Long short-term memory based semi-supervised encoder– decoder for early prediction of failures in self-lubricating bearings

Vigneashwara PANDIYAN; Mehdi AKEDDAR; Josef PROST; Georg VORLAUFER; Markus VARGA; Kilian WASMER

doi:10.1007/s40544-021-0584-3

Friction 2023, 11(1): 109-124 https://doi.org/10.1007/s40544-021-0584-3

Research Article |

Open Access | Issue | Published: 28 April 2022

Long short-term memory based semi-supervised encoder– decoder for early prediction of failures in self-lubricating bearings

Show Author's Information Hide Author's Information Vigneashwara PANDIYAN^¹(

), Mehdi AKEDDAR^¹, Josef PROST^², Georg VORLAUFER^², Markus VARGA^², Kilian WASMER^¹

1 Laboratory for Advanced Materials Processing (LAMP), Swiss Federal Laboratories for Materials Science and Technology (Empa), Thun CH-3602, Switzerland

2 AC2T research GmbH, Wiener Neustadt 2700, Austria

Keywords:

long short-term memory (LSTM), tribology, predictive maintenance, in-situ sensing, encoder–decoder, wear monitoring

Cite this article:

PANDIYAN V, AKEDDAR M, PROST J, et al. Long short-term memory based semi-supervised encoder– decoder for early prediction of failures in self-lubricating bearings. Friction, 2023, 11(1): 109-124. https://doi.org/10.1007/s40544-021-0584-3

Download citation

EndNote(RIS)

BibTeX

506

Views

Downloads

Citations

Crossref

WoS

Scopus

CSCD

Abstract Full text About this article

Abstract

The existing knowledge regarding the interfacial forces, lubrication, and wear of bearings in real-world operation has significantly improved their designs over time, allowing for prolonged service life. As a result, self-lubricating bearings have become a viable alternative to traditional bearing designs in industrial machines. However, wear mechanisms are still inevitable and occur progressively in self-lubricating bearings, as characterized by the loss of the lubrication film and seizure. Therefore, monitoring the stages of the wear states in these components will help to impart the necessary countermeasures to reduce the machine maintenance downtime. This article proposes a methodology for using a long short-term memory (LSTM)-based encoder– decoder architecture on interfacial force signatures to detect abnormal regimes, aiming to provide early predictions of failure in self-lubricating sliding contacts even before they occur. Reciprocating sliding experiments were performed using a self-lubricating bronze bushing and steel shaft journal in a custom-built transversally oscillating tribometer setup. The force signatures corresponding to each cycle of the reciprocating sliding motion in the normal regime were used as inputs to train the encoder–decoder architecture, so as to reconstruct any new signal of the normal regime with the minimum error. With this semi-supervised training exercise, the force signatures corresponding to the abnormal regime could be differentiated from the normal regime, as their reconstruction errors would be very high. During the validation procedure for the proposed LSTM-based encoder–decoder model, the model predicted the force signals corresponding to the normal and abnormal regimes with an accuracy of 97%. In addition, a visualization of the reconstruction error across the entire force signature showed noticeable patterns in the reconstruction error when temporally decoded before the actual critical failure point, making it possible to be used for early predictions of failure.

Full text

Abstract

Full text

Outline

About this article

Long short-term memory based semi-supervised encoder– decoder for early prediction of failures in self-lubricating bearings

Show Author's information Hide Author's Information Vigneashwara PANDIYAN^¹(

), Mehdi AKEDDAR^¹, Josef PROST^², Georg VORLAUFER^², Markus VARGA^², Kilian WASMER^¹

1 Laboratory for Advanced Materials Processing (LAMP), Swiss Federal Laboratories for Materials Science and Technology (Empa), Thun CH-3602, Switzerland

2 AC2T research GmbH, Wiener Neustadt 2700, Austria

Abstract

Keywords: long short-term memory (LSTM), tribology, predictive maintenance, in-situ sensing, encoder–decoder, wear monitoring

References(58)

[1]

Mobley R K. An Introduction to Predictive Maintenance. Woburn (USA): Elsevier Inc., 2002.

