Sürdürülebilir Kalkınma Amaçları
Yayınlar
- MakaleYalnız künye2026Comparison of Zn recovery prediction from carbonate ores with machine-learning methods
Erkan, Ilker; Günen, Mehmet Akif
This study addresses the challenge of predicting zinc (Zn) recovery from carbonate ores via sodium hydroxide (NaOH) leaching. This complex process influenced by variable ore composition, surface passivation effects, and nonlinear reaction dynamics, which complicate reagent optimization and process control in hydrometallurgical operations. To tackle this, a dataset containing 422 experimental observations was compiled from previous studies, incorporating ore composition and process parameters, such as NaOH concentration, leaching time, temperature, and solid-to-liquid ratio. Four regression models (decision tree, neural network, generalized additive model, and random forest) were trained and evaluated using performance metrics, such as coefficient of determination (R2), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and symmetrical mean absolute percentage error (SMAPE). Among these, the random forest model achieved the best predictive accuracy, with R2 value of 0.8541 on the test set and the lowest error rates, demonstrating its effectiveness in capturing the complex relationships between input variables and Zn recovery. Explainable artificial intelligence, particularly SHapley additive exPlanations (SHAP) analysis, revealed that NaOH concentration, leaching time, and solid-to-liquid ratio had the most positive influence on Zn recovery, whereas elements such as Ca, Fe, and Pb had inhibitory effects. These findings align with known geochemical behavior and provide valuable insights for reagent optimization and process efficiency in leaching processes. This study demonstrates the practical potential of machine learning in mineral processing, offering a scalable framework for optimizing Zn recovery from non-sulfide ores and a data-driven approach to enhance decision-making in hydrometallurgical applications.
- MakaleAçık Erişim2025Sulfur Removal From Low-Grade Turkish Kaolin Clay
Erkan, Ilker; Alp, Ibrahim
This study investigated the effects of NaOH direct leaching for sulfur removal from a kaolin ore from the Balıkesir region, Turkey. Characterization studies were undertaken before sulfur removal studies to enlighten the structure and originate the source of sulfur. The characterization studies revealed that the ore was mainly composed of quartz, with sulfur originating from alunite minerals with opal inclusions. The leaching process was tested under varying NaOH concentrations (1.5–2 M), temperatures (95 ± 2°C), and durations (2 h) in temperature-controlled closed systems to maintain consistency. Results demonstrated complete (100%) sulfur removal from alunite under optimal conditions. However, significant mass losses (18.15%–45%) occurred because of the dissolution of kaolinite along with alunite, indicating the method's effectiveness in sulfur removal but also its potential drawbacks for kaolinite retention.
- MakaleAçık Erişim2024Exploring the utilization potential of kaolin in the Balıkesir Sındırgı region
Alp, Ibrahim; Erkan, Ilker
Natural kaolins may contain some metal cations (K+, Na+, Mg+2, Ca+2) and anions such as carbonate, phosphate, and sulfate as impurities, depending on the formation conditions. The kaolins of Turkiye generally give a high-quality white color after firing due to their low Fe2O3 content. Unfortunately, Turkiye’s kaolin deposits generally contain high levels of SO3. Since the alunite mineral, which is the source of SO3, cannot be removed from the structure by known methods, kaolins containing alunite can only be used in the white cement sector. In this study, the suitability of the kaolins of the Balıkesir Sındırgı region, which has a large part of the kaolin reserves of Turkiye, to the areas of use where kaolin is mostly used in its current state has been investigated, and the samples obtained from the region have been examined in which areas of use they are suitable for use in raw form, and suggestions have been made about the enrichment methods to be carried out by comparing with the studies in the literature.
- MakaleAçık Erişim2019Determination of the wear performance of diamond saw blades using inductively coupled plasma
Inal, Serkan; Erkan, Ilker; Aydiner, Kerim
Saw blades are one of the most used cutting tools. They compose the expensive parts of a cutting machine. Therefore, saw-blade wear is an important parameter governing the economy of the cutting process. Significant savings could be made when it is controlled effectively. In this study, a new methodology is employed for the determination of the saw-blade wear in the cutting of two types of marble. Wear of segments is determined by high-precision inductively coupled plasma method. Two types of marbles were used to investigate the wear performance of diamond-impregnated segments of circular saw-blade matrix. Taguchi mixed design L16 (43 21) is used as an experimental design and the results are evaluated statistically with Minitab. The results reveal that the specific wear rate (SWR) of Beige marble increases with the increase of the peripheral speed, traverse speed, depth of cut and down-cut mode operation. Additionally, it is demonstrated that the traverse speed and peripheral speed are the dominant cutting parameters affecting the SWR. It is also seen that similar trends are observed for Onyx marble (excluding peripheral speed). Finally, it is concluded that the proposed models can be effectively used for the estimation of the SWR.