This paper presents the development and implementation of a reinforcement learning agent as the mode selector for a multi-chamber actuator in a load-sensing architecture. The agent selects the mode of the actuator to minimise system energy losses. The agent was trained in a simulated environment and afterwards deployed to the real system. Simulation results indicated the capability of the agent to reduce energy consumption, while maintaining the actuation performance. Experimental results showed the capability of the agent to learn via simulation and to control the real system. ; Funding Agencies|Brazilian Coordination for the Improvement of Higher Education Personnel (CAPES); Brazilian National Council for Scientific and Technological Development (CNPq); Swedish Energy Agency (Energimyndigheten)
Multi-Chamber Actuator Mode Selection through Reinforcement Learning-Simulations and Experiments
2022-01-01
ISI:000833728500001
Article (Journal)
Electronic Resource
English
DDC: | 629 |
Analysis of a Two-Staged Supersonic Combustion Chamber using Experiments and Simulations
British Library Conference Proceedings | 2011
|Model-based Reinforcement Learning for Accelerated Learning From CFD Simulations
BASE | 2022
|