Fault Diagnosis of Rotary Machines Using Machine Learning

Iago M. Brandao; Cesar da Costa

doi:10.18618/REP.2022.3.0013

Authors

Iago M. Brandao Department of Electrical Engineering, IFSP Federal Institute of São Paulo, São Paulo, Brazil
Cesar da Costa Department of Electrical Engineering, IFSP Federal Institute of São Paulo, São Paulo, Brazil

DOI:

https://doi.org/10.18618/REP.2022.3.0013

Keywords:

Fault classification, Fault diagnosis, Machine learning, Vibration analysis

Abstract

Classification of faults in rotary machines using machine learning is gaining attention in the field of science and engineering. In rotating machinery, misalignment is a common fault. This type of fault has been extensively studied in the literature using the vibration signals produced by rotary machines. This study proposes an approach based on machine learning techniques to diagnose misalignments in rotary machines under various conditions. A personalized diagnostic fault approach is proposed to detect misalignment faults. The approach includes three steps. First, the data acquisition model is developed to obtain signals (fault samples). The rotor vibration signals in stationary rotation conditions were obtained by two inductive proximity sensors with analog output, and the data were collected by a data acquisition device. Then, to generate the faulty training samples, each data acquisition signal is transformed to the frequency domain using Fast Fourier Transform (FFT). Finally, using the samples obtained through the feature selection techniques, machine learning algorithms Random Forest, Naïve Bayes and SVM were evaluated, resulting in classifications with different efficiencies. The results show that the SVM algorithm outperforms the Naïve Bayes and Random Forest algorithms when the same number of features is used. The proposed personalized diagnostic approach was applied to detect faults of rotating electrical machines misalignment with success.

Downloads

Download data is not yet available.

Author Biographies

Iago M. Brandao, Department of Electrical Engineering, IFSP Federal Institute of São Paulo, São Paulo, Brazil

was born in São Paulo, SP, Brazil. He received the B.Sc. degree in Automation and Control Engineering from the IFSP –Federal Institute of São Paulo, SP, Brazilin 2018. He is currently Machine Learning Engineer. His research interest includes Artificial Neural Network, machine learning, induction motors, sensors, diagnostic, electrical machines, and FPGA.

Cesar da Costa , Department of Electrical Engineering, IFSP Federal Institute of São Paulo, São Paulo, Brazil

was born in Rio de Janeiro, RJ, Brazil. He received the B.Sc. degree in electronic and electrical engineering from the CEFET-RJ, Federal Center of Technological Education Celso Suckow da Fonseca and Nuno Lisboa University in 1975 and 1980 respectively. He received the M.Sc. degree in mechanical engineering from Taubate University, Taubate, SP, Brazil, and the Ph.D. degree in mechanical engineering from UNESP-Universidad Estadual Paulista Julio de Mesquita Filho, Guaratingueta, SP, Brazil in 2005 e 2011, respectively. He did sandwich doctoral stage, PDEE-CAPES, in the IST-Institute Superior Tecnico, Lisbon, Portugal in 2009. He is currently postdoctoral and professor of automation and control engineering in the IFSP –Federal Institute of Education, SP, Brazil. His research interests include Fuzzy controller, Artificial Neural Network, machine learning, electrical machines, FPGA, and Industry 4.0.

References

J. Z.Szabo, "Vibration diagnostic test for effect of unbalance",in 16th International Conference on Intelligent Engineering System,Lisbon, Portugal, pp.81-85,July2012. https://doi.org/10.1109/INES.2012.6249807

T. H.Patel,A. K.Darpe, "Vibration response of misaligned rotor",J. Sound Vibration,325(2009), pp.609-628,Aug2009. https://doi.org/10.1016/j.jsv.2009.03.024

J. M.Bossio,G. R.Bossio,C. H.De Angelo, "Angular misalignment in induction motor with flexible coupling",in 35th Annual Conference of IEEE Industrial Electronics, 2009, pp. 1033-1038,Febr2009. https://doi.org/10.1109/IECON.2009.5414696

M. Lal and R. Tiwari, "Multi-fault identification in simple rotor-bearing-coupling systems based on forced response measurements",Mech. Mach. Theory, vol. 51, pp. 87-109,May2012. https://doi.org/10.1016/j.mechmachtheory.2012.01.001

J. K. Sinha and K. Elbhbah, "A future possibility of vibration-based condition monitoring of rotating machines",Mech. Syst. Signal Process., vol. 34, nº1-2, pp. 231-240,Jan2012. https://doi.org/10.1016/j.ymssp.2012.07.001

M. Monte, F. Verbelen, B. Vervisch, B. "The use of M. Monte, F. Verbelen, B. Vervisch, B. "The use of orbitals and full spectra to identify misalignment",Wicks A. (eds) Structural Health Monitoring, in Conference Proceedings of the Society for Conference Proceedings of the Society for Experimental Mechanics Series Experimental Mechanics Series. Springer, Springer, vol.5. pp.215-222, Feb2014. https://doi.org/10.1007/978-3-319-04570-2_24

