Multi-Objective Optimization of Superconducting Linear Motor Based on Genetic Algorithm

Insufficient traction and large fluctuations are significant challenges for superconducting linear motors used in high-speed maglev trains, and the quality of traction is closely related to the motor's structural parameters. This paper proposes the utilization of multi-objective optimization genetic algorithms to optimize the motor parameters, employing NSGA-II, a non-dominated sorting genetic algorithm based on Pareto front solutions, for objective optimization. The optimized linear motor exhibits a significant increase in traction force coefficient, reduced fluctuation, and improved cost-effectiveness, providing a new approach for multi-objective optimization of superconducting linear motors.