一种新的非线性系统传感器漂移性能退化实时监测方法  

A NEW REAL-TIME SENSOR DRIFT PERFORMANCE DEGRADATION MONITOR METHOD FOR NON-LINEAR SYSTEMS BASED ON PARTICLE FILTER

作　　者：刘斌[1] 徐正国[1] 

机构地区：[1]浙江大学工业控制技术国家重点实验室控制科学与工程学系,杭州310027

出　　处：《系统科学与数学》2012年第6期791-798,共8页Journal of Systems Science and Mathematical Sciences

基　　金：国家自然科学基金(61004074;61134001);科技部支撑计划(2009BAG12A08);浙江省工业过程及生产装备先进控制创新团队项目(2011R09007-02)资助项目

摘　　要：随着传感器使用时间的增加,其测量值会发生漂移,且漂移程度会随时间的增加而增大.针对非线性系统中的传感器漂移性退化现象,基于改进的粒子滤波算法,提出了传感器漂移性能退化实时监测方法.该方法通过实时估计漂移量来实现对系统状态的估计,能够检测并跟踪动态系统中传感器性能退化过程,为系统安全运行提供保障.基于三容水箱系统的仿真验证了该方法的有效性.While a sensor is in service, its measurement value can drift, and the drift value will increase with time increasing. For the performance degradation of a sensor in a non-linear system, based on modified particle filtering algorithm, this paper proposes a method to monitor sensor＇s performance degradation in real time. The system states are estimated on the basis of real-time estimation of drift. The proposed method can detect and track degradation process of a sensor in a dynamic system, and provides safeguard for the operation of dynamic system. Simulation results varify the effectiveness of the proposed method.

关 键 词：性能退化 传感器 漂移 动态系统. 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]