Abstract
The purpose of this paper is to suppress clutch judder by machine learning, and the research was conducted on a two-speed transmission for EVs. The deep reinforcement learning model was developed for seamless gearshift control, and the gearshift results without control were compared with the gearshift results after training. As a result, a control rule that achieves seamless gear shifting while suppressing judder was automatically designed by applying deep reinforcement learning to gear shifting control. In addition, seamless gear shifting can be achieved for various patterns of friction coefficients, enabling the development of a robust controller for changing friction coefficients.
