论文部分内容阅读
DE算法是一类基于种群的启发式全局搜索技术,该算法原理简单,控制参数少,鲁棒性强,具有良好的优化性能。利用差分进化算法对Wiener模型参数进行辨识,把辨识问题等价为以估计参数为优化变量的非线性极小值优化问题,并分析了算法中种群规模NP、缩放因子F、交叉概率CR等控制参数对辨识过程中的全局并行搜索能力和收敛速度的影响,以保证算法的全局收敛性。对Wiener模型的数值仿真结果表明了DE算法在参数辨识问题中的有效性,以及较PSO算法更强的非线性系统辨识能力。
DE algorithm is a kind of heuristic global search technology based on population. The algorithm has simple principle, less control parameters, strong robustness and good optimization performance. The differential evolution algorithm is used to identify the Wiener model parameters, and the identification problem is equivalent to the nonlinear minimum minimization optimization problem with the estimated parameters as the optimization variables. The control of population size NP, scaling factor F and crossover probability CR are analyzed The effect of parameters on the global parallel search ability and convergence speed in the identification process ensures the global convergence of the algorithm. The numerical simulation results of Wiener model show the effectiveness of DE algorithm in parameter identification and the stronger nonlinear system identification ability than PSO algorithm.