Predicting the effect of bed materials in bubbling fluidized bed gasification using artificial neural networks (ANNs) modeling approach

• Published in: Fuel (Guildford) 2020-04, Vol.266, p.117021, Article 117021
• Main Authors: Serrano, Daniel, Golpour, Iman, Sánchez-Delgado, Sergio
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural network; Artificial neural networks; Back propagation networks; Bayesian analysis; Bed material; Bubbling; Bubbling fluidized bed; Carbon dioxide; Carbon monoxide; Computer simulation; Fluidized beds; Gas composition; Gasification; Learning algorithms; Machine learning; Mathematical models; Methane; Network topologies; Neural networks
• ISSN: 0016-2361; 1873-7153
• DOI: 10.1016/j.fuel.2020.117021

•ANNs are used to predict biomass gasification results in bubbling fluidized beds.•The effect of using different bed materials is included in the model.•A large number of network topologies are simulated.•ANNs differentiate the different bed materials predicting the gas composition accurately. The effect of different bed materials was included a as new input into an artificial neural network model to predict the gas composition (CO2, CO, CH4 and H2) and gas yield of a biomass gasification process in a bubbling fluidized bed. Feed and cascade forward back propagation networks with one and two hidden layers and with Levenberg-Marquardt and Bayesian Regulation learning algorithms were employed for the training of the networks. A high number of network topologies were simulated to determine the best configuration. It was observed that the developed models are able to predict the CO2, CO, CH4, H2 and gas yield with good accuracy (R2 > 0.94 and MSE