基于PSO的不稳定过程和稳定过程的辨识  

Identification of Unstable System and Stable System Based on PSO

作　　者：袁晗[1,2] 徐春梅 杨平[1] Yuan Han;Xu Chunmei;Yang Ping(College of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China;State Grid Dazhou Power Supply Company,Dazhou 635000,China)

机构地区：[1]上海电力学院自动化工程学院,上海200090 [2]国网达州供电公司,四川达州635000

出　　处：《科技通报》2017年第8期180-184,共5页Bulletin of Science and Technology

基　　金：上海市电站自动化技术重点实验室(13DZ2273800);上海市科技创新行动计划(13111104300)

摘　　要：带有伪噪声模型的Box-Jenkins模型克服了Box-Jenkins模型不可用于不稳定过程辨识的缺点,但数值优化算法复杂且易陷入局部最优。本文应用PSO对带有伪噪声模型的Box-Jenkins模型进行闭环下不稳定过程和稳定过程模型的参数辨识。通过在不同仿真例子下对比,得出本文方法具有参数估计的有效性和无偏性,而采用其它模型的辨识存在较大的估计偏差,甚至不可辨识。最后,仿真说明在本文方法下当噪声模型属于所选用模型类时,能获得较好的过程模型参数。An alternative Box-Jenkins model circumvents the defect of Box-Jenkins model that can’t use in the identification of unstable system,but it requires excellent numerical optimization algorithm and easy to get local optimal solution.This paper uses an alternative Box-Jenkins model for the closed-loop identification of the unstable and stable system based on PSO.The identification based on other model is worse,and even not identifiability.However,our method is still effectiveness in the high noise signal ratio.Finally,simulation tests show,when the noise model belongs to the model class of identification,the identification is effectiveness.

关 键 词：带伪噪声模型的Box-Jenkins模型 最小二乘 不稳定过程 闭环辨识 无偏性 PSO 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]