Artificial Neural Networks for Predicting Hydrogen Production in Catalytic Dry Reforming: A Systematic Review

Dry reforming of hydrocarbons, alcohols, and biological compounds is one of the most promising and effective avenues to increase hydrogen (H-2) production. Catalytic dry reforming is used to facilitate the reforming process. The most popular catalysts for dry reforming are Ni-based catalysts. Due to their inactivation at high temperatures, these catalysts need to use metal supports, which have received special attention from researchers in recent years. Due to the existence of a wide range of metal supports and the need for accurate detection of higher H-2 production, in this study, a systematic review and meta-analysis using ANNs were conducted to assess the hydrogen production by various catalysts in the dry reforming process. The Scopus, Embase, and Web of Science databases were investigated to retrieve the related articles from 1 January 2000 until 20 January 2021. Forty-seven articles containing 100 studies were included. To determine optimal models for three target factors (hydrocarbon conversion, hydrogen yield, and stability test time), artificial neural networks (ANNs) combined with differential evolution (DE) were applied. The best models obtained had an average relative error for the testing data of 0.52% for conversion, 3.36% for stability, and 0.03% for yield. These small differences between experimental results and predictions indicate a good generalization capability.

Automated summary

This study conducted a systematic review and meta-analysis to evaluate the hydrogen production by various catalysts in the dry reforming process. By combining artificial neural networks with differential evolution, the best models obtained showed small differences between experimental results and predictions, indicating a good generalization capability.