Common Diagnosis Approach to Three-Class Induction Motor Faults Using Stator Current Feature and Support Vector Machine

Induction motors are becoming crucial components in numerous industries. The daily usage of induction creates the demand for proper maintenance and slight fault detection to avoid serious damage motor shutdown Among various kinds faults motors, bearing failures, broken rotor bar short-circuit insulation failures most common. Thus, classification these attracting great attention. There conventional methods detecting such faults, as vibration method failure, self-organizing map case current signature analysis failure. From an industrial point view, diagnosis that can classify all major required. However, reports on using common scarce. In this paper, three notable were artificially induced, diagnoses stator spectral features rotation speed performed. was accomplished auto-tunable arbitrary featured support vector machine algorithm. Although minor, a high accuracy rate obtained. capability prove robustness sensitivity method, enabling its practical applications