Optimization Design of Amorphous Metal Distribution Transformer Based on Improved Fast and Elitist Multi-objective Genetic Algorithm

In order to solve the problems of long designing period, low efficiency and high manufacturing cost with conventional designing method, this paper proposed an optimal design method of amorphous metal distribution transformer (AMDT) based on improved fast and elitist multi-objective genetic algorithm (NSGA-II). A three-phase 315 kVA AMDT was taken as an example. The active part cost and total loss of the transformer are chosen as the object functions of optimization, the multi-objective optimization is carried out with NSGA-II and improved NSGA- II respectively. The experimental results show that the improved NSGA-II greatly improves the diversity of the population, which makes the distribution of the Pareto solutions more uniform. Compared with the original design scheme, the improved NSGA-II can effectively improve the total loss of transformer and reduce its active part cost.