DOI

[2]

Swanson L. Linking maintenance strategies to performance. Int J Prod Econ 70(3): 237–244 (2001)

DOI Google Scholar

[3]

Durocher D B, Feldmeier G R. Predictive versus preventive maintenance. IEEE Ind Appl Mag 10(5): 12–21 (2004)

DOI Google Scholar

[4]

Carnero M C. Selection of diagnostic techniques and instrumentation in a predictive maintenance program. A case study. Decis Support Syst 38(4): 539–555 (2005)

DOI Google Scholar

[5]

McKone K E, Weiss E N. Guidelines for implementing predictive maintenance. Prod Oper Manag 11(2): 109–124 (2002)

DOI Google Scholar

[6]

Daily J, Peterson J. Predictive maintenance: How big data analysis can improve maintenance. In: Supply Chain Integration Challenges in Commercial Aerospace. Richter K, Walther J, Eds. Cham (Switzerland): Springer, Cham, 2017: 267–278.

DOI

[7]

Selcuk S. Predictive maintenance, its implementation and latest trends. Proc Inst Mech Eng B: J Eng Manuf 231(9): 1670–1679 (2017)

DOI Google Scholar

[8]

Lu B, Durocher D B, Stemper P. Predictive maintenance techniques. IEEE Ind Appl Mag 15(6): 52–60 (2009)

DOI Google Scholar

[9]

Meng Y G, Xu J, Jin Z M, Prakash B, Hu Y Z. A review of recent advances in tribology. Friction 8(2): 221–300 (2020)

DOI Google Scholar

[10]

Evans D C. Self-lubricating bearings. Ind Lubr Tribol 33(4): 132–138 (1981)

DOI Google Scholar

[11]

Gawarkiewicz R, Wasilczuk M. Wear measurements of self-lubricating bearing materials in small oscillatory movement. Wear 263(1–6): 458–462 (2007)

DOI Google Scholar

[12]

Ren Y L, Zhang L, Xie G X, Li Z B, Chen H, Gong H J, Xu W H, Guo D, Luo J B. A review on tribology of polymer composite coatings. Friction 9(3): 429–470 (2021)

DOI Google Scholar

[13]

Paxton R R. Manufactured Carbon: A Self-Lubricating Material for Mechanical Devices. Boca Raton (USA): CRC Press, 2017.

[14]

Bhushan B. Modern Tribology Handbook, Two Volume Set. Boca Raton (USA): CRC Press, 2000.

DOI

[15]

Duan C J, He R, Li S, Shao M C, Yang R, Tao L M, Wang C, Yuan P, Wang T M, Wang Q H. Exploring the friction and wear behaviors of Ag–Mo hybrid modified thermosetting polyimide composites at high temperature. Friction 8(5): 893–904 (2020)

DOI Google Scholar

[16]

Lancaster J K. Composite self-lubricating bearing materials. Proc Inst Mech Eng 182(1): 33–54 (1967)

DOI Google Scholar

[17]

Xiang D H, Shan K L. Friction and wear behavior of self- lubricating and heavily loaded metal–PTFE composites. Wear 260(9–10): 1112–1118 (2006)

DOI Google Scholar

[18]

Konstantinos K. Tribology and condition monitoring of composite bearing liners for intelligent aerospace bearings. Ph.D. Thesis. Cardiff (UK): Cardiff University, 2018.

[19]

Deshpande P, Pandiyan V, Meylan B, Wasmer K. Acoustic emission and machine learning based classification of wear generated using a pin-on-disc tribometer equipped with a digital holographic microscope. Wear 476: 203622 (2021)

DOI Google Scholar

[20]

Meylan B, Dogan P, Sage D, Wasmer K. A simple, fast and low-cost method for in situ monitoring of topographical changes and wear rate of a complex tribo-system under mixed lubrication. Wear 364–365: 22–30 (2016)

DOI Google Scholar

[21]

Markus V, Reinhard G, Alexander M, Martin K. Online wear measurement in harsh environment. Part 1: Possible measurement strategies. Tribologie und Schmierungstechnik 66(4–5): 28–34 (2019) (in German)

Google Scholar

[22]

Markus V, Reinhard G, Alexander M, Martin K. Online wear measurement in harsh environment. Part 2: Application roller press. Tribologie und Schmierungstechnik 66(4–5): 35–43 (2019) (in German)

