改进遗传算法在汽车悬架系统中的应用

AN IMPROVED GENETIC ALGORITHMS FOR THE PARAMETRIC OPTIMIZATION OF MULTIBODY MODEL- BASED VEHICLE SUSPENSIONS

本文应用遗传算法模式理论,采用灰度编码,给出模式交叉、模式变异操作的定义,并提出一种新的改进遗传算法。该算法使交叉、变异操作有机结合,避免了交叉概率和变异概率的主观选择,具有收敛速度快,迭代次数少且不易陷入局部最优等优点。最后使用该方法对33自由度的汽车悬架多体模型进行实例分析并和传统优化方法、标准遗传算法和小生境遗传算法进行比较,结果明显优于其它方法。

theory and gray encoding, the definition of schema - crossover and schema - mutation were given, and a new improved genetic algorithm was brought forward. The algorithm makes crossover and mutation organically combined, and avoids the artificial choice to the probability of crossover and mutation. The advantages were fast convergence, less iteration and difficult to fall into the global optimum. And at the end, The optimization results prove that the improved genetic algorithm is better than the classical optimization method, the cononical genetic algorithm and the niche genetic algorithm in the aspects of gaining global optimization solutions and accelerating convergence.