Energy-Optimal Finite-Time Control of PMSMs With Caputo-Based Disturbance Observation via Reinforcement Learning
IEEE Internet of Things Journal · 2026-11 · 13 (22) · 53743-53750
DOI: 10.1109/jiot.2026.3729683 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, 2026-11. Verfasst von Jianhui Wang und 5 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: Natural Science Foundation of Guangdong Province.
Abstract (Originalsprache)
This article develops an energy-optimal finite-time control scheme for a permanent magnet synchronous motor (PMSM) under time-varying dead-zone disturbances. First, a Caputo derivative-based weighted error feedback extended state observer (ESO) is proposed to estimate dead-zone disturbances online. By exploiting the memory property of fractional calculus and introducing a gradient-tracking adaptive mechanism, it can improve disturbance estimation accuracy. It also enables real-time feedforward compensation for disturbances caused by temperature drift and device aging. Second, a finite-time energy-optimal control strategy is developed within a critic–actor reinforcement learning architecture. Meanwhile, the Hamilton–Jacobi–Bellman (HJB) equation is approximately solved online to obtain an adaptive optimal control policy, achieving fast transient response while reducing control energy consumption. Furthermore, rigorous theoretical analysis guarantees the finite-time stability of the closed-loop system and the uniform ultimate boundedness of the observer estimation errors. Finally, Simulation results verify the effectiveness of the proposed method.
Förderung
- Natural Science Foundation of Guangdong Province
Zitieren
APA
Wang, J., Mei, Z., Chen, C. L. P., Liu, Z., Lai, G., & Chen, K. (2026). Energy-Optimal Finite-Time Control of PMSMs With Caputo-Based Disturbance Observation via Reinforcement Learning. IEEE Internet of Things Journal, 13(22), 53743-53750. https://doi.org/10.1109/jiot.2026.3729683
Vancouver
Wang J, Mei Z, Chen CLP, Liu Z, Lai G, Chen K. Energy-Optimal Finite-Time Control of PMSMs With Caputo-Based Disturbance Observation via Reinforcement Learning. IEEE Internet of Things Journal. 2026;13(22):53743-53750. doi:10.1109/jiot.2026.3729683
BibTeX
@article{Wang2026,
author = {Wang, Jianhui and Mei, Ziyou and Chen, C. L. Philip and Liu, Zhi and Lai, Guanyu and Chen, Kairui},
title = {Energy-Optimal Finite-Time Control of PMSMs With Caputo-Based Disturbance Observation via Reinforcement Learning},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {22},
pages = {53743--53750},
doi = {10.1109/jiot.2026.3729683}
}
EUVIMED