提出一种新的育种遗传算法.采用在解空间产生均匀分布初始种群和最优值保留策略.每代个体依优劣按比例分成雌雄两性.随机产生一部分雌性个体直接进入下一代种群.按照育种学理论,一个雄性与多个雌性进行级进杂交,雄性进行自交.初始种群的规模和两性比例调控全局搜索能力,杂交时雌雄双方遗传比例调控收敛速度.函数优化实验表明,本算法具有强鲁棒性,种群进化快.能快速收敛到最优解.%A new breeding genetic algorithm with population uniformity in the whole solution space and elitist strategy is proposed. All individuals of each generation are pro rata divided into males and females based on their values of the fitness function. During the evolution , the individuals of the next generation are generated by three kinds of ways ?. One way is to randomly select several females from the current population, the other way is to conform to the breeding theory to generate the children by cross several females with one male or by cross one male with another male. The global search ability is controlled by the population size and the proportion of male to female, and the convergence rate is controlled by the proportion of chromosome afforded by males and females on hybridization. The experimental results of function optimization show that the proposed algorithm is robust, and can rapidly converge to the global optima.
展开▼
