© The Institution of Engineering and Technology
Condition monitoring and fault diagnosis are important for maintaining the system performance and guaranteeing the operational safety. The traditional data-driven approaches mostly incorporate well-defined features and methodologies such as supervised artificial intelligence algorithms. Prior knowledge of possible features and a large quantity of labelled condition data are needed. Besides, many traditional approaches require rebuilding or a retraining of the original model to diagnosis new conditions. The present study proposes an intelligent fault diagnosis approach that uses a deep neural network (DNN) based on stacked denoising autoencoder. Representative features are learned by applying the denoising autoencoder to the unlabelled data in an unsupervised manner. A DNN is then constructed and fine-tuned with just a few items of labelled data. The trained DNN achieves high performance in fault classification. Furthermore, new conditions can be correctly classified by simply fine-tuning the trained DNN model using a small amount of labelled data under the new conditions. The effectiveness of the proposed approach is evaluated using a case study of fault diagnosis of a bearing unit. The results indicate that the proposed method can extract representative features from massive unlabelled data on the system condition and achieve high performance in fault diagnosis.
References
-
-
1)
-
10. Yin, S., Wang, G.: ‘Data-driven design of robust fault detection system for wind turbines’, Mechatronics, 2014, 24, (4), pp. 298–306.
-
2)
-
31. Vincent, P., Larochelle, H., Bengio, Y., et al: ‘Extracting and composing robust features with denoising autoencoders’. Proc. 25th Int. Conf. on Machine Learning, 2008, pp. 1096–1103.
-
3)
-
23. Di lena, P., Nagata, K., Baldi, P.: ‘Deep architectures for protein contact map prediction’, Bioinformatics, 2012, 28, (19), pp. 2449–2457.
-
4)
-
17. Yuan, J., Liu, X.: ‘Semi-supervised learning and condition fusion for fault diagnosis’, Mech. Syst. Signal Process., 2013, 38, (2), pp. 615–627.
-
5)
-
11. Kang, H.-J., Van, M.: ‘Bearing-fault diagnosis using non-local means algorithm and empirical mode decomposition-based feature extraction and two-stage feature selection’, IET Sci. Meas. Technol., 2015, 9, (6), pp. 671–680.
-
6)
-
2. Yoon, J., He, D.: ‘Planetary gearbox fault diagnostic method using acoustic emission sensors’, IET Sci. Meas. Technol., 2015, 9, (8), pp. 936–944.
-
7)
-
30. Hinton, G.E., Salakhutdinov, R.R.: ‘Reducing the dimensionality of data with neural networks’, Science, 2006, 313, (5786), pp. 504–507.
-
8)
-
15. Yan, J., Lu, L.: ‘Improved Hilbert–Huang transform based weak signal detection methodology and its application on incipient fault diagnosis and ECG signal analysis’, Signal Process., 2014, 98, pp. 74–87.
-
9)
-
1. Phillips, P., Diston, D.: ‘A knowledge driven approach to aerospace condition monitoring’, Knowledge Based Syst., 2011, 24, (6), pp. 915–927.
-
10)
-
6. Yin, S., Ding, S.X., Xie, X., et al: ‘A review on basic data-driven approaches for industrial process monitoring’, IEEE Trans. Ind. Electron., 2014, 61, (11), pp. 6418–6428.
-
11)
-
35. ‘Case Western Reserve University Bearing Data Centre Website’, .
-
12)
-
34. Hinton, G.E.: ‘A practical guide to training restricted Boltzmann machines’, in Montavon, G., Orr, G.B., Müller, K.-R. (EDs.): ‘Neural networks: tricks of the trade’ (Springer Berlin Heidelberg, 2012, 2nd edn.), pp. 599–619.
-
13)
-
12. Cococcioni, M., Lazzerini, B., Volpi, S.L.: ‘Robust diagnosis of rolling element bearings based on classification techniques’, IEEE Trans. Ind. Inform., 2013, 9, (4), pp. 2256–2263.
-
14)
-
4. Liu, T.-I., Lee, J., Liu, G., et al: ‘Monitoring and diagnosis of the tapping process for product quality and automated manufacturing’, Int. J. Adv. Manuf. Technol., 2013, 64, (5-8), pp. 1169–1175.
-
15)
-
29. Bengio, Y., Lamblin, P., Popovici, D., et al: ‘Greedy layer-wise training of deep networks’, Adv. Neural Inf. Process. Syst., 2007, 19, (1), p. 153.
-
16)
-
24. Tao, S., Zhang, T., Yang, J., et al: ‘Bearing fault diagnosis method based on stacked autoencoder and softmax regression’. Proc. 34th Chinese Control Conf., 2015, pp. 6331–6335.
