Multiple Open Switch Fault Diagnosis of Three Phase Voltage Source Inverter Using Ensemble Bagged Tree Machine Learning Technique

Three-phase converters based on insulated-gate bipolar transistors (IGBTs) are widely used in various industrial applications. Faults IGBTs can significantly affect the operation and safety of power electronic equipment loads. It is critical to accurately detect inverter faults as soon they occur ensure system availability high-power quality. This study provides a novel integration signal data-driven fault-diagnosis approaches for detecting open-circuit switch three-phase inverters. The proposed technique uses average root-mean-square (RMS) ratio phase current key extraction feature. feature be estimate fault types faulty switches (es) irrespective changes running load. Ensemble-bagged machine learning classification was predict inverter. results demonstrate ability diagnosis identify single-, double-, triple-switch (s). experimental also attested simulation multiple diagnosis. A unique this its under inverter-operating conditions.