Abstract
Functional surfaces in relative contact and motion are prone to wear and tear, resulting in loss of efficiency and performance of the workpieces/machines. Wear occurs in the form of adhesion, abrasion, scuffing, galling, and scoring between contacts. However, the rate of the wear phenomenon depends primarily on the physical properties and the surrounding environment. Monitoring the integrity of surfaces by offline inspections leads to significant wasted machine time. A potential alternate option to offline inspection currently practiced in industries is the analysis of sensors signatures capable of capturing the wear state and correlating it with the wear phenomenon, followed by in situ classification using a state-of-the-art machine learning (ML) algorithm. Though this technique is better than offline inspection, it possesses inherent disadvantages for training the ML models. Ideally, supervised training of ML models requires the datasets considered for the classification to be of equal weightage to avoid biasing. The collection of such a dataset is very cumbersome and expensive in practice, as in real industrial applications, the malfunction period is minimal compared to normal operation. Furthermore, classification models would not classify new wear phenomena from the normal regime if they are unfamiliar. As a promising alternative, in this work, we propose a methodology able to differentiate the abnormal regimes, i.e., wear phenomenon regimes, from the normal regime. This is carried out by familiarizing the ML algorithms only with the distribution of the acoustic emission (AE) signals captured using a microphone related to the normal regime. As a result, the ML algorithms would be able to detect whether some overlaps exist with the learnt distributions when a new, unseen signal arrives. To achieve this goal, a generative convolutional neural network (CNN) architecture based on variational auto encoder (VAE) is built and trained. During the validation procedure of the proposed CNN architectures, we were capable of identifying acoustics signals corresponding to the normal and abnormal wear regime with an accuracy of 97% and 80%. Hence, our approach shows very promising results for in situ and real-time condition monitoring or even wear prediction in tribological applications.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Yoshizawa H, Chen Y L, Israelachvili J. Fundamental mechanisms of interfacial friction. 1. Relation between adhesion and friction. J Phys Chem 97(16): 4128–4140 (1993)
Arnell D. Mechanisms and laws of friction and wear. In Tribology and Dynamics of Engine and Powertrain: Fundamentals, Applications and Future Trends. Rahnejat H, Ed. Amsterdam: Elsevier, 2010: 41–72.
Ludema K C. A review of scuffing and running-in of lubricated surfaces, with asperities and oxides in perspective. Wear 100(1–3): 315–331 (1984)
Holmberg K, Erdemir A. Influence of tribology on global energy consumption, costs and emissions. Friction 5(3): 263–284 (2017)
Bhushan B. Introduction to Tribology. 2nd ed. New York (USA): John Wiley & Sons, 2013.
Bowman W F, Stachowiak G W. A review of scuffing models. Tribol Lett 2(2): 113–131 (1996)
Saeidi F, Taylor A A, Meylan B, Hoffmann P, Wasmer K. Origin of scuffing in grey cast iron-steel tribo-system. Mater Des 116: 622–630 (2017)
Blok H. Theoretical study of temperature rise at surfaces of actual contact under oiliness lubricating conditions. In Proceedings of the Institution of Mechanical Engineers, London, 1937: 222.
Dyson A. The failure of elastohydrodynamic lubrication of circumferentially ground discs. Proc Inst Mech Eng 190(1): 699–711 (1976)
Kato K. Abrasive wear of metals. Tribol Int 30(5): 333–338 (1997)
Hong W, Cai W J, Wang S P, Tomovic M M. Mechanical wear debris feature, detection, and diagnosis: A review. Chin J Aeronaut 31(5): 867–882 (2018)
Yaroshchyk P, Morrison R J S, Body D, Chadwick B L. Quantitative determination of wear metals in engine oils using laser-induced breakdown spectroscopy: A comparison between liquid jets and static liquids. Spectrochim Acta Part B: At Spectrosc 60(7–8): 986–992 (2005)
Dwivedi D K. Adhesive wear behaviour of cast aluminium-silicon alloys: Overview. Mater Des (1980-2015) 31(5): 2517–2531 (2010)
Liu L, Sheng Y Y, Liu M, Dienwiebel M, Zhang Z C, Dastan D. Formation of the third bodies of steel sliding against brass under lubricated conditions. Tribol Int 140: 105727 (2019)
Spikes H A. Mixed lubrication—An overview. Lubr Sci 9(3): 221–253 (1997)
Pandiyan V P S R. Modelling and in-process monitoring of abrasive belt grinding process. Ph.D. Thesis. Singapore: Nanyang Technological University, 2019.