Google Scholar

[23]

Vakharia V, Gupta V K, Kankar P K. Ball bearing fault diagnosis using supervised and unsupervised machine learning methods. Int J Acoust Vib 20(4): 244–250 (2015)

DOI Google Scholar

[24]

Orhan S, Aktürk N, Çelik V. Vibration monitoring for defect diagnosis of rolling element bearings as a predictive maintenance tool: Comprehensive case studies. NDT E Int 39(4): 293–298 (2006)

DOI Google Scholar

[25]

Prieto M D, Cirrincione G, Espinosa A G, Ortega J A, Henao H. Bearing fault detection by a novel condition-monitoring scheme based on statistical-time features and neural networks. IEEE Trans Ind Electron 60(8): 3398–3407 (2013)

DOI Google Scholar

[26]

Sadegh H, Mehdi A N, Mehdi A. Classification of acoustic emission signals generated from journal bearing at different lubrication conditions based on wavelet analysis in combination with artificial neural network and genetic algorithm. Tribol Int 95: 426–434 (2016)

DOI Google Scholar

[27]

König F, Sous C, Ouald Chaib A, Jacobs G. Machine learning based anomaly detection and classification of acoustic emission events for wear monitoring in sliding bearing systems. Tribol Int 155: 106811 (2021)

DOI Google Scholar

[28]

Elforjani M, Shanbr S. Prognosis of bearing acoustic emission signals using supervised machine learning. IEEE Trans Ind Electron 65(7): 5864–5871 (2018)

DOI Google Scholar

[29]

Glowacz A, Tadeusiewicz R, Legutko S, Caesarendra W, Irfan M, Liu H, Brumercik F, Gutten M, Sulowicz M, Antonino Daviu J A, et al. Fault diagnosis of angle grinders and electric impact drills using acoustic signals. Appl Acoust 179: 108070 (2021)

DOI Google Scholar

[30]

Moder J, Bergmann P, Grün F. Lubrication regime classification of hydrodynamic journal bearings by machine learning using torque data. Lubricants 6(4): 108 (2018)

DOI Google Scholar

[31]

Prost J, Cihak-Bayr U, Neacşu I A, Grundtner R, Pirker F, Vorlaufer G. Semi-supervised classification of the state of operation in self-lubricating journal bearings using a random forest classifier. Lubricants 9(5): 50 (2021)

DOI Google Scholar

[32]

Mokhtari N, Pelham J G, Nowoisky S, Bote-Garcia J L, Gühmann C. Friction and wear monitoring methods for journal bearings of geared turbofans based on acoustic emission signals and machine learning. Lubricants 8(3): 29 (2020)

DOI Google Scholar

[33]

Kankar P K, Sharma S C, Harsha S P. Fault diagnosis of ball bearings using machine learning methods. Expert Syst Appl 38(3): 1876–1886 (2011)

DOI Google Scholar

[34]

Caesarendra W, Tjahjowidodo T. A review of feature extraction methods in vibration-based condition monitoring and its application for degradation trend estimation of low-speed slew bearing. Machines 5(4): 21 (2017)

DOI Google Scholar

[35]

Zhao B, Zhang X M, Zhan Z H, Wu Q Q. A robust construction of normalized CNN for online intelligent condition monitoring of rolling bearings considering variable working conditions and sources. Measurement 174: 108973 (2021)

DOI Google Scholar

[36]

Eren L, Ince T, Kiranyaz S. A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier. J Signal Process Syst 91(2): 179–189 (2019)

DOI Google Scholar

[37]

Wang D C, Guo Q W, Song Y, Gao S Y, Li Y B. Application of multiscale learning neural network based on CNN in bearing fault diagnosis. J Signal Process Syst 91(10): 1205–1217 (2019)

DOI Google Scholar

[38]

Narendiranath Babu T, Aravind A, Rakesh A, Jahzan M, Prabha R D, Ramalinga Viswanathan M. Automatic fault classification for journal bearings using ANN and DNN. Archives of Acoustics 43(4): 727–738 (2018)

Google Scholar

[39]

Glowacz A. Ventilation diagnosis of angle grinder using thermal imaging. Sensors 21(8): 2853 (2021)

DOI Google Scholar

[40]

Glowacz A. Fault diagnosis of electric impact drills using thermal imaging. Measurement 171: 108815 (2021)

DOI Google Scholar

[41]

Lee K, Kim J K, Kim J, Hur K, Kim H. CNN and GRU combination scheme for bearing anomaly detection in rotating machinery health monitoring. In: Proceedings of the 1st IEEE International Conference on Knowledge Innovation and Invention, Jeju, Republic of Korea, 2018: 102–105.

