论文部分内容阅读
变异操作是解决粒子群算法早熟的一种有效方法。针对迭代过程中种群多样性变化的特点,提出了一种自适应变异概率的混合变异粒子群优化算法。通过聚集度动态地调节每代粒子的变异概率,并用这种变异概率对全局最优位置进行高斯和柯西混合变异和对最差个体最优位置进行自适应小波变异。通过在matlab中和其他几种变异的粒子群优化算法进行比较验证,结果证明该算法具有较高的收敛精度和较好的算法性能。
Variation operation is an effective method to solve the precocity of PSO. Aiming at the characteristics of population diversity during iteration, a hybrid mutation particle swarm optimization algorithm with adaptive mutation probability is proposed. Through the aggregation degree, the mutation probability of each generation of particles is dynamically adjusted, and the Gaussian and Cauchy mixture mutation of the global optimum position and the adaptive wavelet variation of the worst individual optimal position are obtained by using this mutation probability. The results of comparison and verification by matlab and other several particle swarm optimization algorithms show that the algorithm has higher convergence accuracy and better performance.