Computational Technology Resources - CCC

D. Bogucki, M. Ostrowski, B. Blachowski, "Reinforcement Learning-Based Control Strategy for Semi-Active Energy Transfer in Beam Structures", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 11, Paper 3.2, 2025, doi:10.4203/ccc.11.3.2

Keywords: semi-active control, vibration mitigation, reinforcement learning, lockable joints, modal analysis, structural dynamics.

Abstract

In this paper, a modern, reinforcement learning-based semi-active vibration control strategy is presented. Three different reinforcement learning algorithms are used to determine the control of the vibration process of a cantilever beam modeled as a system of two rigid links connected by a rotational spring. The control is achieved by blocking the connections between the links. This effect is achieved by introducing an equivalent rotational viscous damper. The obtained control signals are compared with the instantaneous optimal control, which greedily transfers the vibration energy from one mode to another. The quality of the control signal obtained using reinforcement learning confirms the ability of such algorithms to obtain results consistent with the analytical solution.

download the full-text of this paper (PDF, 14 pages, 1049 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 11 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, SOFT COMPUTING, MACHINE LEARNING AND OPTIMIZATION IN ENGINEERING Edited by: P. Iványi, J. Kruis and B.H.V. Topping Paper 3.2 Reinforcement Learning-Based Control Strategy for Semi-Active Energy Transfer in Beam Structures D. Bogucki, M. Ostrowski and B. Blachowski Institute of Fundamental Technological Research, Polish Academy of Sciences, Warsaw, Poland doi:10.4203/ccc.11.3.2 Full Bibliographic Reference for this paper D. Bogucki, M. Ostrowski, B. Blachowski, "Reinforcement Learning-Based Control Strategy for Semi-Active Energy Transfer in Beam Structures", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 11, Paper 3.2, 2025, doi:10.4203/ccc.11.3.2 Keywords: semi-active control, vibration mitigation, reinforcement learning, lockable joints, modal analysis, structural dynamics. Abstract In this paper, a modern, reinforcement learning-based semi-active vibration control strategy is presented. Three different reinforcement learning algorithms are used to determine the control of the vibration process of a cantilever beam modeled as a system of two rigid links connected by a rotational spring. The control is achieved by blocking the connections between the links. This effect is achieved by introducing an equivalent rotational viscous damper. The obtained control signals are compared with the instantaneous optimal control, which greedily transfers the vibration energy from one mode to another. The quality of the control signal obtained using reinforcement learning confirms the ability of such algorithms to obtain results consistent with the analytical solution. download the full-text of this paper (PDF, 14 pages, 1049 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions