An adaptive PID controller is created using mix locally recurrent neural networks.
•
A sequential learning mechanism is derived for on line adaptation of the gains.
•
Fast, stable and accurate training algorithm compared to conventional gradient based methods.
•
The implemented controller is robust due to its on line learning capabilities.
NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.