Bearing Fault Classification Using Statistical Features And Machine Learning Approach
Authors
-
,IN
G. Manjunatha -
,INH.C. Chittappa
DOI:
https://doi.org/10.18311/jmmf/2022/30676Keywords:
Bearing fault, diagnosis, ANN, classifiers, statistical features.Abstract
Bearing degradation is the most common source of faults in machines. In this context, this work presents a monitoring scheme to diagnose bearing faults using machine learning approach. In this approach classification of healthy and faulty conditions of the bearing is carried out using artificial neural network (ANN). A set of statistical features are extracted from the acquired vibration signals. The decision tree technique is used to select significant features out of all statistical extracted features. The selected features were classified using different classifiers. Based on the various classifier results obtained, the ANN classifier achieve the maximum classification accuracy which is recommended for online monitoring and fault diagnosis of the bearing in various machines.
Downloads
Metrics
Downloads
Published
How to Cite
Issue
Section
Accepted 2022-07-12
Published 2022-03-01
References
H. Yang, J. Mathew, and L. Ma, (2003): “Vibration Feature Extraction Techniques for Fault Diagnosis of Rotating Machinery – A Literature Survey,” Asia Pacific Vib. Conf. Aust., no. November, pp. 1–7.
S. N. Engin, K. Gulez, and M. N. M. Badi, (1999): “Advanced signal processing techniques for fault diagnostics – a review,” Mathematical and Computational Applications, vol.4, no.1. pp.121-136.
M. Delgado et al., (2011): “Bearing Faults Detection by a Novel Condition Monitoring Scheme based on Statistical-Time Features and Neural Networks,” IEEE, no. c.
B. R. Nayana and P. Geethanjali, (2018): “Identification of Bearing Faults Using Statistical Time Domain Features and Fused Time-Domain Descriptor Features,”.
P. K. Kankar, S. C. Sharma, and S. P. Harsha, (2011): “Fault diagnosis of ball bearings using machine learning methods,” Expert Syst. Appl., vol.38, no.3, pp. 1876–1886.
R. Liu, B. Yang, E. Zio, and X. Chen, (2018): “Artificial intelligence for fault diagnosis of rotating machinery : A review,” Mech. Syst. Signal Process., vol.108, pp. 33–47, Aug.
S. S. Zhang, S. S. Zhang, B. Wang, and T. G. Habetler, (2019): “Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics - A Review,” Proc. 2019 IEEE 12th Int. Symp. Diagnostics Electr. Mach. Power Electron. Drives, SDEMPED 2019, pp. 257–263.
R. Bal and S. Sharma, (2016): “Review on Meta Classification Algorithms using WEKA,” Int. J. Comput. Trends Technol., vol.35, no.1, pp. 38–47.
Fault diagnosis of automobile gearbox based on machine learning techniques. Procedia Engineering, 97(0): pp. 2092 – 2098, (2014).
Jalel Chebil, Meftah Hrairi, and Nazih Abushikhah. (2011): Signal analysis of vibration measurements for condition monitoring of bearings. Australian Journal of Basic and Applied Sciences, vol.5(1), pp.70-78.
V.E. Gai. (2014): Method of diagnostics of the state of rolling element bearing on the basis of the theory of active perception. In Mechanical Engineering, Automation and Control Systems (MEACS), International Conference on, pp.1-4.
P. K. Kankar, Satish C. Sharma, and S. P. Harsha. (2011): Fault diagnosis of ball bearings using machine learning methods. Expert Syst. Appl., 38(3), pp. 1876– 1886.
Abd Kadir Mahamad and Takashi Hiyama. (2011): Fault classiûcation based on artiûcial intelligence methods for induction motor. Internation Journal of Innovative Computing, Information and Control, 7(9), pp. 5477 – 5494.
Thomas W. Rauber, Francisco de Assis Boldt, and Fla´vio Miguel Vareja˜o. (2015): Heterogeneous feature models and feature selection applied to bearing fault diagnosis. IEEE Transactions on Industrial Electronics, 62(1), pp. 637–646.
Sadok Sassi, Bechir Badri, and Marc Thomas. (2007): A numerical model to predict damaged bearing vibrations. Journal of Vibration and Control, 13(11), pp. 1603– 1628.
