Skip to main content
SpringerLink
Log in

A machine learning approach for the condition monitoring of rotating machinery

  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

Rotating machinery breakdowns are most commonly caused by failures in bearing subsystems. Consequently, condition monitoring of such subsystems could increase reliability of machines that are carrying out field operations. Recently, research has focused on the implementation of vibration signals analysis for health status diagnosis in bearings systems considering the use of acceleration measurements. Informative features sensitive to specific bearing faults and fault locations were constructed by using advanced signal processing techniques which enable the accurate discrimination of faults based on their location. In this paper, the architecture of a diagnostic system for extended faults in bearings based on neural networks is presented. The multilayer perceptron (MLP) with Bayesian automatic relevance determination has been applied in the classification of accelerometer data. New features like the line integral and feature based sensor fusion are introduced which enhance the fault identification performance. Vibration feature selection based on Bayesian automatic relevance determination is introduced for finding better feature combinations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. D. M. Himmelblau, Fault detection and diagnosis in chemical and petrochemical processes, Elsevier Press, Amsterdam (1978).

    Google Scholar 

  2. G. Craessaerts, J. De Baerdemaeker and W. Saeys, Fault diagnostic systems for agricultural machinery, Biosystems Engineering, 106(1) (2010) 26–36.

    Article  Google Scholar 

  3. V. Purushotham, S. Narayanan and S. A. N. Prasad, Multifault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition, NDT&E International (2005) 1–11.

    Google Scholar 

  4. D. Bently, Bently Nevada Co. Predictive maintenance through the monitoring and diagnostics of rolling element bearings, Applications Note ANO44 (1989) 2–8.

    Google Scholar 

  5. F. K. Choy, J. Zhou, M. J. Braun and L. Wang, Vibration monitoring and damage quantification of fault ball bearings, Transactions of the ASME, 127 (2005) 776–783.

    Google Scholar 

  6. B. Samanta, K. R. Al-Balushi and S. A. Al-Araimi, Artificial neural networks and genetic algorithm for bearing fault detection, Soft Computing, 10 (2006) 264–271.

    Article  Google Scholar 

  7. Yean-Ren Hwang, Kuo-Kuang Jen and Yu-Ta Shen, Application of cepstrum and neural network to bearing fault detection, Journal of Mechanical Science and Technology, 23 (2009) 2730–2737.

    Article  Google Scholar 

  8. V. Sugumaran and K. I. Ramachandran, Effect of number of features on classi?cation of roller bearing faults using SVM and PSVM, Expert Systems with Applications, 38 (2011) 4088–4096.

    Article  Google Scholar 

  9. A. Widodo, E. Kim, J-D. Son, B-S. Yang, A. Tan, D-S. Gu, B-K. Choi and L. Mathew, Fault diagnosis of low speed bearing based on relevance vector machine and support vector machine, Expert Systems with Applications, 36(2) (2009) 7252–7261.

    Article  Google Scholar 

  10. Bo Suk Yang, Tian Han and Won-Woo Hwang, Fault diagnosis of rotating machinery based on multi-class support vector machines, Journal of Mechanical Science and Technology, 19(3) (2005) 846–859.

    Article  Google Scholar 

  11. C. J. C. Burgess, A tutorial on support vector machines for pattern recognition, Data Mining and Knowledge Discovery, 2 (1998) 955–974.

    Google Scholar 

  12. S. Tyagi, A comparative study of SVM classifiers and artificial neural networks application for rolling element bearing fault diagnosis using wavelet transform preprocessing. In Proceedings of World Academy of Science, Engineering And Technology, 33 (2008) 319–327.

    Google Scholar 

  13. P. K. Kankar, S. C. Sharma and S. P. Harsha, Fault diagnosis of ball bearings using machine learning methods, Expert Systems with Applications, 38(3) (2011) 1876–1886.

    Article  Google Scholar 

  14. J. Chenga, D. Yua, J. Tangb and Y. Yanga, Application of SVM and SVD technique based on EMD to the fault diagnosis of the rotating machinery, Shock and Vibration, 16 (2009) 89–98.

    Article  Google Scholar 

  15. V. Sugumaran, G. R. Sabareesh and K. I. Ramachandran, Fault diagnostics of roller bearing using kernel based neighborhood score multi-class support vector machine, Expert Systems with Applications, 34(4) (2008) 3090–3098.

    Article  Google Scholar 

  16. Y. Yang, D. Yu and J. Cheng, A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM, Measurement, 40(9–10) (2007a) 943–950.

    Article  Google Scholar 

  17. J. Yang, Y. Zhang and Y. Zhu, Intelligent fault diagnosis of rolling element bearing based on SVMs and fractal dimension, Mechanical Systems and Signal Processing, 21(5) (2007b) 2012–2024.

