Browsing by Author "Koken, Ekin"

Now showing 1 - 20 of 31

Citation - WoS: 5
Citation - Scopus: 6
Size Reduction Characterization of Underground Mine Tailings: A Case Study on Sandstones
(Springer, 2021) Koken, Ekin
The production of construction and building materials starts with reducing the size of natural, industrial, and waste materials. In addition to strength and durability considerations of natural resources recommended by various institutions, size reduction characterization, specific to rock aggregates, has a vital role in their size-related quality. In this study, various sandstones extracted from underground mines located in northwestern Turkey were investigated for size reduction characterizations. Several mineralogical, textural, and physico-mechanical properties were determined for each rock type. Crushability tests were carried out using a laboratory-scale cone crusher for different feeding size fractions, namely + 11.20 - 16.00 mm (size I), + 9.52 - 16.00 mm (size II), and + 6.30 - 16.00 mm (size III). Based on the crushability tests, crushed particles were analyzed, focusing on production yield, size, and shape properties. Each crushability test was also explored for energy consumption arising from varying rock properties of the sandstones. The laboratory test results demonstrated that the degree of rock crushability (DRC) and specific energy consumption (E-cs, kJ/kg) were associated with the Brazilian tensile strength (BTS, MPa) and apparent porosity (n(e), %) of the sandstones. The results also showed that the degree of sorting in mineral constituents, quantified as the sorting coefficient (S-c), affected the DRC. However, mineralogical features of the sandstones have no significant impact on DRC andE(cs). Variations in feeding gradation, irrespective of whether mineralogical, textural, or physico-mechanical properties, have remarkable effects on product flakiness and yields for specific size fractions. In light of the findings obtained, the present study provides knowledge on how the sandstones behave under cone crushing operations.
Kalabak Tepe Kireçtaşlarının Nihai Taşıma Gücünün Farklı Analiz Yöntemleri ile Araştırılması
(2024) Kıncal, Cem; Koken, Ekin; Koca, Tümay Kadakci; Kuruoglu, Mehmet
Farklı kütle özelliklerine sahip kayaç kütlelerinin taşıma gücünü en doğru şekilde tahmin eden yöntemlerin seçiminde karşılaştırmalı çalışmalar önem kazanmaktadır. Hangi yöntemin daha sağlam sonuçlar verdiği dayandıkları parametrelerle ilişkili olmaktadır. Bu çalışmada, Miyosen yaşlı Kalabak Tepe (İzmir) kireçtaşlarının taşıma gücü incelemesi değişik yöntemler uygulanarak gerçekleştirilmiştir. Kayaç kütle özellikleri Genelleştirilmiş Hoek-Brown yenilme ölçütü dikkate alınarak belirlenmiştir. Taşıma gücü için uygun yöntemlerin belirlenmesinde arazi modeli ve süreksizliklerin konumları dikkate alınmıştır. Kayacın kütle dayanım parametreleriyle birlikte limit analiz veya sonlu elemanlar yöntemlerinin taşıma gücü analizlerinde kullanılması uygun bir yaklaşım olmaktadır. Sonlu elemanlar yöntemiyle kireçtaşlarının nihai taşıma gücü, limit analiz yöntemlerinden elde edilenlerle karşılaştırılmıştır. Sonuç olarak, bazı limit analiz yöntemlerinden elde edilen sonuçlar, sonlu elemanlar ve diğer limit analiz yöntemlerinden elde edilenlerden daha yüksek bulunmuştur. Yöntemler arasındaki bulgu farklılıkları detaylıca tartışılarak yöntemlerin pratik kullanımına ışık tutulmuştur.
