DocumentCode :
2206884
Title :
Robust hypothesis testing for structured uncertainty models
Author :
Rangan, Sundeep ; Poolla, Kameshwar
Author_Institution :
Dept. of Electr. Eng., Michigan Univ., Ann Arbor, MI, USA
Volume :
3
fYear :
1998
fDate :
21-26 Jun 1998
Firstpage :
1434
Abstract :
Developing uncertainty models suitable for modern robust design methods involves numerous modeling decisions regarding uncertainty structure, noise models and uncertainty bounds. We consider the problem of selecting between one of two candidate uncertainty models based on input-output data. Each uncertainty model consists of a nominal linear plant with a standard linear fractional transformation (LFT) uncertainty structure and Gaussian output noise. A classical statistical hypothesis testing performance measure is used to evaluate decision procedures. We derive a D-scaled upper bound on this performance measure, and show that this upper bound can be minimized by convex programming and ℋ filtering techniques. In addition, a general robust hypothesis testing result is derived
Keywords :
Gaussian noise; control system synthesis; convex programming; filtering theory; probability; robust control; statistical analysis; uncertain systems; ℋ filtering techniques; D-scaled upper bound; Gaussian output noise; classical statistical hypothesis testing performance measure; convex programming; decision procedures; modeling decisions; noise models; nominal linear plant; robust design methods; robust hypothesis testing; standard linear fractional transformation; structured uncertainty models; uncertainty bounds; uncertainty structure; 1f noise; Design methodology; Filtering; Gaussian noise; Noise robustness; Robust control; Testing; Uncertainty; Upper bound; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
American Control Conference, 1998. Proceedings of the 1998
Conference_Location :
Philadelphia, PA
ISSN :
0743-1619
Print_ISBN :
0-7803-4530-4
Type :
conf
DOI :
10.1109/ACC.1998.707062
Filename :
707062
Link To Document :
بازگشت