Published Paper Details:

The efficient operation of three-phase induction motors is crucial for various industrial applications. However, the occurrence of faults can lead to unexpected downtime and costly repairs. This project proposes a novel approach for fault diagnosis in three-phase induction motors by integrating wavelet analysis and artificial neural networks (ANN). Wavelet analysis is employed for feature extraction from motor current signals, allowing for the detection of subtle changes indicative of different fault types. The extracted features are then fed into an ANN model, trained to classify various fault conditions accurately. The effectiveness of the proposed methodology is demonstrated through simulation data of three phase induction motor under different fault scenarios. Results indicate that the combined approach of wavelet analysis and ANN yields high accuracy in fault detection and classification, enabling proactive maintenance and minimizing downtime in industrial systems. This project contributes to advancing the field of condition monitoring and predictive maintenance for three-phase induction motors, offering a robust solution for early fault detection and diagnosis, thereby enhancing reliability and efficiency in industrial operations.