H. Zhao et al., A nonlinear industrial model predictive controller using integrated PLS and neural net state-space model, CON ENG PR, 9(2), 2001, pp. 125-133
Model predictive control (MPC) technology has been well developed and succe
ssfully applied in the refinery and petrochemical process industries over t
he last 20 years. Recent development has been focused on nonlinear MPC and
robust MPC technologies because new challenges have been encountered in the
polymer and chemical industries where many processes show strong nonlinear
ity and uncertainty. This paper presents a nonlinear industrial model predi
ctive controller, recently developed by Aspen Technology Inc. This MPC cont
roller uses a nonlinear, state-space, integrated partial least-squares (PLS
) and neural net model (Zhao, Guiver and Sentoni, American control conferen
ce, Philadelphia, PA, USA, 1998), and a multi-step, constrained. Newton-typ
e optimization algorithm (Oliveira and Biegler, Automatica, 31 (2) (1995) 2
81-286). It results in a robust and cost-effective industrial nonlinear MPC
controller. A pH reactor example and a successful industrial application i
n NOx emission control of a power plant are presented to demonstrate the ca
pability of this controller. (C) 2001 Elsevier Science Ltd. All rights rese
rved.