Inter-turn fault and condition identification in induction machines using multiple indicator approach

A multiple model indicator based fault diagnosis and condition identification has been proposed and experimentally verified in this work. One of the important challenges in fault isolation is discriminating the fault with voltage imbalances, which always exists in the system. The multiple indicator approach proposed in this work, is found to be useful, especially at early stages of the fault. The fault indicators are derived from the analytic fault model of the induction machine, and the technique is found to work well for complex conditions when fault and imbalances occur together. The method is insular to load variations. The experimental results show the applicability of the method to accommodate varying operating conditions of the machine as well as the imbalances in supply.