1-05　Development of Estimation Method of Kinetic Parameters in Distributed Activation Energy Model by Using Neural Network and Applicability to the Prediction of Coke Gasification Reaction

Abstract

The distributed Activation Energy Model (DAEM) is widely used for the analysis of pyrolysis or gasification of coal and coke. We proposed an estimation method of kinetic parameters in DAEM using a neural network. For validation, the kinetic parameters were estimated by applying the proposed method and the conventional method to the experimental data of CO₂ gasification of coke. In addition, the obtained kinetic parameters were used to predict progress on the conversion of coke, and the prediction accuracy was compared between the proposed method and the conventional method. As a result, the prediction accuracy of the proposed method was higher than that of the conventional method.