摘要
针对粒子群优化算法难以适应复杂的非线性优化,为此提出一种借助正负反馈原理来调整惯性权重和通过随机数对位置更新公式进行调整的改进算法。在仿真实验过程中,通过实验确定了改进算法中的反馈参数与更新公式;并对4个经典测试函数进行仿真实验,结果显示改进算法求解精度高、解的稳定性优良,尤其在多峰值函数中表现优越。
In view of the inability of the particle swarm optimization algorithm to adapt to the complex nonlinear optimization,an improved algorithm is put forward based on the principles of positive and negative feedback to adjust the inertia weight and updating formula of position by random number to adjust. The feedback parameters and updating formula for the improved algorithm are determined by experiment. Simulations of the 4 Classic functions show that the improved algorithm has high accuracy and good stability of solutions,especially in the multi pear function.
出处
《电子科技》
2015年第2期35-37,共3页
Electronic Science and Technology
基金
教育部数学与应用数学专业综合改革基金资助项目(ZG0464)
四川高校数值仿真与数学实验教学示范中心基金资助项目(01247)
内江师范学院青年科研基金资助项目(2011NJZ-3)
关键词
粒子群优化
惯性权重
多峰函数
正负反馈
particle swarm optimization
inertia weight
multi peak function
positive and negative feedback
