Analysis and Prediction of Hydrogen Yield Using Artificial Neural Networks
This study aims to design a reliable prediction model for H$_2$ production by steam methane reforming using artificial neural networks (ANN). To achieve this, experimental data related to this process were first analyzed and then used to develop an ANN model implemented in Python. Model construction was carried out in three stages: network architecture design, training, and performance evaluation. Data analysis revealed that temperature has the dominant influence on the H$_2$ yield, followed by space time. The resulting ANN model, with an optimal (2–5–1) architectur