-
17)
-
5. Gao, Z., Cecati, C., Ding, S.X.: ‘A survey of fault diagnosis and fault-tolerant techniques – Part I: fault diagnosis with model-based and signal-based approaches’, IEEE Trans. Ind. Electron., 2015, 62, (6), pp. 3757–3767.
-
18)
-
26. Vincent, P., Larochelle, H., Lajoie, I., et al: ‘Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion’, J. Mach. Learn. Res., 2010, 11, (3), pp. 3371–3408.
-
19)
-
25. Jia, F., Lei, Y., Lin, J., et al: ‘Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data’, Mech. Syst. Signal Process., 2015, 73, pp. 303–315.
-
20)
-
22. Graves, A., Mohamed, A., Hinton, G.: ‘Speech recognition with deep recurrent neural networks’. Proc. 2013 IEEE Int. Conf. Acoustics, Speech and Signal Processing, 2013, pp. 6645–6649.
-
21)
-
3. Lu, S., He, Q., Hu, F., et al: ‘Sequential multiscale noise tuning stochastic resonance for train bearing fault diagnosis in an embedded system’, IEEE Trans. Instrum. Meas., 2014, 63, (1), pp. 106–116.
-
22)
-
8. Tobon-Mejia, D.A., Medjaher, K., Zerhouni, N., et al: ‘A data-driven failure prognostics method based on mixture of Gaussians hidden Markov models’, IEEE Trans. Reliab., 2012, 61, (2), pp. 491–503.
-
23)
-
9. Gao, R.X., Chen, X.: ‘Wavelets for fault diagnosis of rotary machines: a review with applications’, Signal Process., 2014, 96, pp. 1–15.
-
24)
-
7. Dai, X., Gao, Z.: ‘From model, signal to knowledge: A data-driven perspective of fault detection and diagnosis’, IEEE Trans. Ind. Inform., 2013, 9, (4), pp. 2226–2238.
-
25)
-
14. Wang, J., He, Q., Kong, F.: ‘Multiscale envelope manifold for enhanced fault diagnosis of rotating machines’, Mech. Syst. Signal Process., 2015, 52, pp. 376–392.
-
26)
-
28. Betechuoh, B.L., Marwala, T., Tettey, T.: ‘Autoencoder networks for HIV classification’, Curr. Sci., 2006, 91, (11), pp. 1467–1473.
-
27)
-
20. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘ImageNet classification with deep convolutional neural networks’, Adv. Neural Inf. Process. Syst., 2012, pp. 1097–1105.
-
28)
-
36. Van Der Maaten, L.J.P., Hinton, G.E.: ‘Visualizing high-dimensional data using t-SNE’, J. Mach. Learn. Res., 2008, 9, pp. 2579–2605.
-
29)
-
33. D'Ambrosio, R., Iannello, G., Soda, P.: ‘Softmax regression for ECOC reconstruction’. Int. Conf. Image Analysis and Processing, 2013, pp. 682–691.
-
30)
-
18. LeCun, Y., Bengio, Y., Hinton, G.: ‘Deep learning’, Nature, 2015, 521, (7553), pp. 436–444.
-
31)
-
32. Feng, X., Zhang, Y., Glass, J.: ‘Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition’. Proc. 2014 IEEE Int. Conf. Acoustics, Speech and Signal Processing, 2014, pp. 1759–1763.
-
32)
-
16. Amarnath, M., Praveen Krishna, I.R.: ‘Empirical mode decomposition of acoustic signals for diagnosis of faults in gears and rolling element bearings’, IET Sci. Meas. Technol., 2012, 6, (4), p. 279.
-
33)
-
19. Schmidhuber, J.: ‘Deep Learning in neural networks: an overview’, Neural Netw., 2015, 61, pp. 85–117.
-
34)
-
13. Meeker, W.Q., Hong, Y.L.: ‘Reliability meets big data: opportunities and challenges’, Qual. Eng., 2014, 26, (1), pp. 102–116.
-
35)
-
21. Collobert, R., Weston, J.: ‘A unified architecture for natural language processing: deep neural networks with multitask learning’. Proc. 25th Int. Conf. Machine Learning, 2008, pp. 160–167.
-
36)
-
27. Le, Q.V.: ‘Building high-level features using large scale unsupervised learning’. Proc. 2013 IEEE Int. Conf. Acoustics, Speech and Signal Processing, 2013, pp. 8595–8598.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-smt.2016.0423
Related content
content/journals/10.1049/iet-smt.2016.0423
pub_keyword,iet_inspecKeyword,pub_concept
6
6