Kamath et al. Res. Trends Int. J. Technol. Innov., July - September 2026, 1 (3) : 26-33
1Department of Electrical and Electronics Engineering, National Institute of Technology Karnataka, Surathkal, India; 2Department of Instrumentation Engineering, Manipal Institute of Technology, Manipal, India
Article History
Accepted : 25 Jun 2026
Published : 10 Jul 2026
Publication Issue
Volume 1, Issue 3
July - September 2026
Page Number26–33
Bearing and rotor faults account for a majority of unplanned induction motor failures in industrial settings, and vibration-based condition monitoring remains the most widely deployed diagnostic approach. This paper extracts time-domain, frequency-domain and wavelet-packet energy features from vibration signals of a motor test rig seeded with four fault types, and classifies them using a support vector machine with a radial basis function kernel. The SVM classifier achieved 97.8 percent classification accuracy across the four fault classes plus healthy baseline, outperforming a k-nearest-neighbour baseline by 5.6 percentage points.
Keywords - induction motor, fault diagnosis, vibration analysis, support vector machine, condition monitoring
Unplanned induction motor downtime in industrial plants is frequently traceable to bearing defects, rotor bar breakage, or shaft misalignment, all of which produce characteristic vibration signatures that can be detected before catastrophic failure with appropriate feature extraction and classification.
Vibration data was collected from a motor test rig under four seeded fault conditions, outer-race bearing fault, inner-race bearing fault, broken rotor bar, and shaft misalignment, plus a healthy baseline, using a tri-axial accelerometer. Eighteen time-domain, frequency-domain and wavelet-packet energy features were extracted per sample and used to train a multi-class SVM classifier with an RBF kernel, tuned via grid search over five-fold cross-validation.
The SVM classifier achieved 97.8 percent overall classification accuracy across the five classes, with the lowest per-class recall of 95.1 percent for distinguishing inner-race from outer-race bearing faults, which share overlapping spectral signatures. This outperformed a k-nearest-neighbour baseline (92.2 percent) evaluated on the identical feature set.
Wavelet-packet energy features combined with SVM classification provide a reliable, computationally light approach for induction motor fault diagnosis suitable for embedded condition-monitoring hardware. Future work will validate the approach on field data from operating plant motors rather than a controlled test rig.
[1] Nandi S. et al., Condition monitoring and fault diagnosis of electrical motors, IEEE Transactions on Energy Conversion, 2005. [2] Cortes C. and Vapnik V., Support-vector networks, Machine Learning, 1995.
© 2026 The Author(s). Published by IJEIA Editorial Office. This is an open access article under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Girish Kamath, Anushka Rane (2026). Fault Diagnosis of Induction Motors Using Vibration Signal Analysis and Support Vector Machines. IJEIA, 1(3), 26-33.