Integrated Quantitative Modelling for the Dimension Stone Quality Evaluation: Implications for Sustainable Resource Management
(Springer Heidelberg, 2025) Koken, Ekin; Strzalkowski, Pawel
The growing demand for dimensional stones in construction and monument conservation requires fast, repeatable and scientifically valid quality assessment procedures. The present study, in this context, established a solid foundation for quantifying the quality of dimension stones by adopting two quantitative methods: the Suitability Index (SI) and Dimension Stone Field Performance Coefficient (DSFPC). Both methods were coded in the MATLAB environment and implemented for 20 different rock types used in various dimension stone applications in Turkey. Evaluations based on the above-mentioned methods demonstrate that the DSFPC provides a more conservative assessment than the SI method. Additionally, engineering interpretations derived from the SI and DSFPC approaches are compared with recently published classification systems developed for the dimension stone industry. Focusing on this comparison, it is concluded that the adopted methods offer a more holistic evaluation framework compared to the approaches based solely on a single input parameter, such as effective porosity (ne), uniaxial compressive strength (UCS), or B & ouml;hme abrasion value (BAV) of rocks. Furthermore, it is concluded that the adopted methods complement each other by yielding supportive outcomes. The coded methods can be adapted to other lithological series and integrated with spatial information systems to support decision-making in mining and construction sectors. From this point of view, the present study may be considered a case study supporting holistic approaches to sustainable resource management in the dimension stone industry.
Citation - WoS: 1
Assessment of Installed Power for Inclined Belt Conveyors Using Genetic Algorithm and Artificial Neural Networks
(Konya Teknik Univ, 2022) Koken, Ekin
In this study, the installed power (P inst , kW) of several inclined belt conveyors operating in the mining industry of Turkey was investigated through two soft computing algorithms (i.e., genetic expression programming (GEP) and artificial neural networks (ANN)). For this purpose, the most crucial belt (i.e., belt length (L), belt width (W), belt inclination (alpha)), operational (i.e., belt speed (Vb) b ) and throughput (Q)) and infrastructural (belt weight (Wb) b ) and idler weight (Wid)) id )) features of 42 belt conveyors were collected for each investigated belt conveyor. The collected data was transformed into a comprehensive dataset for soft computing analyses. Based on the GEP and ANN analyses, two robust predictive models were proposed to estimate the P inst . The performance of the proposed models was evaluated using several statistical indicators, and the statistical evaluations demonstrated that the models yielded a correlation of determination (R2) 2 ) greater than 0.95. Nevertheless, the ANN-based model has slightly overperformed in predicting the P inst values. In conclusion, the proposed models can be reliably used to estimate the P inst for the investigated conveyor belts. In addition, the mathematical expressions of the proposed models were given in the present study to let users implement them more efficiently.
Citation - WoS: 4
Citation - Scopus: 5
Assessment of Los Angeles Abrasion Value (LAAV) and Magnesium Sulphate Soundness (MWL) of Rock Aggregates Using Gene Expression Programming and Artificial Neural Networks
(Polska Akad Nauk, Polish Acad Sciences, 2022) Koken, Ekin
It has been acknowledged that two important rock aggregate properties are the Los Angeles abrasion value (LAAV) and magnesium sulphate soundness (Mwl). However, the determination of these properties is relatively challenging due to special sampling requirements and tedious testing procedures. In this stu-dy, detailed laboratory studies were carried out to predict the LAAV and Mwl for 25 different rock types located in NW Turkey. For this purpose, mineralogical, physical, mechanical, and aggregate properties were determined for each rock type. Strong predictive models were established based on gene expression programming (GEP) and artificial neural network (ANN) methodologies. The performance of the proposed models was evaluated using several statistical indicators, and the statistical analysis results demonstra-ted that the ANN-based proposed models with the correlation of determination (R2) value greater than 0.98 outperformed the other predictive models established in this study. Hence, the ANN-based predictive models can reliably be used to predict the LAAV and Mwl for the investigated rock types. In addition, the suitability of the investigated rock types for use in bituminous paving mixtures was also evaluated based on the ASTM D692/D692M standard. Accordingly, most of the investigated rock types can be used in bituminous paving mixtures. In conclusion, it can be claimed that the proposed predictive models with their explicit mathematical formulations are believed to save time and provide practical knowledge for evaluating the suitability of the rock aggregates in pavement engineering design studies in NW Turkey.
