Electrified vehicular industry is growing at a rapid pace with a global increase in production of electric vehicles (EVs) along with several new automotive cars companies coming to compete with the big car industries. The technology of EV has evolved rapidly in the last decade. But still the looming fear of low driving range, inability to charge rapidly like filling up gasoline for a conventional gas car, and lack of enough EV charging stations are just a few of the concerns. With the onset of self-driving cars, and its popularity in integrating them into electric vehicles leads to increase in safety both for the passengers inside the vehicle as well as the people outside. Since electric vehicles have not been widely used over an extended period of time to evaluate the failure rate of the powertrain of the EV, a general but definite understanding of motor failures can be developed from the usage of motors in industrial application. Since traction motors are more power dense as compared to industrial motors, the possibilities of a small failure aggravating to catastrophic issue is high. Understanding the challenges faced in EV due to stator fault in motor, with major focus on induction motor stator winding fault, this dissertation presents the following: 1. Different Motor Failures, Causes and Diagnostic Methods Used, With More Importance to Artificial Intelligence Based Motor Fault Diagnosis. 2. Understanding of Incipient Stator Winding Fault of IM and Feature Selection for Fault Diagnosis 3. Model Based Temperature Feature Prediction under Incipient Fault Condition 4. Design of Harmonics Analysis Block for Flux Feature Prediction 5. Flux Feature based On-line Harmonic Compensation for Fault-tolerant Control 6. Intelligent Flux Feature Predictive Control for Fault-Tolerant Control 7. Introduction to Machine Learning and its Application for Flux Reference Prediction 8. Dual Memorization and Generalization Machine Learning based Stator Fault Diagnosis