The Elite Multi-parent Crossover Evolutionary Optimization Algorithm to Optimum Design of Automobile Gearbox

The optimum model of the truck´s gearbox was built up. On the basis of GuoTao algorithm, an elite multi-parent crossover evolutionary optimization algorithm by introducing the elite-preservation strategy, constructing dynamic penalty function and enhancing the selection pressure of parents in the process of crossover was presented. Based on Matlab software, the program DEMPCOA with hybrid discrete variables for the proposed algorithm was developed. The truck´s gearbox was optimized with the proposed method. The results show that this algorithm has no special requirements on the characteristics of optimal designing problems, which has a fairly good universal adaptability and a reliable operation of program with a strong ability of overall convergence. After optimization, the weight can be reduced, the cost can be lowered and the product quality can be raised.