Artificial neural network model of molten carbonate fuel cells: Validation on experimental data

Abstract

Summary This article shows the teaching processes of artificial neural networks that are used to model the molten carbonate fuel cell (MCFC). Researchers model MCFCs to address a variety of issues across a range of complexities, from simply gauging the effect of temperature through to a complete model with 14 input parameters. The architecture of the model is a triple layer network with one hidden layer containing three neurons. The activation function used for the hidden layer was a hyperbolic tangent, with the last layer being based on linear function. We produced various network configurations, mostly networks containing one hidden layer. Models map the work of a real fuel cell with an average error in the range of 2.4% to 4.6%. The model we created guided the optimization of the thermal‐flow and construction parameters of the MCFC. Commercially available software was used to build the model and optimize the operating parameters. The selected objective functions were the efficiency of electricity production and the power density obtained from the cell's surface. The results obtained serve as pointers for possible changes in fuel cell operation and could lead to some structural changes being made.

Modeling the effect of non‐linear process parameters on the prediction of hydrogen production by steam reforming of bio‐oil and glycerol using artificial neural network

“…ANN has been effectively applied in modeling various chemical processes. [31][32][33] Hossain et al 28 employed ANN for modeling the production of hydrogen-rich syngas by dry reforming of methane. The multilayer perceptron (MLP) and radial basis function (RBF) neural networks were robust in predicting the hydrogen-rich syngas production by the dry reforming of methane.…”

“…ANN has been effectively applied in modeling various chemical processes 31‐33 . Hossain et al 28 employed ANN for modeling the production of hydrogen‐rich syngas by dry reforming of methane.…”

Exploring the direct influence of control parameters of experimental facility for fuel cells based on improved generalized regression neural network

“…Neural network algorithms are used extensively in a variety of FCs. Milewski et al 32 showed the teaching processes of ANNs that were used to model the molten carbonate FC. A variety of issues across a range of complexities were addressed, from simply gauging the effect of temperature through to a complete model with 14 input parameters.…”

Boosting the power density of two‐chamber microbial fuel cell: Modeling and optimization

“…The results showed that the LSTM network was successfully applied to the task of predicting the performance degradation of the PEMFC 32 . Also, MCFC “molten carbonate fuel cell” is modeled using artificial neural networks with an accuracy of 2.4% to 4.6% 33 . In a recent study, Rezk et al, 34 investigated the accuracy of the modeling process of a SOFC.…”