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

Zhenli Wang

doi:10.1117/12.3038866

9 August 2024 Research on dead-time compensation algorithm for PMSM drive systems based on stacked LSTM

Zhenli Wang

Proceedings Volume 13220, Third International Conference on Mechatronics and Mechanical Engineering (ICMME 2024); 132201V (2024) https://doi.org/10.1117/12.3038866
Event: International Conference on Mechatronics and Mechanical Engineering (ICMME 2024), 2024, Xi'an, China

Abstract

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.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Zhenli Wang "Research on dead-time compensation algorithm for PMSM drive systems based on stacked LSTM", Proc. SPIE 13220, Third International Conference on Mechatronics and Mechanical Engineering (ICMME 2024), 132201V (9 August 2024); https://doi.org/10.1117/12.3038866

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available