Development of a Matlab(R) Toolbox for the Design of Grey-Box Neural Models

Abstract

A Matlab Toolbox is developed for the design, construction and validation of grey-box neural network models. This toolbox, available in www.diinf.usach.cl=gacuna has been tested in simulations with a continuously stirred reactor process. The grey-box model performs well for validation data with 5% additive gaussian noise for one-step-ahead (OSA) and model-predictive-output (MPO) estimations.