Multi-Objective Optimal Design of Traction Transformer Using Improved NSGA-II

The optimal design of traction transformer is a multi-objective nonlinear problem. The traditional design methods are difficult to consider multiple optimization goals at the same time. Therefore, a comprehensive design method is needed to solve the optimization problem. In this paper, an improved NSGA-II algorithm is used to optimize the design of traction transformer for the conflicting objectives of loss and weight. Then, the traction transformer optimization model based on improved NSGA-II algorithm is established. The nondominated ranking strategy is optimized to improve the global search capability. The solution space distributions of the NSGA-II and improved NSGA-II are compared. The result demonstrates that the improved genetic algorithm is effective and advanced. Finally, the manufacturing of prototype is completed, and the experiment is carried out according to the optimization results.