UNSPECIFIED (2005) Sequential Learning for Adaptive Critic Design: An Industrial Control Application. In: UNSPECIFIED.

Download (424kB)

Abstract

This paper investigates the feasibility of applying reinforcement learning (RL) concepts to industrial process optimisation. A model-free action-dependent adaptive critic design (ADAC), coupled with sequential learning neural network training, is proposed as an online RL strategy suitable for both modelling and controller optimisation. The proposed strategy is evaluated on data from an industrial grinding process used in the manufacture of disk drives. Comparison with a proprietary control system shows that the proposed RL technique is able to achieve comparable performance without any manual intervention.

Item Type:	Conference or Workshop Item (Other)
Additional Information:	Copyright © 2005 IEEE.   Reprinted from  (relevant publication info). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of NUI Maynooth ePrints and eTheses Archive's products or services.  Internal or personal use of this material is permitted.  However, permission for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. copyright laws protecting it.
Keywords:	Reinforcement learning, action-dependent adaptive critic
Academic Unit:	Faculty of Science and Engineering > Electronic Engineering
Item ID:	688
Depositing User:	Sean McLoone
Date Deposited:	24 Aug 2007
Publisher:	Institute of Electrical and Electronics Engineers
URI:
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads