Modeling of Gaseous Reduction of Iron Oxide Pellets Using Machine Learning Algorithms, Explainable Artificial Intelligence, and Hyperparameter Optimization Techniques

In this study, a novel application of machine learning (ML) is introduced to pellet modeling in the intricate non‐catalytic gas–solid reaction of direct reduction of iron oxide in the steel industry. Twenty ML models are developed using four algorithms: multilayer perceptron neural networks (MLPNN), radial basis function neural network (RBFNN), support vector regression, and random forest (RF). Hyperparameter optimization is conducted using Bayesian algorithms, random search, and grid search. The optimum model achieves a mean squared error test of 0.0052 with random RF for the larger dataset (872 samples), while smaller datasets (132, 225, and 242 samples) produce optimum models with MLPNN and RBFNN. Hyperparameters vary between the larger datasets and the smaller datasets. The models offer insight into the complex interactions among variables, including time, temperature, gas composition, hematite composition, pellet radius, and initial pellet porosity, influencing the metallization degree. In this study, the significant role of time and temperature is emphasized, as revealed by explainable artificial intelligence using Shapley additive explanation analysis that utilizes the game theory, and the effects of pellet modeling parameters are elucidated through 3D plots, particularly highlighting the impact of changing H 2 /CO proportion on metallization degree and carbon deposit.