Diagnosis and Monitoring Method for Detecting and Localizing Bearing Faults

Authors

Saida Dahmane
Department of Electrical Engineering, Faculty of Technology, University of M’sila, 28000, Algeria; Electrical Engineering laboratory (LGE), M’sila University, Algeria.
Fouad Berrabah
Department of Electrical Engineering, Faculty of Technology, University of M’sila, 28000, Algeria; LSELM laboratory, Badji Mokhtar Annaba university, Annaba 23000 Algeria
Mabrouk Defdaf
Department of Electrical Engineering, Faculty of Technology, University of M’sila, 28000, Algeria; LSELM laboratory, Badji Mokhtar Annaba university, Annaba 23000 Algeria
Saad Salah
LSELM laboratory, Badji Mokhtar Annaba university, Annaba 23000 Algeria
DOI: https://doi.org/10.52549/ijeei.v12i1.4612
Download PDF
Published: 11-01-2024 • Issue: Vol. 12 No. 1: March 2024 • Section: Regular paper

Abstract

Induction motors in modern industry are becoming more and more functional and complex. Unfortunately, these machines are not free from damages what make their fault diagnosis the most critical aspect of system monitoring and maintenance. Vibrational signal data yields relevant information about the state of the entire system, as well as specifically about one of its components that makes its analysis quite interesting. For this effect, the current paper aims to propose an automatic diagnosis and monitoring method for detecting and locating bearing faults in an induction motor based on vibration signal processing. The suggested method combines the discrete wavelet transform (DWT) with the envelope spectrum (ENV) as advanced signal processing, incorporating a machine learning algorithm based on random forest classifier. The discrete wavelet transforms (DWT), using the Haar wavelet, decomposes the vibrational signal to provide both approximations and details. Each detail is then reconstructed to avoid any missing of information. To precisely select the reconstructed detail (ð‘…ð‘’ð‘ð‘‘ð‘˜) that provides pertinent information about bearing faults, a statistical study is conducted. This study involves calculating four indicators (Root mean square (RMS), correlation coefficient (CC), energy coefficient (EC) and peak to peak (P2P) factor) is performed for each (ð‘…ð‘’ð‘ð‘‘ð‘˜). These indicators are compared with threshold indicators, and this criterion is met by the reconstructed details 1 and 3. The obtained reconstructed details are then subjected to the spectral envelope analysis to detect the fault frequencies, which are considered as new features entering the random forest classifier model. This combination of approaches allows better feature extraction and structuring of the dataset, leading to improved accuracy of the random forest classifier, achieving a higher classification rate of more than 99,53 %. The proposed DWT-ENV-RF method indicates well its efficiency when compared to other recent works, and the attained results are all confirmed by the experimental tests conducted in the CWRU laboratory.
Keywords: Induction motor; Bearing fault; DWT; Spectral ENV; Random Forest

References

C. Lessmeier, J. K. Kimotho, D. Zimmer, and W. Sextro, “Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification.,†Third Eur. Conf. Progn. Heal. Manag. Soc. 2016, no. Cm, pp. 152–156, 2016.

R. A. Rahman, M. F. Erikyatna, and A. F. Hery, “Study on Predictive Maintenance of V-Belt in Milling Machines Using Machine Learning Study on Predictive Maintenance of V-Belt in Milling Machines Using Machine Learning,†no. November, 2022, doi: 10.17977/um016v6i22022p085.

A. Picot, Z. Obeid, J. Régnier, S. Poignant, O. Darnis, and P. Maussion, “Statistic-based spectral indicator for bearing fault detection in permanent-magnet synchronous machines using the stator current,†Mech. Syst. Signal Process., vol. 46, no. 2, pp. 424–441, 2014, doi: 10.1016/j.ymssp.2014.01.006.

M. Ye, J. Zhang, and J. Yang, “Bearing Fault Diagnosis under Time-Varying Speed and Load Conditions via Observer-Based Load Torque Analysis,†Energies, vol. 15, no. 10, 2022, doi: 10.3390/en15103532.

A. Allouche et al., “A PLL based mechanical faults detection in PMSM at variable speed,†vol. 51, no. 24, pp. 1445–1451, 2018, doi: 10.1016/j.ifacol.2018.09.534.

