MODELING COAL-GASIFICATION WITH A HYBRID NEURAL-NETWORK

Gasification of two coals was carried out in a batch feed fluidized be d reactor at atmospheric pressure using steam as fluidizing medium. A model of coal gasification was developed, incorporating a first-princi ples model with a neural network parameter estimator. The hybrid neura l network was trained with experimental data for the two coals and gav e good performance in process modelling. A parameter for the overall r eactivity of char, namely 'active char ratio' (ACR), was identified by the neural network, as a function of gasification time and temperatur e. The ACR profile showed a strong dependence on coal type. Other para meters estimated by the neural network also reflected distinct charact eristics of the two coals. (C) 1997 Elsevier Science Ltd.