Citation - WoS: 10
Citation - Scopus: 16
Investigating the Effects of Feeding Properties on Rock Breakage by Jaw Crusher Using Response Surface Method and Gene Expression Programming
(Elsevier, 2021) Koken, Ekin; Lawal, Abiodun Ismail
The present study investigates the effects of feeding properties on rock comminution by a laboratory-scale jaw crusher. For this purpose, detailed crushability tests were carried out on four different rock types to assess their degree of rock crushability (DRC). Various feeding sizes (9.5 - 19 mm) and quantities (500 - 1500 g) were adopted to reveal the choke feeding intensity during crushing actions. The efficiency of feeding properties was investigated through the response surface methodology (RSM). The RSM results demonstrated that the characterized feeding size (F-80, mm) dominates the general size reduction, whereas the feeding quantity (m(f), g) is associated with the crushing energy consumption and product flakiness. Therefore, the choke feeding intensity has a direct relation to the m(f) and F-80. In addition, novel gene expression programming (GEP) models were employed to generate empirical formulations to predict the DRC parameters. The established GEP models have a satisfactory estimation capability. Therefore, the DRC of the investigated rocks can be optimized through the proposed GEP models based on the coupling variables of m(f) and F-80. (C) 2021 The Society of Powder Technology Japan. Published by Elsevier B.V. and The Society of Powder Technology Japan. All rights reserved.
Citation - WoS: 1
Citation - Scopus: 2
Estimating Uniaxial Compressive Strength of Pyroclastic Rocks Using Soft Computing Techniques
(Shahrood Univ Technology, 2024) Koken, Ekin
In this study, several soft computing analyses are performed to build some predictive models to estimate the uniaxial compressive strength (UCS) of the pyroclastic rocks from central Anatolia, Turkey. For this purpose, a series of laboratory studies are conducted to reveal physico-mechanical rock properties such as dry density (rho d), effective porosity (ne), pulse wave velocity (Vp), and UCS. In soft computing analyses, rho d, ne, and Vp are adopted as the input parameters since they are practical and cost-effective non-destructive rock properties. As a result of the soft computing analyses based on the classification and regression trees (CART), multiple adaptive regression spline (MARS), adaptive neuro-fuzzy inference system (ANFIS), artificial neural networks (ANN), and gene expression programming (GEP), five robust predictive models are proposed in this study. The performance of the proposed predictive models is evaluated by some statistical indicators, and it is found that the correlation of determination (R2) value for the models varies between 0.82 - 0.88. Based on these statistical indicators, the proposed predictive models can be reliably used to estimate the UCS of the pyroclastic rocks.
Citation - WoS: 8
Citation - Scopus: 8
Guidelines for Natural Stone Products in Connection With European Standards
(MDPI, 2023) Strzalkowski, Pawel; Koken, Ekin; Sousa, Luis
The selection of ornamental stones for specific applications requires technical guidance since it should be based on the durability, service life, and aesthetic value of the stones. In most cases, these fundamentals provide quantitative data on the usability and performance of ornamental stones. The present study attempts to put forward a quantitative classification system for natural stone products concerning critical rock properties. For this purpose, fundamental physical and mechanical rock properties are listed based on European standards. Then, minimum limit values are proposed for different applications of natural stone products based on retrospective analyses of numerous ornamental stone applications. The suggested limit values based on several physical and mechanical rock properties can guide relevant engineers to initially consider possible rock types for use as natural stones in a wide range of applications. In this context, it is believed that the present study contributes to the natural stone industry by discussing the minimum limit values for the consideration of a wide range of rock types possibly usable in the dimension stone industry.
Citation - WoS: 8
Citation - Scopus: 12
Assessment of Rock Aggregate Quality Through the Analytic Hierarchy Process (AHP)
(Springer, 2020) Koken, Ekin; Top, Soner; Ozarslan, Ahmet
The present study aimed to assess rock aggregate quality through the Analytic Hierarchy Process (AHP). In the context of the AHP analyses, four rock types (i.e., andesite, basalt, granodiorite, and gabbro), five evaluation criteria, and several technical requirements/suggestions for coarse aggregates related to bituminous paving mixtures were considered. In order to set over the evaluation criteria, detailed laboratory studies were conducted. For this purpose, various mineralogical, physical, and mechanical aggregate properties were determined for each rock type concerning their weathering grades. As a result of the laboratory studies, it was determined that the rock weathering processes have substantial negative impacts on the rock aggregate properties considered in this study. The AHP analysis results indicated that that different rock types have several advantages concerning various evaluation criteria. Based on the general evaluation point (EP) of the rocks, the gabbros were found to have the highest rock aggregate quality (EP = 0.393). In contrast, the andesites had the lowest quality (EP = 0.069). Besides, the basalts (EP = 0.271) and granodiorites (EP = 0.267) presented approximately the same quality for their use in bituminous pavement mixtures. It was also demonstrated that the AHP, with its specific methodology, can be utilized to represent different environmental and mechanical conditions by changing the relative weight of the evaluation criteria. In this way, the pros and cons of different rock types could be revealed quantitatively, which enables related engineers to select proper rock types for their use under different environmental and mechanical conditions. From this point of view, the present study could be declared a case study noted for combining theoretical and practical approaches on bituminous paving mixtures as a sign of rock aggregate quality.