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, vol. 66, Issue 1, pp.509-518, Feb2019. https://doi.org/10.1109/TIE.2018.2807414

G. Toh and J. Park, "Review of Vibration-Based Structural Health Monitoring Using Deep Learning",Applied Sciences,vol. 10, nº5: 1680, March 2020. https://doi.org/10.3390/app10051680

Martin-Diaz, D. Morinigo-Sotelo, O. Duque-Perez, 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, nº3, pp.2215-2224,Feb2018. https://doi.org/10.1109/TIA.2018.2801863

A. Pinheiro, I. M. Brandão, C. Da Costa, "Vibration Analysis in Turbomachines Using Machine Learning Techniques",European Journal of Engineering European Journal of Engineering Research and Science Research and Science, vol. 4, nº2, pp. 12-16,Feb2019. https://doi.org/10.24018/ejers.2019.4.2.1128

R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, R. X. Gao, "Deep learning and its applications to machine health monitoring",Mech. Syst. Signal Process, vol. 115, pp. 213-237,January 2019. https://doi.org/10.1016/j.ymssp.2018.05.050

J. Feng, L. Yaguo, L. Jing, Z. Xin, L. Na, "Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data",Mechanical Systems and Signal Processing, vol. 72, pp. 303-315, May 2016. https://doi.org/10.1016/j.ymssp.2015.10.025

P. K. Kankar, S. C. Sharma, S. P. Harsha, "Fault diagnosis of ball bearings using machine learning methods",Expert Systems with Applications, vol.38, nº3, pp.1876-1886,March2011. https://doi.org/10.1016/j.eswa.2010.07.119

J. R. Huerta-Rosales, D. Granados-Lieberman, A. Garcia-Perez, D. Camarena-Martinez, J. P. Amezquita-Sanchez. "Short-Circuited Turn Fault Diagnosis in Transformers by using Vibration Signals, Statistical Time Features, and Support Vector Machines on FPGA",Sensor.,vol.21, nº11: 3598,May2021. https://doi.org/10.3390/s21113598

G. K. Yamamoto, C. Da Costa, J. S. S. Sousa, "A smart experimental setup for vibration measurement and imbalance fault detection in rotating machinery",Case Studies in Mechanical Systems and Signal Processing, vol. 4, pp 8-18,Dec2016. https://doi.org/10.1016/j.csmssp.2016.07.001

C. Da Costa, R.S. Gama, C. E. Nascimento, I. M. Brandão, E. C. Medeiros, M. H. Mathias, "Orbit Analysis for Imbalance Fault Detection in Rotating Machinery",Journal of Electrical and Electronics Engineering (IOSR-JEEE)-JEEE)-, vol.13, Issue 1, pp 43-53, March 2018

.[17] IBM,"Whatissupervisedlearning?IBMCloudLearnHub,SupervisedLearning".Learning".(2020)[Online]. Available: https://www.ibm.com/cloud/learn/supervised-learning#toc-what-is-su-d3nKa9tk

Y. LeCun, Y. Bengio, and G. Hinton, "Review -Deep learning"learning",Nature, vol.521,pp.436-444, May 2015.444, May 2015. https://doi.org/10.1038/nature14539

C. G. Mattera, J. Quevedo, T. Escobet, H. R. Shaker, and M. Jradi, "Fault Detection and Diagnostics in Ventilation Units Using Linear Regression Virtual Sensors",in 2018 International Symposium on Advanced Electrical and Communication Technologies (ISAECT),Rabat, Morocco, pp. 1-6, Jan2019. https://doi.org/10.1109/ISAECT.2018.8618755

Q. Yang, D. Guo, W. Yao, J. Cai, and C. Mei, "Support Vector Machines based Rotor Fault Diagnosis with Improved Particle Swarm optimization",in Chinese Automation Congress (CAC), Hangzhou, China, pp. 4321-4324, Feb2019. https://doi.org/10.1109/CAC48633.2019.8996884

N. N. Iman, and T. Ahmad, "Improving Intrusion Detection System by Estimating Parameters of Random Forest in Boruta",inInternational Conference on Smart Technology and Applications (ICoSTA),Surabaya, Indonesia, pp. 1-6, April2020. https://doi.org/10.1109/ICoSTA48221.2020.1570609975

X. Shi, J. Liang, L. Ye, and B. Hu, "A method of fault diagnosis based on PCA and Bayes classification",in8th World Congress on Intelligent Control and Automation,Jinan, pp. 5628-5631, July 2010.

X. Xing, J. Luo, Z. Jia, Y. Li, and Q. Han, "Automated Fault Detection for Web Services using Naïve Bayes Approach",in IEEE 10th International Conference on Software Engineering and Service Science (ICSESS)Software Engineering and Service Science (ICSESS)Software Engineering and Service Science (ICSESS,Beijing, China, pp. 336-339,March2019 https://doi.org/10.1109/ICSESS47205.2019.9040756