The magnetic components are critical for power electronics systems and can greatly impact their overall efficiency and performance. This paper proposes an intelligent fast DC inductor design optimization system which generates a design of DC inductor with airgap in one second, given the operation conditions of triangular excitation currents. More specifically, it is based on Deep Deterministic Policy Gradient (DDPG), which is a reinforcement learning (RL) algorithm that enables an agent to interact with and learn from its environment. By using a single universal DDPG model, the magnetic design process with variant operation points can be substantially accelerated. The results indicate that the DDPG algorithm can effectively achieve optimal magnetic component design, demonstrating the potential of RL as a valuable tool for automating power electronics design.
