45, June 2017. BibTeX

@article{10.5120/ijca2017914249,
	author = {Ahmad Shaheryar and Xu-Cheng Yin and Waheed Yousuf Ramay},
	title = {Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines},
	journal = {International Journal of Computer Applications},
	issue_date = {June 2017},
	volume = {167},
	number = {4},
	month = {Jun},
	year = {2017},
	issn = {0975-8887},
	pages = {37-45},
	numpages = {9},
	url = {http://www.ijcaonline.org/archives/volume167/number4/27763-2017914249},
	doi = {10.5120/ijca2017914249},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

Mechanical failures in rotating machinery (e.g. wind turbines, generators, motor-derives etc.) may result in catastrophic failures. Different mechanical faults induce characteristic vibrations in the equipment structure. Online vibration monitoring helps mitigate catastrophic failures through early detection and identification of underlying mechanical faults. However, extracting characteristic vibration features that improve fault classification performance and are robust to various noises in the vibration signals is a challenging task. Various statistical and signal processing-based vibration-features have been proposed in the literature. These vibration-features were devised on the basis of prior knowledge about characteristics of vibration signals from different fault types. Recently, automatic feature extraction through unsupervised learning in deep neural architectures has resulted in state of art performance on image and speech recognition tasks. So, Instead of feature-engineering, we, here, hypothesized that feature learning on raw vibration signal possibly will extract vibration-features that can improve fault identification performance of subsequent classifier. To the purpose, we explored Convolutional Neural Network for unsupervised feature learning on vibration signals and Denoising Auto-Encoder for extracting vibration features that are robust and invariant to the noises in vibration signals. We proposed a Hybrid deep-model consisting of a Multi-channel Convolutional Neural Network followed by a stack of Denoising Auto-Encoders (MCNN-SDAE) with a single classification layer at the top. We compared the fault identification and classification performance of the proposed model with other models employing tradition statistical and signal processing based vibration-features. We validated the performance of all models on a benchmark vibration data collected from an experimental test-rig specifically designed to study vibration characteristics of bearing related faults.

