Identification and predictive control of a multistage evaporator

Abstract

a b s t r a c tA recurrent neural network-based nonlinear model predictive control (NMPC) scheme in parallel with PI control loops is developed for a simulation model of an industrial-scale five-stage evaporator. Inputoutput data from system identification experiments are used in training the network using the Levenberg-Marquardt algorithm with automatic differentiation. The same optimization algorithm is used in predictive control of the plant. The scheme is tested with set-point tracking and disturbance rejection problems on the plant while control performance is compared with that of PI controllers, a simplified mechanistic model-based NMPC developed in previous work and a linear model predictive controller (LMPC). Results show significant improvements in control performance by the new parallel NMPC-PI control scheme.

Studies on parameter estimation and model predictive control of paste thickeners

“…MPC determines the control action u(t) by solving a finite horizon optimal control problem [26] and is able to handle operating constraints explicitly. MPC has been implemented in many process control applications (to name a few, the control of multistage evaporators [27] and an integrated wind/solar/reverse osmosis system [28]). …”

Application of Model Predictive Control to a Continuous Multiple‐Effect Crystallizer

“…In particulate processes, the moment balances coupled with material and energy balances typically lead to systems of differential equations with nonlinear behavior , . This nonlinear behavior is also observed in evaporative multiple‐effect processes and it has led to the development of a nonlinear variant of the model predictive control (NMPC) . Nevertheless, the NMPC requires solution of a nonconvex optimization problem, which is computationally more expensive than a quadratic convex problem to achieve a real‐time feasible solution.…”

Distributed dissipative model predictive control for process networks with imperfect communication

“…Model predictive control (MPC) is one of the few advanced control techniques which has achieved wide spread use in the chemical industry, due to its ability to handle constraints (both soft and hard), multivariable problems, and generate an optimal control action. Constraints, along with large scale and strong interactions (potentially inducing time‐scale separation) are key problems in the control of chemical process networks .…”