A Study on the Design Method of a Four-Port EMI Filter Using the DDPG Algorithm

In this paper, we propose a design method for a busbar-PCB type EMI filter using the deep deterministic policy gradient (DDPG) algorithm, which is a reinforcement learning method. Owing to the presence of several parasitic elements in the busbar-PCB type EMI filter, the accuracy in the differential mode and common mode insertion loss in the wideband equivalent circuits was first demonstrated replacing the EM-circuit co-simulation. The state and behavior were defined, and learning was performed to satisfy the necessary insertion loss using the DDPG method. Consequently, impedances satisfying the required insertion loss were derived from the open impedance at five positions on the given PCB, and it was confirmed that the CISPR 25 class 4 regulation condition was satisfied in all frequency bands compared to that in the model used in the existing analysis.