Multi-objective optimization design of oil spray cooling system for hairpin motor based on particle swarm optimization-backpropagation-non-dominated sorting genetic algorithm III.

Abstract

The oil spray cooling system of a new thermal management system for hairpin winding motors was designed and optimized by establishing a multi-objective optimization platform. The spray cooling effects of three types of nozzles were compared using single factor analysis, and the nozzle type with the best cooling effect was determined. The flow characteristics of the fluid inside the oil spray ring were simulated and analyzed. The particle swarm algorithm was used to optimize the backpropagation neural network non-dominated sorting genetic algorithm (PSO-BP-NSGA III), and to perform multi-objective optimization of structural parameters. The optimal solutions of winding temperature and fluid pressure were obtained from the Pareto optimal solution set, the structural optimization and fluid simulation calculation of the oil spray ring were carried out based on the optimal solution, and the consistency between the calculated results and the algorithm prediction results reaches 98%. Compared with the pre-optimization structure, the maximum temperature and pressure of the optimized winding decreased by 8.5% and 25.6% respectively. The multi-objective optimization based on PSO-BP-NSGA III provides practical guidance for the optimization design of the cooling system for hairpin winding motors.