论文部分内容阅读
粒子群优化算法本质上是一种全局随机优化技术,优化性能高但容易陷于局部最优,并且算法性能很大程度上依赖于参数设置。本文对该算法的3个控制参数进行数据实验和调查,分析参数设置对算法性能的影响规律,提出一种改进的粒子群优化算法,该算法在迭代的每一代中,惯性权重和加速系数都是在一定范围内随机产生:ω=rand(0.4,0.7),C1=rand(0.5,3.0),C2=rand(1,3.5)。由于该算法的控制参数不再固定取值;而且在一定范围内随机产生,从而增强了算法的多样性和遍历性,能够有效避免算法早熟收敛。通过标准函数的测试,验证了该算法性能优于固定参数粒子群算法和随机加速系数粒子群算法,具有更好的收敛性和稳定性。
Particle swarm optimization algorithm is essentially a global random optimization technique, which has high optimization performance but is easily trapped in local optima, and the performance of the algorithm depends heavily on the parameter settings. In this paper, three control parameters of the algorithm are tested and investigated. The influence of parameter setting on the performance of the algorithm is analyzed. An improved particle swarm optimization algorithm is proposed. In each iteration of the algorithm, the inertia weight and acceleration coefficient Is randomly generated within a certain range: ω = rand (0.4,0.7), C1 = rand (0.5,3.0), C2 = rand (1,3.5). Because the control parameters of the algorithm are no longer a fixed value, but also randomly generated within a certain range, thereby enhancing the diversity and ergodicity of the algorithm, which can effectively prevent premature convergence of the algorithm. Through the tests of standard functions, the performance of this algorithm is proved to be better than the fixed parameter PSO and stochastic acceleration PSO, which has better convergence and stability.