By Topic

Getting weights to behave themselves: achieving stability and performance in neural-adaptive control when inputs oscillate

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Macnab, C.J.B. ; Dept. of Electr. & Comput. Eng., Calgary Univ., Alta., Canada

Local basis functions offer computational efficiency when used in nonlinear adaptive control schemes. However, commonly used robust weight (parameter) update methods do not result in acceptable performance when applied to underdamped systems. This is because persistent oscillation in the inputs encourages severe weight drift, in turn requiring large robust terms that significantly limit the performance. In particular, the methods of leakage, c-modification, dead/one, and weight projection sacrifice performance to halt this weight drift. In contrast, it is observed (in simulations) that application of the proposed method halts the weight drift without sacrificing the performance.

Published in:

American Control Conference, 2005. Proceedings of the 2005

Date of Conference:

8-10 June 2005