改进滑动平均滤波在PSO辨识中的应用

Application of Improved Moving Average Filter to Identification of PSO

在实际系统信号中不可避免的会存在噪声和瞬时扰动,噪声过大会严重影响粒子群优化算法(PSO)的辨识结果。针对强噪声环境下利用PSO算法进行参数辨识精度差甚至不能收敛的问题,提出了一种改进的滑动平均滤波算法,通过动态修正滑动平均后的数据相位,来实现无滞后的滑动平均滤波效果。仿真实验表明,对这种改进滑动平均滤波算法应用于PSO辨识数据预处理后,有效地提高了PSO对强噪声系统辨识的精度。

The problem of additive noise and instantaneous disturbance producing the advers influences to system identification is discussed.Strong noise will seriously affect the identification results and the particle swarm optimization（PSO）algorithm may not converge due to the interference of noise in the process of identification.An improved moving average filter algorithm is proposed.The moving average filtering result without lag is obtained by using the data phase by dynamic phase correction,PSO method can identify the system model more effectively.The experimental results show that the proposed approach effectively enhance the accuracy of the identification result.