Data-Driven Modeling of Inverter-Fed Induction Motor Drives using DMDc for Faulty Conditions

Abstract

Modeling faulty behavior of systems has benefits in diagnosis and control. In this paper a data-driven method, dynamic mode decomposition with control (DMDc), is employed for modeling an inverter-fed induction machine. Results are shown and compared for two scenarios: A step input change and an inverter fault. For both cases, the algorithm can correctly predict behavior of the system. The advantage of this model is its independence from the system parameters. The results show promise for data-drivenfault diagnostics and system modeling.