Abstract
This paper presents a method for machine component supervision with little to none prior knowledge of the machine, operating conditions and wear behavior. A hybrid approach based on unsupervised learning methods, consisting of an autoencoder network and clustering, to identify machine states and possible failure preceding anomalies is proposed. In order to cope with information sparsity, the model parameters of the unsupervised methods are derived automatically based on data distribution and a physical motivation. The approach was validated on a dataset of artificially introduced bearing faults. The gained clustering results show a general usability of the approach for condition monitoring with vibration data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Celebi, M.E., Aydin, K.: Unsupervised Learning Algorithms. Springer, Cham (2016)
Bishop, C.M.: Pattern Recognition and Machine Learning Information Science and Statistics. Springer, New York (2009)
Seif, G.: An easy introduction to unsupervised learning with 4 basic techniques. https://towardsdatascience.com/an-easy-introduction-to-unsupervised-learning-with-4-basic-techniques-da7fbf0c3adf (2019). Accessed 15 May 2020
Ballard, D.H.: Modular learning in neural networks. In: AAAI (ed.) Sixth National Conference on Artificial Intelligence, vol. 1, pp. 279–284. Los Altos, California (1987)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Mathworks Train Autoencoders: https://de.mathworks.com/help/deeplearning/ref/trainautoencoder.html. Accessed 18 Apr 2020
Ng, A., Ngiam, J., Foo, C.Y., et al. UFLDL Tutorial – Autoencoders: https://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/. Accessed 18 Apr 2020
Roy, M., Bose, S.K., Kar, B., et al.: A stacked autoencoder neural network based automated feature extraction method for anomaly detection in on-line condition moni-toring. In: IEEE (ed.) Symposium Series on Computational Intelligence (SSCI), pp. 1501–1507 (2018)
Marchi, E., Vesperini, F., Eyben, F., et al.: A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks. In: IEEE (ed.) International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1996–2000 (2015)
Madiraju, N.S., Sadat, S.M., Fisher, D., et al.: Deep temporal clustering: fully unsu-pervised learning of time-domain features. https://arxiv.org/abs/1802.01059 (2018)
Michau, G., Fink, O., Hu, Y., et al.: Feature learning for fault detection in high dimen-sional condition monitoring signals. J. Risk Reliab. 234(1), 104–115 (2019). 10.1177/1748006X19868335
Zhang, S., Ye, F., Wang, B., et al.: Semi-supervised learning of bearing anomaly detection via deep variational autoencoders. https://arxiv.org/pdf/1912.01096.pdf (2019)
Meng, Z., Zhan, X., Li, J., et al.: An enhancement denoising autoencoder for rolling bearing fault diagnosis. Measurement 130, 448–454 (2018). 10.1016/j.measurement.2018.08.010
Ren, L., Sun, Y., Cui, J., et al.: Bearing remaining useful life prediction based on deep autoencoder and deep neural networks. J. Manuf. Syst. 48, 71–77 (2018). 10.1016/j.jmsy.2018.04.008
Sohaib, M., Kim, J.M.: Reliable fault diagnosis of rotary machine bearings using a stacked sparse autoencoder-based deep neural network. Shock Vib. 2018, 1–11 (2018). 10.1155/2018/2919637
Borghesi, A., Bartolini, A., Lombardi, M., et al.: Anomaly detection using autoencod-ers in high performance computing systems. In: AAAI Conference on Innovative Applications (2019)
Wen, Q., Sun, L., Song, X., et al.: Time series data augmentation for deep learning: a survey. https://arxiv.org/pdf/2002.12478v1(2020)
Ester, M., Kriegel, H-P, Sander, J., et al.: A density-based algorithm for discovering clusters in large spatial databases with noise (1996)
Fukunaga, K., Hostetler, L.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inform. Theory 21(1), 32–40 (1975). 10.1109/TIT.1975.1055330
Ankerst, M., Breunig, M.M., Kriegel, H.P., et al.: OPTICS: Ordering points to identify the clustering structure. SIGMOD Rec. 28(2), 49–60 (1999). 10.1145/304181.304187
Mathworks: Estimate neighborhood threshold: DBSCAN. Phased array system toolbox. https://de.mathworks.com/help/phased/ref/clusterdbscan.clusterdbscan.estimateepsilon.html. (2020). Accessed 25 Apr 2020
Case Western Reserve University Bearing Data Center: https://csegroups.case.edu/bearingdatacenter/home. Accessed 20 Apr 2020
Acknowledgement
This research work is funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Project 388141462.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer-Verlag GmbH, DE , part of Springer Nature
About this paper
Cite this paper
Hillenbrand, J., Fleischer, J. (2021). Autoconfiguration of a Vibration-Based Anomaly Detection System with Sparse a-priori Knowledge Using Autoencoder Networks. In: Behrens, BA., Brosius, A., Hintze, W., Ihlenfeldt, S., Wulfsberg, J.P. (eds) Production at the leading edge of technology. WGP 2020. Lecture Notes in Production Engineering. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-62138-7_52
Download citation
DOI: https://doi.org/10.1007/978-3-662-62138-7_52
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-62137-0
Online ISBN: 978-3-662-62138-7
eBook Packages: EngineeringEngineering (R0)