一种鲁棒故障检测与分离的参数化方法  

A Parametric Approach for Robust Fault Detection and Isolation

作　　者：李福明[1] 段广仁[1] 

机构地区：[1]哈尔滨工业大学控制理论与制导技术研究中心,黑龙江哈尔滨150001

出　　处：《控制工程》2005年第4期374-378,共5页Control Engineering of China

基　　金：国家杰出青年基金资助项目(69925308)

摘　　要：针对具有未知干扰输入的多变量线性系统,提出一种鲁棒故障检测与分离的完全参数化方法。利用最近的结果,基于Luenberger未知输入观测器矩阵的特征值及一组自由参数向量,分别给出了系统干扰解耦和故障分离的充要条件。通过适当选择满足一些约束的自由参数,仅使用单一观测器实现了鲁棒故障检测与分离设计。该方法提供了所有设计自由度。一个数值例子证明了该方法的有效性。A parametric observer-based approach for robust fault detection and isolation in multivariable linear systems with unknown disturbances is proposed.Based on a result recently,in terms of the eigenvalues of the Luenberger-type unknown input observer matrix and a group of free parameter vector,the necessary and sufficient conditions of fault isolation and disturbance decoupling are established.By appropriately choosing the free parameter satisfying some constraints,the robust fault detection and isolation scheme is realized by employing only one observer-based residual generator.The proposed approach offers the all degress off design freedom.A numerical example shows the effect of the proposed approach.

关 键 词：鲁棒故障检测与分离 参数化方法 残差产生器 干扰解耦 Luenberger观测器 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]