Modeling and Control of Spring-Mass Systems With Switched Dynamics Using Reservoir Computing
IEEE Access · 2026 · 14 · 77825-77838
DOI: 10.1109/access.2026.3693102 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Osemudiamen Andrew Ihimekpen und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Army Research Office.
Abstract (Originalsprache)
Hybrid spring-mass systems with switched dynamics present significant challenges for modeling and control due to their complex nonlinear dynamics and discrete state transitions. Traditional control methods, such as proportional-integral-derivative (PID) controllers and linear-quadratic-regulators (LQR), often struggle with the complexity of hybrid systems, limiting their effectiveness for real-time applications. Similarly, conventional machine learning approaches face difficulties, including long training times, overfitting, and insufficient temporal memory to capture hybrid dynamics effectively. To address these challenges, we introduce a reservoir computing framework based on echo state networks (ESNs) in this work to model and control a hybrid spring-mass system with switched dynamics. The proposed method enables efficient learning of spatiotemporal patterns of hybrid dynamics without air friction and with air friction based on velocity thresholds, offering accurate system identification and robust control capabilities. Experimental results demonstrate that the proposed model achieves high performance across different velocity thresholds, with Mean Absolute Percentage Error (MAPE) values of 0.06% to 8.2% for modeling and 2.52% to 7.07% for control tasks, respectively. Furthermore, the proposed method is computationally efficient, supporting rapid training (under 5 seconds) and real-time deployment.
Förderung
- Army Research Office
Zitieren
APA
Ihimekpen, O. A., Li, X., & Qian, L. (2026). Modeling and Control of Spring-Mass Systems With Switched Dynamics Using Reservoir Computing. IEEE Access, 14, 77825-77838. https://doi.org/10.1109/access.2026.3693102
Vancouver
Ihimekpen OA, Li X, Qian L. Modeling and Control of Spring-Mass Systems With Switched Dynamics Using Reservoir Computing. IEEE Access. 2026;14:77825-77838. doi:10.1109/access.2026.3693102
BibTeX
@article{Ihimekpen2026,
author = {Ihimekpen, Osemudiamen Andrew and Li, Xiangfang and Qian, Lijun},
title = {Modeling and Control of Spring-Mass Systems With Switched Dynamics Using Reservoir Computing},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {77825--77838},
doi = {10.1109/access.2026.3693102}
}
EUVIMED