Application of improved multi-population genetic algorithm in structural optimization of automotive electrical equipment

Abstract The structure of automotive electrical equipment is becoming increasingly complex. How to optimize the structure without affecting the performance of the car itself to reduce the weight and manufacturing cost of electrical equipment has become particularly important. Based on this, this study introduces diversity preservation mechanism and adaptive mutation strategy to improve the multi-population genetic algorithm, and proposes the objective function and constraint conditions for the results of automotive electrical equipment, constructing an optimization model for the structure of automotive electrical equipment. The results showed that at 500 iterations, the improved multi-population genetic algorithm had optimal and average fitness values of 0.96 and 0.94, respectively, demonstrating higher accuracy and search capability compared to other algorithms. After using optimization models for different automotive electrical equipment structures, the average energy consumption decreased by 18%, the total cost decreased by 16.55%, and the average total weight of electrical equipment structures decreased by 16.475%. This model is effective in optimizing the structure of electrical equipment. This study contributes to improving the performance and design efficiency of automotive electrical equipment, and has significant implications for promoting the application of intelligent optimization technology in the automotive industry.