Title :
Residual Generation from Principal Component Models for Fault Diagnosis in Linear Systems - Part II: Extension to Optimal Residuals and Dynamic Systems
Author_Institution :
Sch. of Inf. Technol., George Mason Univ., Fairfax, VA
Abstract :
The generation of enhanced (structured) residuals from PC models, both by algebraic transformation and by direct structured modeling, was reviewed in Part I of this paper. In Part II, some recent results on residual optimization are included. Extensions to dynamic systems are discussed. The new concept of dynamic redundancy is introduced, followed by an algorithm to simultaneously estimate the system order and the number of linear relations. The generation of enhanced (and optimized) residuals is revisited in the dynamic framework and explained in the light of dynamic redundancy. A simple example is given to illustrate the new concepts
Keywords :
fault diagnosis; linear systems; principal component analysis; redundancy; dynamic redundancy; dynamic systems; fault diagnosis; linear system; optimal residuals; principal component analysis; residual generation; structured residuals; Constraint optimization; Fault diagnosis; Information technology; Linear systems; Modeling; Performance analysis; Principal component analysis; Redundancy; System identification; Testing;
Conference_Titel :
Intelligent Control, 2005. Proceedings of the 2005 IEEE International Symposium on, Mediterrean Conference on Control and Automation
Conference_Location :
Limassol
Print_ISBN :
0-7803-8936-0
DOI :
10.1109/.2005.1467088