Regresar

MPC of a four-stage grape juice evaporator based on an adaptive neural model

Abstract:

The four-stage evaporator is the core of the process in the manufacture of concentrated grape juice. The dynamic features of this process are very complex due to inputs/outputs constraints, time delays, loop interactions and the persistent unmeasured disturbances that affect it. This paper addresses the non-linear control of an industrial-scale multiple-effect evaporator by means of a model pbkp_redictive control (MPC) based on a neural network model (NNM). This strategy allows it on one hand, overcome the classical control systems limitations and, by the other that the neural controller continue learning during the plant operation. The achieved results allow us to conclude that the developed neural model pbkp_redictive control is adequate to control effectively a four-effect evaporator to concentrate grape juice with different characteristics; its application at industrial scale is possible in the future. © 2009 Elsevier B.V. All rights reserved.