A. D. Nembhard, J. K. Sinha, A. J. Pinkerton, and K. Elbhbah, “Fault diagnosis of rotating machines using vibration and bearing temperature measurements,†Diagnostyka, vol. 14, no. 3, pp. 45–51, 2013.

M. A. Jamil and S. Khanam, “Fault Classification of Rolling Element Bearing in Machine Learning Domain,†Int. J. Acoust. Vib., vol. 27, no. 2, pp. 77–90, 2022, doi: 10.20855/ijav.2022.27.21829.

R. N. Toma and J. M. Kim, “bearing fault classification of induction motors using discrete wavelet transform and ensemble machine learning algorithms,†Appl. Sci., vol. 10, no. 15, 2020, doi: 10.3390/APP10155251.

G. Georgoulas, T. Loutas, C. D. Stylios, and V. Kostopoulos, “Bearing fault detection based on hybrid ensemble detector and empirical mode decomposition,†Mech. Syst. Signal Process., vol. 41, no. 1–2, pp. 510–525, 2013, doi: 10.1016/j.ymssp.2013.02.020.

P. Thanh Noi and M. Kappas, “Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery,†Sensors (Basel)., vol. 18, no. 1, 2017, doi: 10.3390/s18010018.

S. M. Yadavar Nikravesh, H. Rezaie, M. Kilpatrik, and H. Taheri, “Intelligent fault diagnosis of bearings based on energy levels in frequency bands using wavelet and support vector machines (SVM),†J. Manuf. Mater. Process., vol. 3, no. 1, 2019, doi: 10.3390/jmmp3010011.

P. Kamat et al., “Bearing Fault Detection Using Comparative Analysis of Random Forest, ANN, and Autoencoder Methods,†Lect. Notes Networks Syst., vol. 204, no. June, pp. 157–171, 2021, doi: 10.1007/978-981-16-1089-9_14.

D. Wu et al., “An automatic bearing fault diagnosis method based on characteristics frequency ratio,†Sensors (Switzerland), vol. 20, no. 5, pp. 1–12, 2020, doi: 10.3390/s20051519.

S. Adamczak and W. Makieła, “Analyzing variations in roundness profile parameters during the wavelet decomposition process using the MATLAB environment,†Metrol. Meas. Syst., vol. 18, no. 1, pp. 25–34, 2011, doi: 10.2478/v10178-011-0003-6.

L. Souad, B. Azzedine, C. B. D. Eddine, B. Boualem, M. Samir, and M. Youcef, “Induction machine rotor and stator faults detection by applying the DTW and N-F network,†Proc. IEEE Int. Conf. Ind. Technol., vol. 2018-Febru, no. February, pp. 431–436, 2018, doi: 10.1109/ICIT.2018.8352216.

C. Uyulan and T. Erguzel, “Comparison of Wavelet Families for Mental Task Classification,†J. Neurobehav. Sci., vol. 3, no. 2, p. 59, 2016, doi: 10.5455/jnbs.1454666348.

S. Seninete, M. Mimi, B. D. Eddine Cherif, and A. Ould Ali, “Vibration Signal Analysis for Bearing Fault Diagnostic of Asynchronous Motor using HT-DWT Technique,†Proc. - 2019 6th Int. Conf. Image Signal Process. their Appl. ISPA 2019, no. February 2020, 2019, doi: 10.1109/ISPA48434.2019.8966801.

A. A. Bengharbi, S. Laribi, T. Allaoui, and A. Mimouni, “Photovoltaic system faults diagnosis using discrete wavelet transform based artificial neural networks,†Electr. Eng. Electromechanics, vol. 2022,no. 6, pp. 42–47, 2022, doi: 10.20998/2074-272X.2022.6.07.

A. Rabah and K. Abdelhafid, “2777 . Rolling bearing fault diagnosis based on improved complete ensemble empirical mode of decomposition with adaptive noise combined with minimum entropy deconvolution,†pp. 240–257, 2018, doi: 10.21595/jve.2017.18762.

N. Bessous, S. E. Zouzou, W. Bentrah, S. Sbaa, and M. Sahraoui, “Diagnosis of bearing defects in induction motors using discrete wavelet transform,†Int. J. Syst. Assur. Eng. Manag., vol. 9, no. 2, pp. 335–343, 2018, doi: 10.1007/s13198-016-0459-6.