Development of Soft Computing-Based Predictive Tools for Estimating the Young Modulus of Weak Rocks
(Univ Zielona Gora, 2024) Koken, Ekin; Strzalkowski, Pawel
The deformation characteristics of rocks are of vital importance in addressing most geomechanical issues as they are one of the most critical input parameters in rock engineering analyses. For this reason, robust forecasting models are required when analysing the stability of tunnels, slopes, mine galleries, and other underground excavations. In this research, novel predictive models are proposed to estimate the tangential Young modulus (E-ti) of weak rocks. To achieve this, an extensive literature review is performed to obtain a comprehensive database including critical physico-mechanical properties of various weak rocks. Thanks to the advantages of soft neural networks (ANN) and multivariate adaptive regression splines (MARS), novel predictive models are established. The effectiveness of the developed predictive models is investigated using various statistical measures and it is concluded that empirical models utilizing ANN and ANFIS methodologies are the most effective tools for estimating the E-ti of weak rocks. In addition, a practical design chart is also developed for assessing the E-ti of weak rocks.
Citation - WoS: 10
Citation - Scopus: 13
Evaluation of Size Reduction Process for Rock Aggregates in Cone Crusher
(Springer Heidelberg, 2020) Koken, Ekin
The size reduction process of rocks in cone crushers is one of the most important issues, particularly for the secondary and tertiary stages of crushing operations. In this study, 17 different rock types were considered for the evaluation of their size reduction variations that occurred in a laboratory-scale cone crusher. Based on several mineralogical, physico-mechanical, and aggregate properties determined for each rock type, the crushability tests were performed. Before and after the crushability tests, particle size distribution (PSD) of the uncrushed (feed) and crushed (product) materials were determined by sieve analyses. On the basis of these PSDs, the degree of rock crushability (DRC) was attempted to quantify by simple approaches (i.e., size reduction ratio, SRR, and the theoretical square mesh aperture size that corresponds to the 10% of the cumulative undersize in the product, P-10 (mm)). The crushability test results demonstrated that the DRC in cone crusher could be quantified by focusing on the variations in the SRR and P-10. The SRR and P-10 are associated with three important rock properties, Shore hardness (SH), Los Angeles abrasion loss (LAA, %), and Brazilian tensile strength (BTS, MPa). The textural and mineralogical features of rocks also have substantial impacts on the DRC for several rock types. It was concluded that the combination of the SRR and P-10 could be considered together for the evaluation of DRC in cone crushers. Moreover, further research potentials on the DRC were also discussed in this study.
