RNN-Based High Fidelity Permanent Magnet Synchronous Motor Emulator Considering Driving Inverter Switching Faults

This paper presents a novel interior permanent magnet synchronous motor (IPMSM) model with a new PI-PR controller for emulation applications with the goal to accurately mimic the behavior of the lower order harmonics in the motor caused by drive inverter faults. The proposed method utilizes recurrent neural networks (RNNs) to model the machine under study with the goal to alleviate the computational burden of the emulator and reduce the overall latency in the system. To validate the accuracy of the proposed model, a comparative analysis with a Look-Up-Table (LUT)-based model under varying loading conditions has been conducted. The empirical findings validate the efficacy of the IPMSM emulator in facilitating drive inverter fault testing and demonstrate its utility in mitigating the risk of inverter impairment that may result from the emulation of machine behavior under such faulty circumstances. The proposed emulator is a significant advancement in the field of drive inverter fault testing, allowing for more accurate and efficient simulation of machine currents under defective conditions. This research provides a viable resolution to emulate the behavior of the machine at the presence of drive inverter switching failure.