DocumentCode
848624
Title
The strong consistency of the stochastic gradient algorithm of adaptive control
Author
Chen, H. ; Caines, P.
Author_Institution
Institute of Systems Science, Beijing, China
Volume
30
Issue
2
fYear
1985
fDate
2/1/1985 12:00:00 AM
Firstpage
189
Lastpage
192
Abstract
By use of a technique due to Chen, sufficient conditions are established for the strong consistency of the stochastic gradient (SG) algorithm for MIMO ARMAX stochastic systems without monitoring. This result is then used in conjunction with the method of disturbed adaptive controls introduced in [1], [2]. Hence it is shown that the SG algorithm generates strongly consistent parameter estimates while it is operating as a part of the SG algorithm of adaptive control of Goodwin, Ramadge, and Caines.
Keywords
Adaptive control, linear systems; Autoregressive moving-average processes; Gradient methods; Linear systems, stochastic; Multivariable systems; Stochastic systems, linear; Adaptive control; Condition monitoring; Control systems; Feedback control; MIMO; Parameter estimation; Programmable control; Stochastic processes; Stochastic systems; Sufficient conditions;
fLanguage
English
Journal_Title
Automatic Control, IEEE Transactions on
Publisher
ieee
ISSN
0018-9286
Type
jour
DOI
10.1109/TAC.1985.1103906
Filename
1103906
Link To Document