Adaptive Control Strategy for Servo PMSM Trajectory Tracking Based on Transfer‐Learning Parameter Identification
International Journal of Energy Research · 2026-01 · 2026 (1)
DOI: 10.1155/er/4876039 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Energy Research, online erschienen am 01.07.2026. Verfasst von Peng Jiang und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Focusing on the issue that the electrical parameters of servo PMSM are susceptible to operating temperature and short‐term high overload, leading to significant dynamic high‐precision trajectory tracking errors in conventional PI control methods, this paper proposes an adaptive trajectory tracking control strategy based on transfer‐learning parameter identification. First, a multiphysics finite element model coupling electrical, magnetic, and thermal fields of the servo PMSM is established to obtain auxiliary training data for constructing a parameter‐identification model. This model acquires resistance, dq‐axis inductance, and permanent magnet flux linkage under various operating temperatures and overload conditions. A small amount of target data from the prototype is collected using experimental measurement methods. Second, a neural network is developed based on the auxiliary training data to characterize the mapping relationships between the four electrical parameters and operating temperature and current. By integrating the target data with a backpropagation (BP) neural network, feature transfer learning for electrical parameters is performed. Subsequently, an adaptive trajectory tracking control strategy is proposed, featuring online self‐tuning of PI parameters for the position, speed, and current loops of the servo PMSM. Finally, simulations and experiments are conducted under combined working conditions involving energy‐ and time‐optimal trajectories with varying operating temperatures. Compared with the conventional PI control strategy, the proposed adaptive trajectory tracking control strategy significantly reduces dynamic errors. Additionally, positioning energy consumption and time are reduced by up to 5.28% and 44.24%, respectively, which verifies the effectiveness of the proposed strategy.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Jiang, P., Xiang, X., Li, H., Li, J., Yuan, B., & Tan, H. (2026). Adaptive Control Strategy for Servo PMSM Trajectory Tracking Based on Transfer‐Learning Parameter Identification. International Journal of Energy Research, 2026(1). https://doi.org/10.1155/er/4876039
Vancouver
Jiang P, Xiang X, Li H, Li J, Yuan B, Tan H. Adaptive Control Strategy for Servo PMSM Trajectory Tracking Based on Transfer‐Learning Parameter Identification. International Journal of Energy Research. 2026;2026(1). doi:10.1155/er/4876039
BibTeX
@article{Jiang2026,
author = {Jiang, Peng and Xiang, Xuewei and Li, Hui and Li, Jianfu and Yuan, Bin and Tan, Hongtao},
title = {Adaptive Control Strategy for Servo PMSM Trajectory Tracking Based on Transfer‐Learning Parameter Identification},
journal = {International Journal of Energy Research},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/er/4876039}
}
EUVIMED