Co-gasification of rice husk and plastic in the presence of CaO using a novel ANN model-incorporated Aspen plus simulation

Abstract

This study presents a novel model for the simulation of co-gasification of rice husk and plastic using Aspen Plus. The new approach involved using an artificial neural network (ANN) to predict pyrolysis process involved in the gasification, purposely with the aim of providing a more realistic model. Three ANN models were developed with inputs as ultimate analysis (C, H and O), higher heating value (HHV) and pyrolysis temperature. In the gasification section, effects of temperature (600–850 °C), steam-to-feed ratio and CaO to feed ratio were examined. The developed ANN models proved to have good agreement with the actual data with a correlation coefficient (R) > 0.979. The performances of the models were also assessed by absolute mean error (MAE), root mean square error (RMSE) and mean bias error (MBE). A maximum of 69.42 vol% H2 content was obtained at 750 °C from the Aspen Plus gasification model, which was validated with experimental data and a least RMSE of 2.62 was obtained.