In this paper, an affine neural model is used to model the unknown part of SISO processes with un-modeled actuator dynamics. It is assumed that a partially known first principlesbased model of the process, which is invertible with respect to the unknown part, is available. Using this available knowledge, I/O training data of the process, and affine neural networks, a serial gray-box model is generated which is suitable for applying feedback linearization. Hence, the resulting nonlinear controller works in a large operating region. The superiority of the gray-box over the black-box approach is investigated for a fermentor using the experimental data borrowed from the literature. Simulation results of our case study show that the proposed affzne gray-box method is superior to the conventional agfine black-box method and preserves extrapolation property.
Bazaei,A. and Johari Majd,V. (2006). Application of affine gray-box neural models for nonlinear control of chemical processes. Iranian Journal of Chemical Engineering (IJChE), 3(1), 65-76.
MLA
Bazaei,A. , and Johari Majd,V. . "Application of affine gray-box neural models for nonlinear control of chemical processes", Iranian Journal of Chemical Engineering (IJChE), 3, 1, 2006, 65-76.
HARVARD
Bazaei A., Johari Majd V. (2006). 'Application of affine gray-box neural models for nonlinear control of chemical processes', Iranian Journal of Chemical Engineering (IJChE), 3(1), pp. 65-76.
CHICAGO
A. Bazaei and V. Johari Majd, "Application of affine gray-box neural models for nonlinear control of chemical processes," Iranian Journal of Chemical Engineering (IJChE), 3 1 (2006): 65-76,
VANCOUVER
Bazaei A., Johari Majd V. Application of affine gray-box neural models for nonlinear control of chemical processes. IJChE, 2006; 3(1): 65-76.
