论文部分内容阅读
在系统分析和研究自适应遗传算法特点的基础上,提出了一种新颖的混合软计算:结合混沌搜索的自适应遗传算法.一方面,算法将具有对初值敏感、易跳出局部极小、搜索速度快和计算精度高的混沌优化算法引入到自适应遗传算法中,以平衡其“开发”和“探测”之间的性能;另一方面,算法设定群体早熟收敛的量化计算公式和判定阈值,并引入了一组新的自适应交叉率和变异率的计算函数,从而有效防止了算法陷入局部最优的缺点.通过对4个基准测试函数的仿真计算,证明该算法能有效提高全局寻优的性能,且鲁棒性好.
On the basis of systematically analyzing and studying the characteristics of adaptive genetic algorithm, a novel hybrid soft computing is proposed: an adaptive genetic algorithm combined with chaotic search.On the one hand, the algorithm will have sensitivity to initial value, easy to jump out of local minimum, Search speed and high precision of the chaotic optimization algorithm is introduced into the adaptive genetic algorithm to balance the performance between its “development ” and “probe ”; on the other hand, the algorithm sets the quantitative premature convergence Calculation formulas and decision thresholds and introduces a new set of adaptive crossover and mutation rate calculation functions to effectively prevent the algorithm from falling into the local optimum.By simulating the four benchmark test functions, Can effectively improve the performance of global optimization, and good robustness.