Diagnostic of Induction Motor Eccentricity Defaults in Electrical Vehicles using SVM

Electric motors are crucial components in electric vehicles. However, defaults in such induction machine can significantly impact the car's operation, disrupt traffic flow, and raise diagnostic costs, where many of these defaults being progressive. This paper explores default detection approaches in electric motors, focusing on employing support vector machines technique (SVMs) for identifying defaults in induction motors to mitigate potential consequences on electric vehicle operation and safety. The developed methodology is utilized to classify different types of eccentricity resulting from mechanical defaults, alongside normal operating conditions. Performance of the SVM technique is compared to other classification methods such as Naive Bayes and Dummy. It achieves an accuracy of up to 98%.