Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
4 results
Search Results
Article Citation - Scopus: 3Soft Computing Implementations for Evaluating Los Angeles Abrasion Value of Rock Aggregates From Kütahya, Turkey(Szechenyi Istvan University, 2024-02-28) Köken, E.The Los Angeles abrasion value (LAAV) of rocks is a critical mechanical aggregate property for designing road infrastructures and concrete quality. However, the determination of this critical aggregate property is labour-intensive and time-consuming and thus, in the literature, there are many predictive models to estimate the LAAV for different rock types. However, most of them are based on classical regression analyses, limiting their broader usage. In this study, several soft computing analyses are performed to develop robust predictive models for the evaluation of LAAV of rocks in the Ilıca region (Kütahya – Turkey). The main motivation for implementing soft computing analyses is that precise predictive models might be useful when exploring suitable rock types that are manufactured in crushing–screening plants. For this purpose, a comprehensive laboratory schedule was established to obtain some inputs for the evaluation of LAAV. As a result of the soft computing analyses, four robust predictive models are developed based on artificial neural networks (ANN), multiple adaptive regression spline (MARS), adaptive neuro-fuzzy inference system (ANFIS) and gene expression programming (GEP) methodologies. The performance of the proposed models is investigated by some statistical indicators such as R2 and RMSE values and scatter plots. As a result, the ANFIS-based predictive model turns out to be the best alternative to estimate the LAAV of the investigated rocks. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 1On the Variation in Several Rock Properties due to Magnesium Sulfate Weathering Tests ‒ A Case Study for Limestones(International Multidisciplinary Scientific Geoconference, 2019-06-20) Köken, E.Contributions to the behavior of rock materials under various conditions provide a practical knowledge about issues relating the performance and long-term serviceability of rocks. In this study, various limestones with varying textural features were investigated in terms of their resistance against magnesium sulfate weathering tests. For this purpose, initial physico-mechanical properties of limestones were determined. Then, rock materials were subjected to magnesium sulfate weathering tests (up to 20 cycles) and the variation in physico-mechanical properties were determined for each rock type. As a result of laboratory tests, compared to initial rock properties, effective porosity (ne, %) increased in the range of 3% ‒ 14% and 12% ‒ 35% after 10th and 20th magnesium sulfate weathering cycles, respectively. Uniaxial compressive strength of rocks (UCS, MPa) decreased by 9% ‒ 24% after 10th cycles and by 32% – 58% after 20th cycles. Brazilian tensile strength of rocks (BTS, MPa) decreased in the range of 7% ‒ 19% and 20% ‒ 49% after 10th and 20th cycles, respectively. Similar to the variations in UCS and BTS, Tangential Young Modulus (Eti, GPa) also decreased at a rate of 13% ‒ 28% and 23% ‒ 64% after 10th and 20th cycles, respectively. However, the values of Tangential Poisson’s Ratio (vti) fluctuated with progressive accelerated weathering cycles, which could be linked to varying axial and lateral strain rates at 50% of UCS values for the limestones investigated. Furthermore, the variation in crack initiation stress σCI (MPa) due to progressive magnesium sulfate tests were also evaluated considering two strain-based methods and the findings showed that σCI of limestones slowly decreased with increasing weathering test cycles. It could be claimed that cyclic magnesium sulfate tests performed on rock materials would be beneficial for assessing the long-term serviceability of rocks. In this context, mud-supported limestones seem to have a greater resistance against magnesium sulfate weathering tests compared to the grain-supported ones. However, the number of samples should be increased in order to achieve a comprehensive understanding about the degradation processes of limestones. © 2021 Elsevier B.V., All rights reserved.Conference Object Modelling of Rock Comminution Using Statistical and Soft Computing Analyses – A Case Study on a Laboratory-Scale Jaw Crusher(Baski, 2022) Köken, E.The present study encompasses a quantitative investigation on rock comminution using statistical and soft computing analyses. For this purpose, physical and mechanical rock aggregate properties were determined for nine different rock types (R1-R9) in Turkey. Then, crushability tests were performed to determine the size reduction ratio (SRR) using a laboratory-scale jaw crusher. Based on statistical and soft computing analyses, five different predictive models (M1 to M5) were established to estimate the SRR in this study. Consequently, the SRR values are associated with water absorption by weight (w<inf>a</inf>), dry unit weight (γ<inf>d</inf>), and aggregate impact value (AIV) of the investigated rocks. However, the individual use of these independent variables results in undulating SRR estimations. Therefore, among the established predictive models, the empirical formulation based on artificial neural networks (ANN) (M5) was found to be the most reliable model with a correlation of determination value (R2) of 0.88. However, the predictive models stated in this study should be implemented to several portable jaw crushers to observe the similarities or difficulties in quantifying SRR as a function of rock properties in future studies. © 2022 Elsevier B.V., All rights reserved.Article Citation - Scopus: 3Estimation of Deformation Modulus of Coals Using Artificial Neural Networks (ANN)(Szechenyi Istvan University, 2022-05-29) Köken, E.In this study, the Young modulus (E) of different coals was investigated using artificial neural networks (ANN). For this purpose, a comprehensive literature survey was carried out to compile such datasets available for the ANN analyses. As a result of the literature survey, a database composed of 81 datasets was formed. In the ANN analyses, uniaxial compressive strength (UCS) and dry density (ρ<inf>d</inf>) of coals were adopted as input parameters. The ANN analysis results demonstrated that the predictive model established in this study could be reliably used to estimate the E for different coals. The correlation of determination value (R2) for the developed model is 0.85, which shows its relative success. In this context, this study can be declared a case study showing the applicability of ANN for the evaluation of E for a wide range of coal types. However, the number of samples and independent variables should be increased to obtain more comprehensive models in future studies. © 2025 Elsevier B.V., All rights reserved.