A Comprehensive Optimal Design of Inductors Using Monte Carlo Tree Search

This article presents a strategy of optimizing inductors with non-linear properties, using Monte Carlo tree search (MCTS). Compared with the existing optimization tools, the proposed method can simultaneously optimize global configuration, such as material, number of turns and winding arrangement, and local geometry. It indicates that the strategy statistically provides a best solution from global and local aspects after iterations with different lengths of chromosomes, which is challenging in conventional optimization techniques. The covariance matrix adaptation evolution strategy (CMA-ES) is used to solve the parametric optimization. For validation, the optimizations on 2-D inductors are performed. The proposed method is very suitable for the optimization of devices with possibly different global configurations. The most notable originality of this work is in the proposal of an inherited search for design targets with different emphases, suggesting that using an inherited search from the previous search history can make it easier to find the optimal solution.