基于粒子群优化的Wiener模型辨识与实例研究

针对一类工业过程中可描述成Wiener模型的非线性系统,其辨识问题可等价成以估计参数为优化变量的非线性极小值优化问题．利用粒子群优化(PSO)算法在整个参数空间内并行搜索获得极小值优化问题的最优解(Wiener模型的最优估计),通过对粒子的迭代轨迹进行分析,改进了PSO算法中惯性权重和学习因子的选择．通过一个Wiener模型的数值仿真验证了本文提出的辨识方法的有效性和实用性,并将该方法应用在连续退火机组加热炉产品质量模型的辨识研究,取得了满意的辨识效果．

Particle swarm optimal identification ofWiener model and a case study

For a class of nonlinear systems described by Wiener model,the model identification problem is equivalent to the nonlinear minimization problem with the estimated parameters as the optimized variables subjected to some equality and inequality constraints.The particle swarm optimization (PSO) algorithm is used to obtain the optimal solution to the minimization problem (i.e.the optimal estimation of Wiener model parameters) by searching in the whole parameter space in parallel.The inertia weight and learning gains in PSO algorithm are then modified through analyzing particle trajectory.A numerical simulation of a Wiener model is also provided to verify the effectiveness when applying the proposed identification scheme.Finally,PSO based identification method is applied to the quality model for a continuous annealing furnace,achieving some satisfactory identification results.