Geological-Geochemical Signatures of Opal Occurrences in Keciborlu (Isparta-Turkey)
(Pamukkale Univ, 2022) Baspinar Tuncay, Ebru; Koken, Ekin; Kuscu, Mustafa; Cengiz, Oya; Aydemir, Fatih; Raimov, Rahmen
Silica-rich solutions, considered as the final products of acidic volcanism, which started from the Late Miocene to throughout the Plio-Quaternary around Isparta, are effective along the main fault observed around the Keciborlu (Isparta) sulfur deposit. Therefore, opal occurrences are intensively observed along this fault zone. Opal occurrences are in various colors such as gray, beige, yellowish, reddish, blackish. Opals with a massive structure, observed as bands, are sharp -edged, conchoidal diffraction, translucent, matte, oily glossy surface opals are iron oxidized. Some opals contain brecciated rock fragments. The locations of the opal occurrences in the field were determined in this study. Using representative samples, structural and textural properties of opals were determined by thin section, scanning electron microscopy analyses, and mineral paragenesis was analyzed via x-ray diffraction and Fourier transform infrared spectroscopy analyses. Geochemical findings revealed chemical compositions. Based on the thin-section studies, it was observed that the opalized samples lost their primary properties due to the effect of hydrothermal solutions and they became iron oxidized, laminated, and argillized. In addition, they contain opaque minerals such as magnetite and hematite. Different micro textures such as amorphous, granular, desert rose, and lepisphere quartz associations were observed in SEM images. In the XRD and FTIR analyzes, it was determined that most of the opals were Opal CT and some of them were defined as Opal C type. Based on the geochemical analyses considering Ba <120 ppm and Ca >200 ppm, the remarkable changes in loss on ignition values, and the relative relationship between C/T ratio and Ga, such hydrothermal alterations in opals the Keciborlu opals were found to have the magmatic origin.
Citation - WoS: 1
Citation - Scopus: 1
Development of Comprehensive Predictive Models for Evaluating Böhme Abrasion Value (BAV) of Dimension Stones Using Non-Destructive Testing Methods
(MDPI, 2025) Koken, Ekin
Due to the global demand for dimension stones, fast and reliable evaluation tools are essential for assessing the quality of dimension stones. For this reason, this study aims to develop comprehensive tools for estimating the abrasion resistance of various dimension stones from Turkey. Non-destructive rock properties, including dry density (rho d), water absorption by weight (wa), and pulse wave velocity (Vp), were determined to build a comprehensive database for soft computing analyses. Three predictive models were established using multivariate adaptive regression spline (MARS), M5P, and artificial neural networks (ANN) methodologies. The performance of the models was assessed through scatter plots and statistical indicators, showing that the ANN-based model outperforms those based on M5P and MARS. The applicability of the models was further validated with independent data from the existing literature, confirming that all models are suitable for estimating varying B & ouml;hme abrasion values (BAVs). A MATLAB-based software tool, called B & ouml;hme abrasion calculator (v1.00), was also developed, allowing users to estimate BAV values by inputting adopted non-destructive rock properties. This tool is available upon request, supporting the dimension stone industry and fostering future research in this field.
Citation - WoS: 4
Citation - Scopus: 4
Evaluation of Soft Computing Methods for Estimating Tangential Young Modulus of Intact Rock Based on Statistical Performance Indices
(Springer, 2022) Koken, Ekin; Kadakci Koca, Tumay
The tangential Young modulus (E-ti) of intact rock is a critical parameter in engineering geological design calculations and rock mass classification systems. The E-ti of various rock types has been successfully estimated by many studies based on numerous soft computing methods in recent years. However, these studies mainly involve a single analysis method or are valid for a limited number of samples. For this reason, this study aimed to compare artificial neural networks (ANN), adaptive neural fuzzy inference system (ANFIS), and Gene expression programming (GEP) methods to estimate the E-ti of various rock types based on 147 datasets collected from the published literature. As a result of the soft computing analyses, three different predictive models were proposed in this study. In the proposed prediction models, rock properties such as dry density (rho(d)), effective porosity (n(e)), P-wave velocity (V-p), and uniaxial compressive strength (UCS) were used. The estimation performance of the proposed models was examined through several performance indices such as coefficient of determination (R-2), root mean square error (RMSE), the variance accounted for (VAF), and mean absolute percent error (MAPE). As a result of statistical analyses, it was determined that the ANFIS model presents a better prediction performance (R-2 = 0.967) than the other methods in the training datasets. On the other hand, the accuracy of the ANFIS model decreased significantly in the test datasets (R-2 = 0.803). Furthermore, the GEP model presented the lowest predictive performance. Finally, considering the overall estimation accuracy of the proposed models, it was concluded that the proposed ANN model with an R-2 of 0.94 could reliably be used to estimate the E-ti of investigated rocks.
