Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
3 results
Search Results
Article Citation - WoS: 1Citation - Scopus: 1Predictive Modeling and SHAP-Based Interpretability of Manganese and Iron Dissolution in Multi-Acid Leaching Systems Using Hybrid Machine Learning(Multidisciplinary Digital Publishing Institute (MDPI), 2026) Top, Soner; Altiner, Mahmut; Kursunoglu, Sait; Kuzu, EmrahHydrometallurgical leaching processes contain complex and nonlinear parameter interactions that are difficult to capture with conventional empirical models. In this study, a multiple hybrid machine learning approach was developed to predict manganese (Mn) and iron (Fe) dissolution efficiency in leaching systems and performed using sulfuric acid (H2SO4), hydrochloric acid (HCl), and nitric acid (HNO3). A large-format dataset consisting of 204 independent leaching experiments was generated in which acid type, acid concentration (0.5-5 M), temperature (25-90 degrees C), solid/liquid ratio (100-200 g/L), leaching time (1-4 h), and eight different reducing agent types were systematically varied. XGBoost, LightGBM, CatBoost, and Random Forest algorithms were individually trained and subsequently combined with a Soft Voting Ensemble architecture. Hyperparameters were optimized using the RandomizedSearchCV method with 3-fold cross-validation. The XGBoost model achieved the highest prediction accuracy for Mn dissolution (R-2 = 0.8993, RMSE = 8.06%), while CatBoost demonstrated the best performance in Fe dissolution (R-2 = 0.8415, RMSE = 4.43%). SHAP analysis suggested that the dosage and type of reducing agents are the most influential predictive features for Mn dissolution, while acid molarity and temperature were identified as the dominant predictors for Fe leaching. Friedman test confirmed that performance differences among both Mn and Fe models were statistically significant (Mn: chi(2) = 32.76, p < 0.001; Fe: chi(2) = 25.96, p < 0.001). The developed models contribute significantly to hydrometallurgical process optimization by predicting the nonlinear effects of leaching parameters on metal dissolution with high accuracy. This study presents a comprehensive and interpretable machine learning framework supported by an extensive experimental dataset, a substantial portion of which has not been previously utilized or comparatively analyzed within a unified multi-acid framework, enabling systematic modeling of selective Mn-Fe dissolution across multiple acid systems and reducing agents.Article Citation - WoS: 11Citation - Scopus: 12Production of Mn3O4 Nanoparticles From a Manganiferous Iron Ore via Reductive Leaching, Precipitation, and Calcination(Elsevier, 2022-02) Altiner, Mahmut; Top, Soner; Bouchekrit, Chafia; Kursunoglu, SaitThe synthesis of Mn3O4 nanoparticles from a manganiferous iron ore through reductive leaching, precipitation, and calcination was investigated. The reductive leaching results showed that Mn (99.9%) was almost completely extracted into the leaching solution along with a substantial amount of Mg (99.9%), Al (99.5%), Ca (80%), and Fe (22.9%) under the following conditions: 30 g/L tartaric acid as a reducing agent, 1 M HCl solution, leaching temperature of 90 ?, and leaching duration of 3 h. In the first precipitation step, Fe and Al were expelled from the pregnant leach solution by the addition of NaOH prior to conducting the precipitation experiments for the production of manganese carbonate (MnCO3) particles from the purified solution. In the second precipitation step, MnCO3 particles were produced using sodium carbonate (Na2CO3) as the precipitating agent. The effects of parameters such as reaction temperature, Na2CO3 concentration, and experimental duration were investigated using the Taguchi approach. Manganse(II) was precipitated in the form of MnCO3 particles (97.4%) under the following conditions: a temperature of 30 ?C, Na2CO3 concentration of 0.014 mol/L, and duration of 30 min. The precipitate was observed to have a structure similar to that of rhodochrosite (MnCO3). Thermogravimetric/ differential thermal analyses were subsequently performed in three different atmospheres (air, oxygen, and nitrogen) to select a suitable atmosphere for calcination. The experimental results indicated the formation of hausmannite (Mn3O4) with a purity of 97.5% Mn3O4, 0.42% MgO, 1.66% CaO, and 0.34% FeO. The specific surface area, particle size, Curie temperature, magnetisation, coercivity, and remanence ratio of the final product obtained via 3 h of calcination at 350 C were estimated to be 133.3 m(2)/g, < 142.2 nm, 56 K, 10.10 Am-2/kg, 0.35 T, and 0.19, respectively. The characterisation results revealed the excellent low-temperature ferromagnetic properties of the produced Mn3O4 nanoparticles.Article Manganzı Demir Cevherinden Manganın Çözündürülmesinde Farklı İndirgeme Maddelerinin Etkisi(Chamber of Mining Engineers of Turkey, 2022-06-26) Top, S.; Altiner, Mahmut; Kursunoglu, SaitIIn this paper, the manganese extraction from a manganiferous iron ore was investigated using reductive leaching. Various chemicals were used as a reducing agent to leach manganese selectively from the ore in the presence of sulfuric acid (H2SO4) solution. Firstly, optimum dissolution values were determined for selective manganese dissolution without using a reducing agent. As it was aimed at the selective extraction of manganese from the ore, the reductive leaching tests were conducted by adding the reducing agents under the following optimal parameters: a leaching time of 1 h, a stirring speed of 300 rpm, a temperature of 70°C, a sulfuric acid concentration of 1 M where the ore was leached with an extraction ratio of 11.54% Mn and 2.16% Fe. Manganese was dissolved with high efficiencies (up to 97.46%) from the ore by using different organic compounds (tartaric acid (C<inf>4</inf>H<inf>6</inf>O<inf>6</inf>), oxalic acid (C<inf>2</inf>H<inf>2</inf>O<inf>4</inf>), citric acid (C<inf>6</inf>H<inf>8</inf>O<inf>7</inf>), glucose (C<inf>6</inf>H<inf>12</inf>O<inf>6</inf>), sucrose (C<inf>12</inf>H<inf>22</inf>O<inf>11</inf>), and maleic acid (C<inf>4</inf>H<inf>4</inf>O<inf>4</inf>)) as the reducing agents. © 2022 Elsevier B.V., All rights reserved.