DOI

[42]

Mandic D P, Chambers J A. Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability. Chichester (UK): John Wiley & Sons, Ltd, 2001.

DOI

[43]

Bullinaria J A. Recurrent neural networks. Available on http://www.cs.bham.ac.uk/~jxb/INC/l12.pdf.

[44]

Bodén M. A guide to recurrent neural networks and backpropagation. The Dallas Project, SICS Technical Report, 2002.

Google Scholar

[45]

Santoro A, Faulkner R, Raposo D, Rae J, Chrzanowski M, Weber T, Wierstra D, Vinyals O, Pascanu R, Lillicrap T. Relational recurrent neural networks. arXiv preprint, 2018, .

DOI Google Scholar

[46]

Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 9(8): 1735–1780 (1997)

DOI Google Scholar

[47]

Graves A. Long short-term memory. In: Supervised Sequence Labelling with Recurrent Neural Networks. Berlin: Springer, Berlin, Heidelberg, 2012: 37–45.

DOI

[48]

Pascanu R, Mikolov T, Bengio Y. On the difficulty of training recurrent neural networks. In: proceedings of the 30th International conference on International Conference on Machine Learning, Atlanta, USA, 2013: 1310–1318.

[49]

Sen S, Raghunathan A. Approximate computing for long short term memory (LSTM) neural networks. IEEE Trans Comput Aided Des Integr Circuits Syst 37(11): 2266–2276 (2018)

DOI Google Scholar

[50]

Sherstinsky A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Phys D: Nonlinear Phenom 404: 132306 (2020)

DOI Google Scholar

[51]

Staudemeyer R C, Morris E R. Understanding LSTM—A tutorial into long short-term memory recurrent neural networks. arXiv preprint, 2019, .

DOI Google Scholar

[52]

Olah C. Understanding LSTM networks. Available on https://colah.github.io/posts/2015-08-Understanding-LSTMs/.

[53]

Pandiyan V, Prost J, Vorlaufer G, Varga M, Wasmer K. Identification of abnormal tribological regimes using a microphone and semi-supervised machine-learning algorithm. Friction 10: 583–596 (2022)

DOI Google Scholar

[54]

Gers F A, Schraudolph N N, Schmidhuber J. Learning precise timing with LSTM recurrent networks. J Mach Learn Res 3:115–143 (2003)

Google Scholar

[55]

Sundermeyer M, Schlüter R, Ney H. LSTM neural networks for language modeling. In: Proceedings of the 13th Annual Conference of the International Speech Communication Association, Portland, USA, 2012: 194–197.

DOI

[56]

Graves A, Jaitly N, Mohamed A R. Hybrid speech recognition with Deep Bidirectional LSTM. In: Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, 2013: 273–278.

DOI

[57]

Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z M, Gimelshein N, Antiga L, et al. PyTorch: An imperative style, high-performance deep learning library. In: Proceedings of the 33rd Conference on Neural Information Processing Systems, Vancouver, Canada, 2019.

[58]

Kingma D P, Ba J. Adam: A method for stochastic optimization. arXiv preprint, 2014, .

DOI Google Scholar

About this article

Publication history

Acknowledgements

Rights and permissions

Publication history

Received: 27 September 2021

Revised: 09 November 2021

Accepted: 04 December 2021

Published: 28 April 2022

Issue date: January 2023

Copyright

Acknowledgements

This work was funded by the Austrian COMET Program (project InTribology, No. 872176) via the Austrian Research Promotion Agency (FFG) and the Provinces of Niederösterreich and Vorarlberg, and has been carried out within the Austrian Excellence Centre of Tribology (AC2T research GmbH). The authors would like to thank Christoph Haslehner for performing the experiments and Matthias Freisinger for microscopic analysis of the bearings.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.