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)


    Access

    Download


    Export, share and cite



    Title :

    Multi-Chamber Actuator Mode Selection through Reinforcement Learning-Simulations and Experiments


    Contributors:

    Publication date :

    2022-01-01


    Remarks:

    ISI:000833728500001



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Cryogenic rocket calorimeter chamber experiments and heat transfer simulations

    Preclik, D. / Wiedmann, D. / Oechslein, W. et al. | AIAA | 1998


    Multi-Agent Deep Reinforcement Learning for Mix-mode Runway Sequencing

    Limin, Shi / Due-Thinh, Pham / Alam, Sameer | IEEE | 2022


    Analysis of a Two-Staged Supersonic Combustion Chamber using Experiments and Simulations

    Vellaramkalayil, J. / Scheuermann, T. / Von Wolfersdorf, J. et al. | British Library Conference Proceedings | 2011


    Analysis of a Two-Staged Supersonic Combustion Chamber using Experiments and Simulations

    Vellaramkalayil, Jiby / Scheuermann, Tobias / von Wolfersdorf, Jens | AIAA | 2011