Neurocontrol of a ball mill grinding circuit using evolutionary reinforcement learning

Simple item page
dc.contributor.authorConradie A.V.E.
dc.contributor.authorAldrich C.
dc.date.accessioned2011-05-15T15:53:56Z
dc.date.available2011-05-15T15:53:56Z
dc.date.issued2001
dc.description.abstractA ball mill grinding circuit is a nonlinear system characterised by significant controller interaction between the manipulated variables. A rigorous ball mill grinding circuit is simulated and used in its entirety for the development of a neurocontroller through the use of evolutionary reinforcement learning. Reinforcement learning entails learning to achieve a desired control objective from direct cause-effect interactions with a simulated process plant. The SANE (symbiotic adaptive neuro-evolution) algorithm is able to learn implicitly to eliminate controller interactions in the grinding circuit by taking a plant wide approach to controller design. The ability of the neurocontroller to maintain high performance in the presence of large disturbances in feed particle size distribution and ore hardness variations is demonstrated. The generalisation afforded by the SANE algorithm in dealing with considerable uncertainty in its operating environment attests to a large degree of controller autonomy. © 2001 Published by Elsevier Science Ltd. All rights reserved.
dc.description.versionArticle
dc.identifier.citationMinerals Engineering
dc.identifier.citation14
dc.identifier.citation10
dc.identifier.issn8926875
dc.identifier.other10.1016/S0892-6875(01)00144-3
dc.identifier.urihttp://hdl.handle.net/10019.1/8902
dc.titleNeurocontrol of a ball mill grinding circuit using evolutionary reinforcement learning
dc.typeArticle
Files
Collections
Stellenbosch University - Scopus Publications