Thankachan T, Prakash K S, Kavimani V, Silambarasan S R. Machine learning and statistical approach to predict and analyze wear rates in copper surface composites. Met Mater Int 27(2): 220–234 (2021)
Markus V. Online wear measurement in harsh environment. Part 1: Possible measurement strategies. Tribol Schmierungstech 66: 36–12 (2019)
Markus V. Online wear measurement in harsh environment. Part 2: Application roller press. Tribol Schmierungstech 66: 43–51s(2019)
Sawyer W G, Wahl K J. Accessing inaccessible interfaces: In situ approaches to materials tribology. MRS Bull 33(12): 1145–1150 (2008)
Asamene K, Sundaresan M. Analysis of experimentally generated friction related acoustic emission signals. Wear 296(1–2): 607–618 (2012)
Varga M, Haas M, Schneidhofer C, Adam K. Wear intensity evaluation in conveying systems-An acoustic emission and vibration measurement approach. Tribol Int 149: 105549 (2020)
Lingard S, Yu C W, Yau C F. Sliding wear studies using acoustic emission. Wear 162–164: 597–604 (1993)
Mano H, Yoshioka T, Korenaga A, Yamamoto T. Relationship between growth of rolling contact fatigue cracks and load distribution. Tribol Trans 43(3): 367–376 (2000)
Symmons G R, McNulty G J. Acoustic output from stickslip friction. Wear 113(1): 79–82 (1986)
Voronenko B I. Acoustic emission during phase transformations in alloys. Met Sci Heat Treat 24(8): 545–553 (1982)
Simmons J A, Wadley H N G. Theory of acoustic emission from phase transformations. J Res Natl Bur Stand 89(1): 55–64 (1984)
Baranov V M, Kudryavtsev E M, Sarychev G A. Modelling of the parameters of acoustic emission under sliding friction of solids. Wear 202(2): 125–133 (1997)
Hase A, Wada M, Mishina H. The relationship between acoustic emissions and wear particles for repeated dry rubbing. Wear 265(5–6): 831–839 (2008)
Beerbower A. Mechanical failure prognosis through oil debris monitoring. USAA MRDL-TR-74-100, 1975.
Hase A, Mishina H, Wada M. Correlation between features of acoustic emission signals and mechanical wear mechanisms. Wear 292–293: 144–150 (2012)
Pandiyan V, Tjahjowidodo T. Use of Acoustic Emissions to detect change in contact mechanisms caused by tool wear in abrasive belt grinding process. Wear 436–437: 203047 (2019)
Hase A. Early detection and identification of fatigue damage in thrust ball bearings by an acoustic emission technique. Lubricants 8(3): 37 (2020)
Al-Dossary S, Hamzah R I R, Mba D. Observations of changes in acoustic emission waveform for varying seeded defect sizes in a rolling element bearing. Appl Acoust 70(1): 58–81 (2009)
Poddar S, Tandon N. Detection of particle contamination in journal bearing using acoustic emission and vibration monitoring techniques. Tribol Int 134: 154–164 (2019)
Korres S, Dienwiebel M. Design and construction of a novel tribometer with online topography and wear measurement. Rev Sci Instrum 81(6): 063904 (2010)
Blau P J. Interpretations of the friction and wear break-in behavior of metals in sliding contact. Wear 71(1): 29–13 (1981)
Rowe K G, Bennett A I, Krick B A, Sawyer W G. In situ thermal measurements of sliding contacts. Tribol Int 62: 208–214 (2013)
Chen G. Handbook of Friction-Vibration Interactions. Sawston, Cambridge (UK): Woodhead Publishing, 2014.
Tyurin A E, Ismailov G M, Beloenko E V, Baranov A V. Monitoring vibrations and microdisplacement for “pin on disc” tribology studies. J Phys: Conf Ser 803: 012167 (2017)
Waydande P, Ambhore N, Chinchanikar S. A review on tool wear monitoring system. J Mech Eng Autom 6(5A): 49–53 (2016)
Yan R Q, Gao R X. An efficient approach to machine health diagnosis based on harmonic wavelet packet transform. Robot Comput-Integr Manuf 21(4–5): 291–301 (2005)
Pandiyan V, Shevchik S, Wasmer K, Castagne S, Tjahjowidodo T. Modelling and monitoring of abrasive finishing processes using artificial intelligence techniques: A review. J Manuf Processes 57: 114–135 (2020)
Baccar D, Schiffer S, Söffker D. Acoustic Emission-based identification and classification of frictional wear of metallic surfaces. In Proceedings of the 7th European Workshop on Structural Health Monitoring, La Cité, Nantes, France, 2014.
Saeidi F, Shevchik S, Wasmer K. Automatic detection of scuffing using acoustic emission. Tribol Int 94: 112–117 (2016)
Shevchik S A, Saeidi F, Meylan B, Wasmer K. Prediction of failure in lubricated surfaces using acoustic time-frequency features and random forest algorithm. IEEE Trans Ind Inform 13(4): 1541–1553 (2017)
Shevchik S A, Zanoli S, Saeidi F, Meylan B, Flück G, Wasmer K. Monitoring of friction-related failures using diffusion maps of acoustic time series. Mech Syst Signal Process 148: 107172 (2021)
Ravikumar S, Ramachandran K I, Sugumaran V. Machine learning approach for automated visual inspection of machine components. Expert Syst Appl 38(4): 3260–3266 (2011)
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)
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)
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)
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)
Thamba N B, Aravind A, Rakesh A, Jahzan M, Duraiswamy R P, Viswanathan M R. Automatic fault classification for journal bearings using ANN and DNN. Arch Acoust 43(4): 727–738 (2018)
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, in press, DOI https://doi.org/10.1016/j.wear.2021.203622.
