Model-free learning control of neutralization processes using reinforcement learning

S. SYAFIIE; F. TADEO; E. C. MARTÍNEZ

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE

Elsevier

Lugar: Oxford, UK; Año: 2006

0952-1976

The pH process dynamic often exhibits severe nonlinear and time-varying behavior and therefore cannot be adequately controlled with a conventional PI control. This article discusses an alternative approach to pH process control using model-free learning control (MFLC), which is based on reinforcement learning algorithms. The MFLC control technique is proposed because this algorithm gives a general solution for acid–base systems, yet is simple enough to be implemented in existing control hardware without a model. Reinforcement learning is selected because it is a learning technique based on interaction with a dynamic system or process for which a goal-seeking control task must be performed. This ‘‘on-the-fly’’ learning is suitable for time varying or nonlinear processes for which the development of a model is too costly, time consuming or even not feasible. Results obtained in a laboratory plant show that MFLC givesgood performance for pH process control. Also, control actions generated by MFLC are much smoother than conventional PID controller.