Gasification of food waste in supercritical water: An innovative synthesis gas composition prediction model based on Artificial Neural Networks

The present study intends to develop multi-layered feed-forward back-propagation algorithm based artificial neural network (FFBPNN) models to predict the synthesis gas (SG) compositions (H-2, CH4, CO & CO2) and yields (mol/kg) for supercritical water gasification (SCWG) of food wastes. Such models are trained with Levenberg-Marquardt (L-M) algorithm, minimized using gradient descent approach and tested with real-time experimental datasets obtained from literature. Moreover, to determine an optimal form of the neural network for a typical non-catalytic SCWG process, a trial and error approach involving multiple combinations of transfer functions and neurons in the network layers is performed. The predicted values of SG compositions yield delivered by the FFBPNN models are in line with the experimental datasets converging to a mean squared error (MSE) value below 0.300 range and coefficient of determination (R-2) above 98%. Best prediction accuracy is achieved for CO yield prediction characterized by a least MSE of 0.022 and highest traintest R-2 of 0.9942-0.9939. The performance of the developed FFBPNN models can be arranged on the basis of MSE as (ann7)(CO) < (ann6)(CH4) < (ann5)(H2) < (ann8)(CO2) and on the basis of testing R-2 as (ann7)(CO) > (ann6)(CH4) > (ann5)(H2) > (ann8)(CO2). (C) 2021 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

Automated summary

This study developed FFBPNN models based artificial neural network to predict the compositions and yields of synthesis gas in supercritical water gasification. The models showed good prediction accuracy and performance when trained and tested with experimental datasets.