Wang Y S, Yao H X, Zhao S C. Auto-encoder based dimensionality reduction. Neurocomputing 184: 232–242 (2016)
Xu W D, Sun H Z, Deng C, Tan Y. Variational autoencoders for semi-supervised text classification. arXiv preprint arXiv:1603.02514 (2016)
Gondara L. Medical image denoising using convolutional denoising autoencoders. In Proceedings of 2016 IEEE 16th International Conference on Data Mining Workshops, Barcelona, Spain, 2016.
Nishizaki H. Data augmentation and feature extraction using variational autoencoder for acoustic modeling. In Proceedings of 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, Kuala Lumpur, Malaysia, 2017.
Pandiyan V, Murugan P, Tjahjowidodo T, Caesarendra W, Manyar O M, Then D J H. In-process virtual verification of weld seam removal in robotic abrasive belt grinding process using deep learning. Robot Comput-Integr Manuf 57: 477–487 (2019)
Sakurada M, Yairi T. Anomaly detection using autoencoders with nonlinear dimensionality reduction. In Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, Gold Coast, Australia QLD, Australia, 2014.
Zhu D, Martini A, Wang W Z, Hu Y Z, Lisowsky B, Wang Q J. Simulation of sliding wear in mixed lubrication. J Tribol 129(3): 544–552 (2007)
Prost J. A detailed view on tribometer dynamics — cycle-based data analysis and visualization. Friction, in press.
Shannon C E. Communication in the presence of noise. Proc IRE 37(1): 10–21 (1949)
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 Advances in Neural Information Processing Systems, Vancouver, BC, Canada, 2019.
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). Experiments were carried out within the framework of a project funded by the government of Lower Austria (No. K3-F-760/001-2017).
Author information
Authors and Affiliations
Corresponding author
Additional information
Vigneashwara PANDIYAN. He is currently a postdoctoral researcher at Laboratory for Advanced Materials Processing (LAMP), ETH Empa Swiss Federal Laboratories for Materials Science and Technology. He completed his master and Ph.D. degrees from Nanyang Technological University, Singapore, under Rolls-Royce @ NTU corporate lab. Prior to joining Empa, he was a research scientist in A*Star—Agency for Science, Technology and Research, Singapore. He now concentrates on implementing machine learning models for in-process sensing of manufacturing processes for anomaly detection and process automation based on sensor signatures.
Josef PROST. He received his Ph.D. degree in physics from Vienna University of Technology, Austria, in 2018. He is currently working as a postdoctoral researcher at the Austrian Excellence Centre for Tribology (AC2T Research GmbH) in Wiener Neustadt, Austria. His main research interest is the application of advanced data analysis and visualisation methods to tribological research questions, including the detection of anomalous operation states and impending failures using machine learning models.
Georg VORLAUFER. He is currently a principal scientist at AC2T Research GmbH, the Austrian Excellence Center for Tribology. He completed his master degree in physics at the TU Wien in 1998 and received his Ph.D. degree in physics in 2002 from the same institution. Between 1998 and 2001, he carried out his Ph.D. studies in the field of vacuum and surface science at CERN (Geneva, Switzerland). He has 18+ years of experience in the field of tribology. Although since many years his research interests have been mainly in the field of physics-based modelling and simulation of tribological systems, he is currently concentrating on tribology-related aspects of data science, machine learning, and artificial intelligence.
Markus VARGA. He is currently leading the strategic research area “Synaptic Tribology” at the Austrian Competence Centre for Tribology (AC2T Research GmbH). He received his master degree at the University of Applied Science Wiener Neustadt, Austria in Mechatronics and completed his Ph.D. degree in Tribology at the Montanuniversität Leoben, Austria. His main research field since 10+ years is optimisation of industrial maintenance by tribological measures, i.e., wear protection, sensors for early detection of failures, etc.
Kilian WASMER. He received the B.S. degree in mechanical engineering from the Applied University, Sion, Switzerland and Applied University, Paderborn, Germany in 1999. He received his Ph.D. degree in mechanical engineering from Imperial College London, Great Britain, in 2003. His current position is deputy laboratory head of the Laboratory for Advanced Materials Processing (LAMP) at Empa (Swiss Federal Laboratories for Materials Science and Technology) as well as a lecturer at EPFL.
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/.
About this article
Cite this article
Pandiyan, V., Prost, J., Vorlaufer, G. et al. Identification of abnormal tribological regimes using a microphone and semi-supervised machine-learning algorithm. Friction 10, 583–596 (2022). https://doi.org/10.1007/s40544-021-0518-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40544-021-0518-0