Prediction of Solid Conversion Process in Direct Reduction Iron Oxide Using Machine Learning

Abstract

The direct reduction process has been developed and investigated in recent years due to less pollution than other methods. In this work, the first direct reduction iron oxide (DRI) modeling has been developed using artificial neural networks (ANN) algorithms such as the multilayer perceptron (MLP) and radial basis function (RBF) models. A DRI operation takes place inside the shaft furnace. A shaft furnace reactor is a gas-solid reactor that transforms iron oxide particles into sponge iron. Because of its low environmental pollution, the MIDREX process, one of the DRI procedures, has received much attention in recent years. The main purpose of the shaft furnace is to achieve the desired percentage of solid conversion output from the furnace. The network parameters were optimized, and an algorithm was developed to achieve an optimum NN model. The results showed that the MLP network has a minimum squared error (MSE) of 8.95 × 10−6, which is the lowest error compared to the RBF network model. The purpose of the study was to identify the shaft furnace solid conversion using machine learning methods without solving nonlinear equations. Another advantage of this research is that the running speed is 3.5 times the speed of mathematical modeling.

Evaluation of hydrogen production via steam reforming and partial oxidation of dimethyl ether using response surface methodology and artificial neural network

“…To achieve this objective, all data have been normalized within the range of 0 to + 1 using Eq. ( 4 ): where X norm represents the normalized data, X is the input variable, and X max and X min correspond to the maximum and minimum values of the data, respectively 32 . To determine network parameter values, the projected network error should be kept to a minimum for every step of the mean square error (MSE) in every iteration during network training.…”

“…R 2 close to 1 and near-zero MSE, MAE, and MAPE values imply network accuracy. MSE, MAE, MAPE, R 2 , and AARD are obtained as follows 32 – 34 : where Y predicted , Y actual , Y mean , and n denote the predicted Y value using a neural network, the actual Y value, the average Y value, and the number of data points, respectively.…”

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

“…[ 1,2 ] Nowadays, AI is employed in the steel industry across different domains of direct reduction of iron oxide (DRI). [ 3–5 ] The DRI is recognized as one of the most intricate solid–fluid systems, [ 6 ] marked by its multiscale nature, [ 7 ] multiparticle system, [ 8 ] complex kinetics, [ 9 ] and the multitude of reactions. [ 9 ] Consequently, the employment of AI not only allows for a smoother pathway but also enables the apprehension of certain aspects that are unattainable through other means.…”

“…In the realm of AI, Hosseinzadeh et al [ 3 ] constructed a model using multilayer perceptron neural network (MLPNN) and radial basis function neural network (RBFNN) algorithms to predict solid conversion in the shaft furnace. This model is developed on simulation data from Parisi and Laborde, [ 17 ] Nouri et al, [ 18 ] and Mirzajani et al [ 19 ] Utilizing this dataset, Hosseinzadeh and Kasiri [ 5 ] showcased the impressive accuracy attainable when employing support vector regression (SVR).…”

Investigation of Pellet Shape on the Hydrogen Reduction of Iron Oxide Using Mathematical Modeling and Image Processing

“…Yang et al [ 34 ] used an artificial neural network to forecast the end‐point carbon concentration in the EAF steelmaking process. Hosseinzadeh et al [ 35 ] used neural networks in the DRI. They created a neural network that can compute the amount of solid conversion in the direct reduction process using four MIDREX shaft furnaces.…”