    Article  Google Scholar 

  18. B. Li, M. Y. Chow, Y. Tipsuwan and J. C. Hung, Neuralnetwork-based motor rolling bearing fault diagnosis, IEEE Transactions on Industrial Electronics, 47 (2000) 1060–1069.

    Article  Google Scholar 

  19. Ngoc-Tu Nguyen, Hong-Hee Lee and Jeong-Min Kwon, Optimal feature selection using genetic algorithm for mechanical fault detection of induction motor, Journal of Mechanical Science and Technology, 22 (2008) 490–496.

    Article  Google Scholar 

  20. R. P. W. Duin, P. Juszczak, P. Paclik, E. Pekalska, D. de Ridder, D. M. J. Tax and S. Verzakov, PRTools 4.1, A matlab toolbox for pattern recognition, Delft University of Technology (2007).

    Google Scholar 

  21. Z. Xu, J. Xuan, T. Shi, B. Wu and Y. Hu, Application of a modified fuzzy ARTMAP with feature-weight learning for the fault diagnosis of bearing, Expert Systems with Applications, 36 (2009) 9961–9968.

    Article  Google Scholar 

  22. P. D. McFadden and J. D. Smith, Vibration monitoring of rolling element bearings by the high-frequency resonance technique — A review, Tribology International, 17(1) (1984) 3–10.

    Article  Google Scholar 

  23. B. A. Paya, I. I. Esat and M. N. M. Badi, Artificial neural network based fault diagnostics of rotating machinery using wavelet transforms as a pre-processor, Mechanical Systems and Signal Processing, 11(5) (1997) 751–765.

    Article  Google Scholar 

  24. N. Sawalhi, Diagnostics, Prognostics and fault simulation for rolling element bearings, PhD Thesis, University of New South Wales, Australia (2007).

    Google Scholar 

  25. R. B. Randall, Vibration-based condition monitoring: industrial, aerospace and automotive applications, Chichester, West Sussex: John Wiley & Sons Ltd. (2011).

    Book  Google Scholar 

  26. N. Sawalhi and R. B. Randall, Simulating gear and bearing interactions in the presence of faults Part II: Simulation of the vibrations produced by extended bearing faults, Mechanical Systems and Signal Processing, 22 (2008) 1952–1966.

    Article  Google Scholar 

  27. G. K. Singh and S. A. Ahmed, Vibration signal analysis using wavelet transform for isolation and identification of electrical faults in induction machine, Electric Power Systems Research, 68(2) (2003) 119–136.

    Article  Google Scholar 

  28. Y. Lei, Z. He and Y. Zi, Application of an intelligent classification method to mechanical fault diagnosis, Expert Systems and Applications, 36 (2009) 9941–9948.

    Article  Google Scholar 

  29. D. E. Rumelhart, G. E. Hinton and R. J. Williams, Learning internal representations by error propagation, In: Rumelhart D E, McClelland J L (Eds.), Parallel Distributed Processing (Part 1). MIT Press, Cambridge, USA (1986) 318–362.

    Google Scholar 

  30. C. M. Bishop, Neural networks for pattern recognition, 1st ed., Oxford University Press, New York, USA (1995).

    Google Scholar 

  31. D. J. C. MacKay, A practical Bayesian framework for back-propagation networks, Neural Computation 4(3) (1992) 448–472.

    Article  Google Scholar 

  32. C. Bravo; D. Moshou, J. West, A. McCartney and H. Ramon, Early disease detection in wheat fields using spectral reflectance, Biosystems Engineering, 84(2) (2003) 137–145.

    Article  Google Scholar 

  33. E. Pękalska and R. P. W. Duin, Classifiers for dissimilarity-based pattern recognition, oral presentation, in: A. Sanfeliu, J. J. Villanueva, M. Vanrell, R. Alquezar, A. K. Jain, J. Kittler (eds.), ICPR15, Proc. 15th Int. Conference on Pattern Recognition (Barcelona, Spain, Sep.3–7), vol. 2, Pattern Recognition and Neural Networks, IEEE Computer Society Press, Los Alamitos, 12–16 (2000).

    Google Scholar 

  34. I. T. Nabney, Netlab: Algorithms for pattern recognition, Springer, London, (2001).

    Google Scholar 

  35. D. Moshou, D. Kateris, N. Sawalhi, I. Gravalos, S. Loutridis, T. Gialamas, P. Xyradakis and Z. Tsiropoulos, Condition monitoring of mechanical subsystems of agricultural vehicles based on fusion of vibration features, In Proceedings of XXXIV CIOSTA CIGR V Conference 2011: Efficient and safe production processes in sustainable agriculture and forestry, Vienna, Austria (2011).

