Thermal image-based fault identification of induction motors using image features

Lakshmi Dandapani, Kavitha Selvaraj, Malathy Batumalay, Taqwa Hariguna

Abstract


Three-phase induction motors are widely used in industrial systems, making reliable fault identification essential for safe and efficient operation. This study presents a non-contact thermal image-based approach for preliminary fault identification of three-phase induction motors using interpretable image features and classification analysis. Thermal images of healthy and faulty motors were acquired under different load levels and processed using hue, saturation, and value (HSV) color-space transformation, hue-based analysis, and Otsu segmentation. Five image features, namely mean, mean squared error (MSE), peak signal-to-noise ratio (PSNR), variance, and standard deviation (SD), were extracted to characterize thermal responses. The results show clear differences between healthy and faulty conditions, with faulty motors producing higher feature values and more prominent hotspots. For the four-bar rotor fault, maximum temperature increased from 26.6 °C at no load to 63.4 °C at full load. Classification performance also improved with increasing load, although overall performance remained limited. These findings demonstrate the potential of thermal imaging for non-contact induction motor condition monitoring and predictive maintenance.

Keywords


Classification analysis; Fault diagnosis; Image feature extraction; Induction motor; Predictive maintenance; Process innovation; Thermal imaging

Full Text:

PDF


DOI: https://doi.org/10.11591/eei.v15i6.13373

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Statistics

Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191 , e-ISSN: 2302-9285
This journal is published by the Institute of Advanced Engineering and Science (IAES) .