Adaptive Neural Control of a Simple Effect Evaporator

I.S. Baruch and C.R. Mariaca G. (Mexico)

Keywords

Adaptive control, integral terms, systems identification and state estimation, recurrent neural networks, discrete timedelay system, and simple effect evaporator.

Abstract

A direct adaptive neural control scheme with single and double I-term is proposed to be applied for multivariable plant. The control scheme contains two Recurrent Trainable Neural Network (RTNN) models. The first RTNN is a plants parameter identifier and state estimator. The second RTNN is a feedback feedforward controller with I-terms. The good performance of the adaptive neural control with I-terms is confirmed by closed-loop systems analysis, and by simulation results, obtained with simple effect evaporator multivariable plant, corrupted by noise and affected by small unknown input time delay.

Important Links:



Go Back