Integrated RBFNN-based finite-time adaptive control of dielectric elastomer actuators with uncertainties
Physica Scripta · 22.05.2026 · 101 (20) · 205218
DOI: 10.1088/1402-4896/ae6a45 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 20.05.2026. Verfasst von Ximing Huang und 1 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
This paper investigates the complex nonlinear dynamics and integrated RBFNN-based finite-time adaptive control of dielectric elastomer actuators (DEAs) under periodic load. Firstly, based on the nonlinear coupled model, the complexity and bifurcation properties are discussed and the complex dynamic behavior is found, the complexity analysis can also verify the effectiveness of the bifurcation results. Then, in order to tune and stabilize the dynamic behaviors onto target orbits, the adaptive sliding mode control (ASMC) integrating tanh-based functions is employed to minimize the buffeting while ensuring robust convergence. Meanwhile, by combining the minimum parameter learning method (MPLM), RBF neural network and ASMC technique, the RBFNN-ASMC approach is proposed to regulate the desired trajectories of DEAs. Both controllers provide the Lyapunov-based stability guarantees and they can tune the motion to the predefined orbit in a short time, after that the controllers is closed but the desired motion can be kept. The RBFNN-ASMC approach can integrate the neural network for intelligent approximation of unknown dynamics with enhanced adaptive capabilities, which can realize the real-time compensation of nonlinearities, faster convergence, and improved robustness to uncertainties. Finally, comparative analysis demonstrates the superior performance of the RBFNN-ASMC method, achieving an average reduction of 66.36% in control time over conventional ASMC. This research establishes the robust framework for controlling the complex nonlinear dynamics of DEAs with significant implications for soft robotics and biomimetic application.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Huang, X., & Huang, D. (2026). Integrated RBFNN-based finite-time adaptive control of dielectric elastomer actuators with uncertainties. Physica Scripta, 101(20), 205218. https://doi.org/10.1088/1402-4896/ae6a45
Vancouver
Huang X, Huang D. Integrated RBFNN-based finite-time adaptive control of dielectric elastomer actuators with uncertainties. Physica Scripta. 2026;101(20):205218. doi:10.1088/1402-4896/ae6a45
BibTeX
@article{Huang2026,
author = {Huang, Ximing and Huang, Dongmei},
title = {Integrated RBFNN-based finite-time adaptive control of dielectric elastomer actuators with uncertainties},
journal = {Physica Scripta},
year = {2026},
volume = {101},
number = {20},
pages = {205218},
doi = {10.1088/1402-4896/ae6a45}
}
EUVIMED