B. D. Eddine Cherif, S. Seninete, and M. Defdaf, “a Novel, Machine Learning-Based Feature Extraction Method for Detecting and Localizing Bearing Component Defects,†Metrol. Meas. Syst., vol. 29, no. 2, pp. 333–346, 2022, doi: 10.24425/mms.2022.140038.

R. Costache et al., “Flash-flood susceptibility assessment using multi-criteria decision making and machine learning supported by remote sensing and GIS techniques,†Remote Sens., vol. 12, no. 1, 2020, doi: 10.3390/RS12010106.

Bearing Data Center - Case Western Reserve university, “http://csegroups.case.edu/bearingdatacenter/ pages/welcome-case western-reserve-university.â€

J. Tian, L. Liu, F. Zhang, Y. Ai, R. Wang, and C. Fei, “Multi-domain entropy-random forest method for the fusion diagnosis of inter-shaft bearing faults with acoustic emission signals,†Entropy, vol. 22, no. 1, p. 57, 2020, doi: 10.3390/e22010057.

L. Yuan, D. Lian, X. Kang, Y. Chen, and K. Zhai, “Rolling Bearing Fault Diagnosis Based on Convolutional Neural Network and Support Vector Machine,†IEEE Access, vol. 8, pp. 137395–137406, 2020, doi: 10.1109/ACCESS.2020.3012053.

X. Li, W. Zhang, and Q. Ding, “Cross-domain fault diagnosis of rolling element bearings using deep generative neural networks,†IEEE Trans. Ind. Electron., vol. 66, no. 7, pp. 5525–5534, 2019, doi: 10.1109/TIE.2018.2868023.

Author Biographies

Saida Dahmane

Saida DAHMANE received her B.Sc. degree in industrial maintenance in 2017, her M.Sc. in Management and engeneering of industrial maintenance in 2020 from the national high school of technology in Algies-Algeria, and is currently a Ph.D. student in Industrial maintenance field. Her research interests include signal processing, machine learning, electrical machine and drive modeling and analysis, electrical machine and drive control and converters as well as electrical machine and drive faults diagnosis and tolerance.

Fouad Berrabah

born in m'sila, in 1979. He received the B.Sc., M.Sc. and Ph.D. degrees in Electromechanical Engineering from Badji-Mokhtar Annaba University Algeria in 2002, 2008 and 2017 respectively. He is a lecturer senior at the University of M'sila in Algeria. His research interests include electrical machine and drive modeling and analysis, electrical machine and drive control and converters as well as electrical machine and drive fault diagnosis and tolerance

 

Mabrouk Defdaf
Mabrouk DEFDAF received his B.Sc., M.Sc. and Ph.D. degrees in Electromechanical Engineering from Badji-Mokhtar Annaba University Algeria in 2000, 2007 and 2018 respectively. He is a lecturer senior at the University of M'sila in Algeria. His research interests include electrical machine and drive modeling and analysis, electrical machine and drive control and converters as well as electrical machine and drive fault diagnosis and tolerance.
Saad Salah
Saad SALAH was born in Batna, Algeria, in 1958. He received the Engineer degree in electromechanical applied to mining fields from the University of Badji-Mokhtar, Annaba, Algeria, in 1983, and Ph.D. degree from Nottingham University, U.K., in 1988. Since 1988, he has been a Lecturer, a Senior Lecturer, and a Professor with the University of Badji-Mokhtar. He has supervised many graduated and postgraduate student theses. He has conducted many research projects in power electronics applications, electrical ac and dc drives, and diagnosis and faults detection in ac machines. He has authored or co-authored many journal and conference papers. He has co-authored a book in the field of signal processing published in Algeria in 1992. His research interests are mainly in the area of power electronics, such as harmonics elimination by active filters, PWM and space vector modulation control, multilevel inverters, new converter topologies, and vibration sensors.

How to Cite

[1]
S. Dahmane, F. Berrabah, M. Defdaf, and S. Salah, “Diagnosis and Monitoring Method for Detecting and Localizing Bearing Faults”, IJEEI, vol. 12, no. 1, pp. 1–14, Jan. 2024, doi: 10.52549/ijeei.v12i1.4612.