Vibration Analysis in Turbomachines Using Machine Learning Techniques


  •   Allan Alves Pinheiro

  •   Iago Modesto Brandao

  •   Cesar Da Costa


This study proposes a method for diagnosing faults in turbomachines using machine learning techniques. In this study, a support vector machine-SVM algorithm is proposed for fault diagnosis of rotor rotation imbalance. Recently, support vector machines (SVMs) have become one of the most popular classification methods in vibration analysis technology. Axis unbalance defect is classified using support vector machines. The experimental data is derived from the turbomachine model of the rigid-shaft rotor and the flexible bearings, and the experimental setup for vibration analysis. Several situations of unbalance defects have been successfully detected.

Keywords: Machine Learning;, Fault Diagnosis, Vibration Analysis, Fault Classification


D. E. Bently; C. T. Hatch, and B. Grissom. “Fundamentals of Rotating Machinery Diagnostics”. Minden, Nev.: Bently Pressurized Bearing Press, 2002.

B. Luo, H. Wang, H. Liu, B. Li, F. Peng. “Early Fault Detection of Machine Tools Based on Deep Learning and Dynamic Identification. IEEE Transactions on Industrial Electronics, V. 66, Issue 1, p.509-518, 2018.

B. Ayhan, M. Y. Chow and M. H. Song, “Multiple Discriminant Analysis and Neural Network-Based Monolith and Partition Fault-Detection Schemes for Broken Rotor Bar in Induction Motors”, IEEE Transactions on Industrial Electronic, Vol. 53, No. 4, pp. 1298-1308, August 2006.

I. Aydin, M. Karakose and E. Akin. “Artificial immune based support vector machine algorithm for fault diagnosis of induction motors”. 2007 International Aegean Conference on Electrical Machines and Power Electronics, Sep. 2007.

R. Razavi-Far, M. Kinnaert. ‘Incremental design of a decision system for residual evaluation: a wind turbine application.” IFAC Proceedings Volumes, V.45, Issue 20, pp. 342-348, Jan. 2012.

R. Razavi-Far, M. Saif, V. Palade and E. Zio. “Adaptive incremental ensemble of extreme learning machines for fault diagnosis in induction motor.”. 2017 International Joint Conference on Neural Networks (IJCNN), July 2017.

I. Martin-Diaz, D. Morinigo-Sotelo, O. Duque-Perez and. T.J. Romero-Troncoso. ‘‘An experimental comparative evaluation of machine learning techniques for motor fault diagnosis under various operating conditions.’’ IEEE Transactions on Industry Applications, vol. 54, NO. 3, May-June 2018.

P.H.F. Souza, N. Nascimento, P.P.R. Filho and. C.M.S. Medeiros. ‘‘Detection and classification of faults in induction generator applied into wind turbines through a machine learning approach.” 2018 International Joint Conference on Neural Networks (IJCNN), July 2018.

B. Samanta, “Gear fault detection using artificial neural networks and support vector machines with genetic algorithms”, Mechanical Systems and Signal Processing, vol. 18, issue 3, pp. 625-644, 2004.

H. Henao, C. Bruzzese, E. Strangas, R. Pusca, J. Estima, M. Rieraguasp, S. H. Kia, “Trends in Fault Diagnosis for Electrical Machines: A Review of Diagnostic Techniques”, IEEE Ind. Electron. Mag. Vol. 8, p.31-42, 2014.

F. P. Shah, V. Patel, “A review on feature selection and feature extraction for text classification”. 2016 International Conference on Wireless Communications, Signal Processing and Networking (wispnet), p.2264-2268, mar. 2016.

R. E Blahut, “Fast Algorithms for Signal Processing”. New York: Cambridge University Press, 2010.

M. B. Kursa, W. R. Rudnick, “Feature Selection with the Boruta Package”. Journal of Statistical Software, vol. 36, issue 11, pp. 1-13. Set. 2010.

D. Meyer, F. Leisch, K. Hornik, “The support vector machine under test”. Neurocomputing, vol. 55, issue 1-2, pp.169-186, 2003.

Y. Fuqing, U. Kumar, D. Galar, “A comparative study of artificial neural networks and support vector machine for fault diagnosis”. International Journal of Performability Engineering, vol. 9, no. 1, pp. 49-60, 2013.

J. J. Carbajal-Hernandez, L. P. Sanchez-Fernandez, I. Hernandez-Bautista, J. J. Medel-Juarez, L. a. Sanchez, “Classification of unbalance and misalignment in induction motors using orbital analysis and associative memories”. Neurocomputing, v. 175, p. 838-850, 2016.

D. Moldovan, T. Ciora, I. Anghel, I. Salomie, “Machine learning for sensor-based manufacturing process”. 2017 13 th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP), Sept. 2017.


Download data is not yet available.


How to Cite
Pinheiro, A., Brandao, I. and Da Costa, C. 2019. Vibration Analysis in Turbomachines Using Machine Learning Techniques. European Journal of Engineering and Technology Research. 4, 2 (Feb. 2019), 12-16. DOI: