Automatic Design of Electric Machines Using Tree Structure and Reinforcement Learning by Utilizing Design Data

Abstract

　An automatic design method of electric machines has been developed based on tree structure and reinforcement learning. The decision process of electric machines designs is modeled as the tree structure, and values of the nodes are learned from the design data generated by expert designers. The candidate designs are automatically generated through the tree search based on the node values. The designers’ knowledge and experience can be utilized in this automatic design method through the learning of the node values.