Data-driven fuzzy models for nonlinear identification of a complex heat exchanger |
| |
Authors: | Hacene Habbi Madjid Kidouche Mimoun Zelmat |
| |
Institution: | Applied Automation Laboratory, F.H.C., University of Boumerdès, Avenue de l’indépendance, 35000 Boumerdès, Algeria |
| |
Abstract: | This paper presents and discusses experimental results on nonlinear model identification method applied to a real pilot thermal plant. The aim of this work is to develop a moderately complex model with interpretable structure for a complex parallel flow heat exchanger which is the main component of the thermal plant using a fuzzy clustering technique. The proposed Takagi–Sugeno-type (TS) fuzzy rule-based model is derived through an iterative fuzzy clustering algorithm using a set of input–output measurements. It is shown that the identified multivariable fuzzy rule-based model captures well the key dynamical properties of the physical plant over a wide operating range and under varying operating conditions. For validation, the model is run in parallel and series-parallel configurations to the real process. The experimental results show clearly the high performance of the proposed fuzzy model in achieving good prediction of the main process variables. |
| |
Keywords: | |
本文献已被 ScienceDirect 等数据库收录! |
|