Unsupervised Deep Learning for Gear Health Monitoring



Published Oct 2, 2017
Tyler Cody Stephen Adams Peter A. Beling


Deep learning has revolutionized many fields in recent years by replacing expert-designed, handcrafted features with learned representations. Gear health monitoring is a field where expert-designed features are heavily used for predictive modeling. This paper investigates how unsupervised
deep learning can be applied to gear health monitoring to make predictions on low frequency scales using high frequency data given small, sparsely labeled data sets. Deep convolutional autoencoders are trained and used to generate learned features. The learned features are compared with relevant handcrafted features via their performance in training machine learning models to predict discrete gear fatigue states. The learned features performed poorly against the handcrafted features, however models trained on feature sets tended to outperform those exclusively trained on handcrafted features. The top performing model was a multi-layer perceptron trained on both feature sets that leveraged the ability of the condition indicators to represent healthy and failure states and the ability of the learned features to represent the intermediate worn state. This work demonstrates that unsupervised deep learning techniques can be used to bolster the performance of handcrafted features in small, sparsely labeled data sets in gear health monitoring.

How to Cite

Cody, T., Adams, S., & Beling, P. A. (2017). Unsupervised Deep Learning for Gear Health Monitoring. Annual Conference of the PHM Society, 9(1). https://doi.org/10.36001/phmconf.2017.v9i1.2429
Abstract 276 | PDF Downloads 150



deep learning, autoencoders, gear health

Appearance of gear teeth - terminology of wear and failure (No. ANSI/AGMA 1010-E95). (2014). AGMA Nomenclature Committee, American Gear Manufacturers Association.
Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35(8), 1798–1828.
Cho, K., Van Merri¨enboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoderdecoder for statistical machine translation. arXiv preprint arXiv:1406.1078.
Chollet, F., et al. (2015). Keras. Collobert, R., & Weston, J. (2008). A unified architecture for natural language processing: Deep neural networks
with multitask learning. In Proceedings of the 25th international conference on machine learning (pp. 160–167).
Dempsey, P. J. (2014). Investigation of spiral bevel gear indicator validation via ac-29-2c using test rig damage progression test data (Tech. Rep. No. TM-2014-218384). NASA.
Geng, J., Fan, J.,Wang, H., Ma, X., Li, B., & Chen, F. (2015). High-resolution sar image classification via deep convolutional autoencoders. IEEE Geoscience and Remote Sensing Letters, 12(11), 2351–2355.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Handschuch, R. F. (1995). Thermal behavior of spiral bevel gears (Tech. Rep. No. TM-106518). NASA.
Handschuch, R. F. (2001). Testing of face-milled spiral bevel gears at high-speed and load (Tech. Rep. No. TM-2001-210743). NASA.
Janssens, O., Slavkovikj, V., Vervisch, B., Stockman, K., Loccufier, M., Verstockt, S., . . . Van Hoecke, S. (2016). Convolutional neural network based fault detection for rotating machinery. Journal of Sound and Vibration, 377, 331–345.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097–1105).
LeCun, Y., & Bengio, Y. (1995). Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361(10), 1995.
Martin, H. R. (1989). Statistical moment analysis as a means of surface damage detection. In Proceedings of the 7th international modal analysis conference.
Masci, J., Meier, U., Cires¸an, D., & Schmidhuber, J. (2011). Stacked convolutional auto-encoders for hierarchical feature extraction. Artificial Neural Networks and Machine Learning–ICANN 2011, 52–59.
Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10), 1345–1359.
Saxe, A., Koh, P.W., Chen, Z., Bhand, M., Suresh, B., & Ng, A. Y. (2011). On random weights and unsupervised feature learning. In Proceedings of the 28th international conference on machine learning (icml-11) (pp. 1089–1096).
Stewart, R. M. (1977). Some useful data analysis techniques for gearbox diagnostics (Tech. Rep. No. Report MHM/R/10/77). Machine Health Monitoring Group, Institute of Sound and Vibration Research, University of Southampton.
Townsend, D. P. (Ed.). (1991). Dudley’s gear handbook. McGraw-Hill.
Vevcevr, P., Kreidl, M., & Smid, R. (2005). Condition indicators for gearbox condition monitoring systems. Acta Polytechnica, 45(6).
Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008). Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th international conference on machine learning (pp. 1096–1103).
Technical Research Papers