References

  1. Verma, A. and Srivastava, S. 2014. Review on Condition monitoring techniques oil analysis, thermography and vibration analysis. Int. J. Enhanc. Res. Sci. Technol. Eng. 3 (2014), 18–25.
  2. Tandon, N. and Parey, A. 2006. Condition monitoring of rotary machines. Ser. Adv. Manuf. 5 (2006), 151–157.
  3. El-Thalji, I. and Jantunen, E. 2015. A summary of fault modeling and predictive health monitoring of rolling element bearings. Mechanical Systems and Signal Processing. 60-61(2015), 252–272.
  4. Lei, Y.G., Lin J., Zuo, M.J. and He, Z.J. 2014. Condition monitoring and fault diagnosis of planetary gearboxes: a review. Measurement. 48 (2014), 292–305.
  5. Boudiaf, A., Moussaoui, A., Dahane, A. et al. 2016. A Comparative Study of Various Methods of Bearing Faults Diagnosis Using the Case Western Reserve University Data. J. Fail. Anal. and Preven. 16-2 (2016), 271–284.
  6. Kankar, P., Sharma, S.C. and Harsha, S. 2011. Fault diagnosis of ball bearings using machine learning methods. Expert Systems with Applications, 38 (3) (2011), 1876–1886
  7. Weston, J. and Watkins, C. 1998. Multi-class support vector machines. Citeseer
  8. Widodo, A. and Yang, BS. 2007. Support vector machine in machine condition monitoring and fault diagnosis Mechanical Systems and Signal Processing. 21 (6) (2007), 2560–2574.
  9. Kankar, P.K., Sharma, S.C. and Harsha,S.P. 2011. Rolling element bearing fault diagnosis using wavelet transform Neurocomputing, 74 (10) (2011), 1638–1645.
  10. Konar, P. and Chattopadhyay, P. 2011. Bearing fault detection of induction motor using wavelet and Support Vector Machines (SVMs) Appl. Soft Comput., 11 (6) (2011), 4203–4211.
  11. Keskes, H., Braham, A. and Lachiri, Z. 2013. Broken rotor bar diagnosis in induction machines through stationary wavelet packet transform and multiclass wavelet SVM. Electric Power Syst. Res. 97(2013), 151–157.
  12. Liangpei, Huang, Chaowei, et al. 2015. Fault pattern recognition of rolling bearing based on wavelet packet decomposition and BP network Sci. J. Inform. Eng., 67 (1) (2015), 7–13.
  13. Saravanan, N. and Ramachandran, K.I. 2010. Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN). Expert Syst. Appl. 37(2010), 4168–4181.
  14. Bin, G.F., Gao, J.J., Li, X.J., et al. 2012. Early fault diagnosis of rotating machinery based on wavelet packets—empirical mode decomposition feature extraction and neural network Mech. Syst. Signal Process., 27 (1) (2012), 696–711
  15. Yang, B.S., Hwang W.W., Kim D.J., et al. 2005. Condition classification of small reciprocating compressor for refrigerators using artificial neural networks and support vector machines Mechanical Systems and Signal Processing, 19 (2005), 371–390
  16. Ding, Y., Ma, J. and Tian, Y. 2015. Health assessment and fault classification for hydraulic pump based on LR and softmax regression J. Vibroeng., 17 (2015), 1805–1816.
  17. Schmidhuber, J. 2015. Deep learning in neural networks: an overview. Neural Networks. 61(2015), 85–117.
  18. Yu, D., Deng, L., Jang, I., et al. 2011. Deep learning and its applications to signal and information processing. IEEE Signal Processing Magazine, 28(1)(2011), 145–154.
  19. Jia, F., Lei, Y., J. Lin, et al. 2015. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech. Syst. Signal Process. 72–73 (2015), 303–315.
  20. Gan, M., Wang, C. and Zhu, C. 2015. Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings. Mech. Syst. Signal Process., 72–73 (2015), 92–104.
  21. Chen, Z., Li, C. and Sánchez, R.V. 2015. Multi-layer neural network with deep belief network for gearbox fault diagnosis. J. Vibroeng. 17(2015), 2379–2392.
  22. Tamilselvan, P. and Wang, P. 2013. Failure diagnosis using deep belief learning based health state classification. Reliab. Eng. Syst. Saf. 115(2013), 124–135.
  23. Shao, H., Jiang, H., Zhang, X., et al. 2015. Rolling bearing fault diagnosis using an optimization deep belief network. Measurement Science and Technology, 26( 11) (2015), Article ID 115002.
  24. Wong, P.K.., Yang, Z., Vong, C.M., et al. 2014. Real-time fault diagnosis for gas turbine generator systems using extreme learning machine. Neurocomputing . 128(2014), 249–257.
  25. Lei, Y., Jia, F., Zhou, X., et al. 2015. A deep learning-based method for machinery health monitoring with big data. Journal of Mechanical Engineering, 51( 21)(2015), 49–56.
  26. Guo, X., Chen, L. and Shen, C. 2016. Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis, Measurement. 93 ( Nov 2016), 490-502.
  27. Tao, J., Liu, Y. and Yang, D. 2016. Bearing Fault Diagnosis Based on Deep Belief Network and Multisensor Information Fusion. Shock and Vibration. Article ID 9306205.
  28. Loparo, K. A. Case Western Reserve University Bearing Data Center. Available online: http://csegroups.case.edu/bearingdatacenter/home.
  29. Larochelle, H., Bengio, Y., Lourador, J. et al. 2009. Exploring Strategies for Training Deep Neural Networks. J. Mach. Learn. Res. 10(2009), 1–40.
  30. Vincent, P., Larochelle, H., Bengio, Y., et al. June 2008 Extracting and composing robust features with denoising autoencoders. In Proceedings of the ACM International Conference, Helsinki, Finland.
  31. Lecun, Y.L., Bottou, L., Bengio, Y., et al. 1998. Gradient-based learning applied to document recognition. Proc. IEEE. 86 (11) (1998), 2278–2324.
  32. Krizhevsky, A., Sutskever, I. and Hinton G.E. 2012. ImageNet classification with deep convolutional neural networks Adv. Neural Inform. Process. Syst. 25 (2) (2012), 1106–1114.
  33. Sainath, T.N., Kingsbury, B., Saon, G., et al. 2015. Deep convolutional neural networks for large-scale speech tasks. Neural Networks. 64 (2015), 39–48.
  34. Leng, B., Guo, S., Zhang, X., et al. 2015. 3D object retrieval with stacked local convolutional autoencoder. Signal Process.112(2015), 119–128.
  35. Lee, H., Pham, P.T., Yan, L., et al. 2009. Unsupervised feature learning for audio classification using convolutional deep belief networks. Adv. Neural Inform. Process. Syst. (2009), 1096–1104
  36. Chen, X., Xiang, S., Liu, C.L., et al. 2014. Vehicle detection in satellite images by hybrid deep convolutional neural networks. IEEE Geosci. Remote Sens. Lett., 11 (2014).
  37. Vincent, P., Larochelle, H., Lajoie, I., et al. 2010. Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion. J. Mach. Learn. Res.11(3)(2010), 3371–3408.

Keywords

Vibration-features learning, equipment condition monitoring, bearing fault identification, machine learning, online monitoring.