Research on dead-time compensation algorithm for PMSM drive systems based on stacked LSTM

Precise control of Permanent Magnet Synchronous Motor (PMSM) drive systems is critical for achieving high performance. A major challenge in PMSM control is mitigating dead-time effects, which can lead to torque fluctuations and efficiency losses. This paper introduces a novel dead-time compensation algorithm utilizing stacked Long ShortTerm Memory (LSTM) networks. Unlike conventional approaches, this algorithm harnesses the deep learning capabilities of LSTM networks to predict and correct real-time dead-time nonlinearities. A comprehensive dataset collected from a PMSM drive system operating under various conditions is employed to train the LSTM network. Simulation and experimental results validate the effectiveness of the proposed algorithm, demonstrating significant reduction in torque fluctuations and enhanced system efficiency. This study highlights the potential benefits of integrating advanced machine learning techniques into PMSM control systems to optimize performance and reliability.