Experimental and Simulation Studies on Hematite Interaction with Na-Metasilicate Pentahydrate.

Iron ore is a fundamental pillar in construction globally, however, its process is highly polluting and deposits are becoming less concentrated, making reusing or reprocessing its sources a sustainable solution to the current industry. A rheological analysis was performed to understand the effect of sodium metasilicate on the flow curves of concentrated pulps. The study was carried out in an Anton Paar MCR 102 rheometer, showing that, in a wide range of dosages, the reagent can reduce the yield stress of the slurries, which would result in lower energy costs for transporting the pulps by pumping. To understand the behavior observed experimentally, computational simulation has been used by means of quantum calculations to represent the metasilicate molecule and the molecular dynamics to study the adsorption of metasilicate on the hematite surface. It has been possible to obtain that the adsorption is stable on the surface of hematite, where increasing the concentration of metasilicate increases its adsorption on the surface. The adsorption could be modeled by the Slips model where there is a delay in adsorption at low concentrations and then a saturated value is reached. It was found that metasilicate requires the presence of sodium ions to be adsorbed on the surface by means of a cation bridge-type interaction. It is also possible to identify that it is absorbed by means of hydrogen bridges, but to a lesser extent than the cation bridge. Finally, it is observed that the presence of metasilicate adsorbed on the surface modifies the net surface charge, increasing it and, thus, generating the effect of dispersion of hematite particles which experimentally is observed as a decrease in rheology.

Prediction of Sinter Properties Using a Hyper-Parameter-Tuned Artificial Neural Network.

The present work aims at performing prediction validation for the physical properties of coke layered and nonlayered hybrid pelletized sinter (HPS) using artificial neural networks (ANNs). Physical property analyses were experimentally performed on the two HPS products. The ANN model was then trained to obtain the best prediction results with the grid-search hyper-parameter tuning method. The learning rate, momentum constant, and the number of neurons varied over specified ranges. The binary variable conversion was utilized to assess the two sintering processes. The nonlayered HPS product of 4 mm micropellets at basicity 1.75 and using 8% coke shows a good combination of physical properties, whereas HPS of 4 mm micropellets at 1.5 basicity using 4% coke as fuel and 2% coke as layering gives a radical improvement in physical properties. The yield of the HPS product is 96.07%, with the shatter index (SI), tumbler index (TI), and abrasion index (AI) values being 86.12, 79.60, and 5.74%, respectively. Hence, HPS can be preferred by implementing the layering of coke powder. The prediction analyses showed that the multilayer perceptron model (MLP) network with a 4-29-5 structure showed prediction accuracies of over 99.99% and a mean squared error (MSE) of 2.87 × 10-4. It verifies the accuracy and prediction effectiveness of the hyper-parameter-tuned ANN model.