Model-Free Intelligent Control with Gain Adaptation Applied to pH Control.

ERNESTO CARLOS MARTINEZ; FERNADO TADEO,; SYAFIIE SYAM,

León

Congreso; 4th International Workshop on practical applications of agents and multiagents systems; 2005

This article presents a solution to pH control based on Model-Free Intelligent Control (MFIC) using Reinforcement Learning (RL). It is proposed to use agents based on MFIC to control chemical process, when a process model is not available. This technique is proposed because the algorithm gives a general solution for acid-base system, yet simple enough to be implemented in existing control hardware. RL is selected, because it is a learning technique based on online learning with a system or process for which a goal-seeking control task must be performed. This online learning makes it adequate for time varying or nonlinear processes for which the development of a model is too costly, time consuming or even non feasible. The application on a pH process at laboratory level shows that the proposed MFIC learns to control adequately the process.