Model-Free Intelligent Control of Neutralization Processes: Experiments on a Laboratory Plant.

ERNESTO CARLOS MARTINEZ; FERNADO TADEO,; SYAFIIE SYAM,

Huelva

Congreso; III Simposio sobre control inteligente; 2005

An alternative approach to pH process control using Model-Free Intelligent Control (MFIC) is proposed, based on reinforcement learning algorithms. Reinforcement learning 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. This paper presents some experiments on a laboratory plant to check the effect of MFIC parameters on closed-loop performance for pH process control for NaCH3COO-HCl.