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Agricultural Engineering Laboratory, School of Agriculture, Aristotle University, Thessaloniki, 54 124, Greece

    Dimitrios Kateris, Dimitrios Moshou & Xanthoula-Eirini Pantazi

  2. Department of Biosystems Engineering, School of Agricultural Technology, Technological Educational Institute of Larissa, Larissa, 41 110, Greece

    Ioannis Gravalos

  3. School of Mechanical Engineering, Prince Mohammad Bin Fahd University, Al Khobar, Kingdom of Saudi Arabia

    Nader Sawalhi

  4. Department of Electrical Engineering, School of Technological Applications, Technological Educational Institute of Larissa, Larissa, 41 110, Greece

    Spiros Loutridis

Authors
  1. Dimitrios Kateris
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dimitrios Moshou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xanthoula-Eirini Pantazi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ioannis Gravalos
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nader Sawalhi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Spiros Loutridis
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dimitrios Kateris.

Additional information

Recommended by Associate Editor Ohseop Song

Dimitrios Kateris is a Ph.D. Candidate in Agricultural Engineering at Aristotle University of Thessaloniki. He received a B.Sc. and M.Sc. in Agricultural Engineering from Aristotle University of Thessaloniki in 2006 and 2009, respectively. His research interests include fault prognosis and diagnosis techniques in mechanical subsystems on agricultural tractors and combines, Neural Networks, Condition monitoring with Neural Networks (NN) and Self — Orginizing Maps (SOM), Support Vectors Machines (SVM), Data fusion, Machinery and Power systems. He has 65 papers published in refereed journals, international and national conference proceedings. Also he has 4 book chapters.

Dimitrios Moshou is Associate Professor at Aristotle University of Thessaloniki and Head of the Biosystems Engineering Laboratory. He has an M.Sc. on neural control of robots from University of Manchester, UK. He was granted a Ph.D. in Neuromorphic Computing from Katholieke Universiteit Leuven (KUL), Belgium. He was senior researcher and manager of EU projects involving smart optical sensors, data fusion and machine learning for about 12 years in research division MeBioS of KUL. He has 40 peer-reviewed journal papers, 70 conference papers, 19 book chapters and 870 citations. He is the author of a research monograph on Artificial Neural Maps.

Xanthoula-Eirini Pantazi is Researcher and Ph.D. Candidate at the Laboratory of Biosystems Engineering at Aristotle University of Thessaloniki. She has an M.Sc. in Biosystems Engineering concerning the optimization of internal combustion engines operating on biofuels by automated recognition of fuel type through intelligent interpretation of engine vibrations and data fusion. Her research interests include data fusion, machine learning, data mining, bio-inspired computational systems, novelty detection architectures and algorithms, sustainable agriculture and food safety through non-destructive monitoring. She has published one paper in a peer-reviewed journal and four papers in international conference proceedings.

Ioannis Gravalos is Associate Professor at the Biosystems Engineering Department of the Technological Educational Institute of Thessaly (Greece). He studied Agricultural Engineering (Dipl.-Ing.) at Agricultural University of Prague, Biotechnology — Nutrition & Environment (M.Sc.) at University of Thessaly, Automation & Control Engineering (Ph.D.) at Agricultural University of Prague. He has twelve years industrial experience in machines reliability and maintenance. His research interests include agricultural mechatronics, condition monitoring of mechanical systems, maintenance technology, and biofuel engines. He has written more than 80 papers for Greek and International scientific Journals and Conferences.

Nader Sawalhi has received a M.Eng.Sc. degree and a Ph.D. in 2001 and 2007, respectively, in mechanical engineering from the University of New south Wales (UNSW), Sydney, Australia. Between 1997 and 2003, he worked for Jordan cement factories, Amman, Jordan, as a predictive maintenance engineer and team leader. Between 2007 and 2011, he worked at the school of mechanical and manufacturing engineering at UNSW as a research associate and lecturer. He is currently an assistant professor of engineering at PMU. His research interests include signal processing, vibration analysis, machine condition monitoring, diagnostics and prognostics and dynamic simulations of mechanical systems.

Spiros J. Loutridis has received a B.Eng. in Electrical Engineering, a M.Sc. in Sound and Vibration studies and a Ph.D. in signal processing. He has contributed a number of papers in the areas of non-destructive testing of machines, signal processing of machinery vibration and room acoustics. He has designed and developed electroacoustic devices and consulted on public address system installation and acoustics. His current research interests include advanced signal processing techniques, machine condition monitoring and digital signal processing for audio. He teaches in the Department of Electrical Engineering at the Technological Institute of Thessaly, Greece.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kateris, D., Moshou, D., Pantazi, XE. et al. A machine learning approach for the condition monitoring of rotating machinery. J Mech Sci Technol 28, 61–71 (2014). https://doi.org/10.1007/s12206-013-1102-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-013-1102-y

Keywords

Search

Navigation