不同类型粒子群算法对传递函数辨识仿真研究

Simulation research on transfer function identification by different types of particle swarm optimization

为解决传递函数的辨识效率问题,通过粒子群优化算法对系统传递函数进行参数辨识,寻找参数的最优解.文章利用基于粒子群优化算法辨识传递函数、带极值扰动粒子群优化算法和惯性权重混沌粒子群优化算法,分别对不同类型的传递函数(一阶惯性、二阶惯性、一阶惯性加滞后和积分惯性加滞后)进行仿真验证.结果表明,改进后的ePSO算法和iPSO算法比bPSO算法具有更好的系统传递函数辨识效果.

In order to solve the problem of the identification efficiency of the transfer function,the param-eters of the system transfer function are identified by the particle swarm optimization algorithm to find the opti-mal solution of the parameters.In this paper,different types of transfer functions(first-order inertia,second order inertia,first-order inertia plus lag,and integral inertia plus hysteresis)are used for simulation verifica-tion by using particle swarm optimization algorithm to identify transfer function,particle swarm optimization algorithm with extreme perturbation,and inertia weight chaotic particle swarm optimization algorithm.The results show that the improved ePSO algorithm and iPSO algorithm have better system transfer function identifica-tion effect than the bPSO algorithm.