Modeling And Control Of Spring-Mass Systems With Switched Dynamics Using Reservoir Computing

Author

• Osemudiamen Andrew Ihimekpen, Prairie View A&M University

Date of Award

12-2025

Document Type

Thesis

Degree Name

Master of Science

Department

Electrical Engineering

Abstract

Hybrid spring-mass systems with dynamic state switching present significant challenges for modeling and control due to their complex nonlinear dynamics and discrete state transitions. In this research, a novel reservoir computing framework based on echo-state networks (ESNs) was proposed to model and control spring-mass systems with two distinct states: F1 (without air friction) and F2 (with air friction). The system switched between states based on velocity thresholds, creating a complex, hybrid dynamic that required sophisticated modeling approaches. The proposed method enabled efficient learning of spatiotemporal patterns in hybrid dynamics, offering accurate system identification and robust control capabilities.

The framework was computationally efficient, supporting rapid training in under 5 seconds and real-time deployment. Experimental results demonstrated that the ESN models achieved high performance across different threshold configurations, with MAPE values of 0.06% to 8.2% for modeling and 2.52% to 7.07% for control tasks. It was also observed that the reservoir computing framework significantly outperformed traditional deep learning methods while maintaining computational efficiency suitable for real-time applications. This research successfully bridged physics-based modeling with machine learning to provide a practical solution for real-world dynamic hybrid system applications.

Index Terms- CMA-ES, control systems, digital twin, echo state networks (ESN), hybrid systems, nonlinear dynamics, reservoir computing (RC), soft robotics, spring-mass systems, switched dynamics.

Committee Chair/Advisor

Lijun Qian

Committee Member

Xiangfang Li

Committee Member

Lin Gong

Publisher

Prairie View A&M University

Rights

Date of Digitization

6/16/2026

Contributing Institution

John B Coleman Library

City of Publication

Prairie View

MIME Type

Application/PDF

Recommended Citation

Ihimekpen, O. (2025). Modeling And Control Of Spring-Mass Systems With Switched Dynamics Using Reservoir Computing. Retrieved from https://digitalcommons.pvamu.edu/pvamu-theses/1675