Hybrid adaptive fuzzy and neural network controller for the molten steel level control in strip casting processes

Article type: Research Article

Authors: Chen, Hung-Yi

Affiliations: Department of Mechanical Engineering, Ming Chi University of Technology, Taishan, New Taipei City, Taiwan

Note: [] Corresponding author. Hung-Yi Chen, Department of Mechanical Engineering, Ming Chi University of Technology, No. 84, Gungjuan Road, Taishan, New Taipei City, 243, Taiwan. E-mail: hychen@mail.mcut.edu.tw

Abstract: The molten steel level control of strip casting process has the properties of nonlinear uncertainty and time-varying characteristics, hence, it is difficult to establish an accurate process model for designing a model-based controller to monitor the strip quality. This study develops a hybrid model-free adaptive fuzzy and neural network controller (HAFNC) which combines an adaptive rule with fuzzy and neural network control to overcome the difficulty. The proposed control strategy has online learning ability for responding to the system's nonlinear and time-varying behaviors during the molten steel level control. Since this model-free controller has simple control structure and small number of control parameters, it is easy to implement. Numerical results based on semi-experimental system dynamic model and parameters are executed to show the control performance of the proposed intelligent controller.

Keywords: Molten steel level control, strip casting process, hybrid adaptive fuzzy and neural network control

DOI: 10.3233/IFS-141269

Journal: Journal of Intelligent & Fuzzy Systems, vol. 27, no. 6, pp. 3123-3130, 2014