MIMO Nonlinear Process Control Using Neuro-Fuzzy System

This study applied ANNs and NFS in modeling and control of a real MIMO industrial nonlinear process. Actually, this work presented a comparative study using ANNs and CoActive Neuro-Fuzzy Inference System (CANFIS) in modeling a quite complicated MIMO nonlinear temperature process of roller kiln used in ceramic tile manufacturing line. By this study, we proved that CANFIS is better suited for modeling this temperature process, therefore, CANFIS model was used to represent the studied plant in control phase of this study. In next step, an ANNs controller has been designed to control the above-mentioned temperature process using a feedback control diagram. The designed controller's performance is then tested by a Visual C++ project and the resulting numerical data showed that this controller can work accurately and reliably even when the roller kiln setpoint temperature set changes. The defects occurring in finished ceramic tiles that partially or fully involve performance of kiln temperature process will be minimized if the CANFIS modeling and ANNs controller is used.

Autorentext

Dr. Nguyen Quoc Dinh got PhD in Asian Institute of Technology (AIT), Bangkok, Thailand. He is now Lecturer at Faculty of Electrical Engineering, Danang University of Technology, Viet Nam.