Beton Dayanım Özelliklerinin Yüzey Tepki Yöntemi, Genetik Algoritma ve Yapay Sinir Ağları İle Tahmini
(2022) Koken, Ekin; Kilincarslan, Semsettin; Tuncay, Ebru Baspınar
Bu çalışmada, beton dayanım özellikleri yüzey tepki yöntemi, genetik algoritma ve yapay sinir ağları yöntemleri ile analiz edilmiştir. Altı farklı beton agregası kullanılarak küp (10x10x10 cm) ve prizmatik (15x15x60 cm) beton numuneleri hazırlanmış olup, beton tek eksenli basınç dayanımı (UCSc) ve eğilme dayanımının (FSc) tahminlenmesi için bazı tahmin modeller geliştirilmiştir. Geliştirilen modellerde beton yoğunluğu (ρc), beton agregalarının Los Angeles aşınma kaybı (LAA) ve betonlara ait P dalgası hızı (Vpc) gibi parametreler kullanılmıştır. Elde edilen modellerin performansları bazı istatistiksel göstergeler ışığında değerlendirilmiş ve genetik algoritma ve yapay sinir ağlarını temel alan yöntemlerin beton dayanım özelliklerini tahmininde başarılı bir şekilde kullanılabileceği belirlenmiştir.
Citation - WoS: 23
Citation - Scopus: 24
Prediction of Mechanical Properties of Coal From Non-Destructive Properties: A Comparative Application of MARS, ANN, and GA
(Springer, 2021) Lawal, Abiodun Ismail; Oniyide, Gafar O.; Kwon, Sangki; Onifade, Moshood; Koken, Ekin; Ogunsola, Nafiu O.
Rock properties are useful for safe operation and design of both surface and underground mines including civil engineering projects. However, the cost and time required to perform detailed assessments of rock properties are high. In addition, rock properties are required in numerical modeling. Different models have been proposed for quick and easy assessments of rock properties but majority of these models are regression-based, which are incapable of capturing inherent variabilities in rock properties. Therefore, this study proposed three different soft computing models (i.e., double input-single output ANN, multivariate adaptive regression spline, genetic algorithm) for accurate prediction of several mechanical properties of coal and coal-like rocks. The performances of the proposed models were statistically evaluated using various indices and they were found to predict rock properties suitably with very strong statistical indices. The proposed models were validated further using external datasets aside from those used in the model development to test the generalization potential of the models. The Pearson's correlation coefficients for the validation were close to 1, indicating that the proposed models can be used to assess geo-mechanical properties of coal, shale, and coal-bearing rocks.
Evaluation of the Capacity of Apron Feeders Used in Crushing–Screening Plants by Response Surface Methodology and Artificial Intelligence Methods
(2024) Koken, Ekin
Bu çalışmada Apron besleyicilerin kapasitesi (Q), yüzey tepki yöntemi (RSM) ve bazı yapay zekâ yöntemleriyle araştırılmıştır. Bu bağlamda, Türk Madencilik Sektöründe (TMI) kullanılan Apron besleyicilerin yaygın çalışma koşullarına ilişkin niceliksel verilerin toplanması amacıyla kapsamlı bir saha araştırması yapılmıştır. Toplanan bu verilere göre, Apron besleyicilerin Q değerini etkileyen değiştirgelerin ortaya konması için RSM analizleri gerçekleştirilmiştir. Buna göre, besleyici hazne genişliği (B), taşınan malzemenin bant üzerindeki yüksekliği (D), konveyör hızı (V) ve doluluk faktörü (φ), Q değeri için en önemli faktörler olarak belirlenmiştir. Q değerlerindeki gözlemlemek için çeşitli etkileşim ve kontur grafikleri sunulmuştur. Ayrıca, apron besleyicilerin Q değerini tahmin için, çok değişkenli uyarlamalı regresyon analizi (MARS), uyarlamalı ağ tabanlı bulanık mantık çıkarım sistemi (ANFIS) ve yapay sinir ağları (ANN) gibi bazı yapay zekâ yöntemlerine dayılı bazı tahmin modelleri tanıtılmıştır. Kurulan tahmin modellerinin performansı dağılım grafiklerine göre değerlendirilmiş ve RSM metodolojisine dayalı tahmin modelinin, yapay zekâ tabanlı tahmin modellerine göre nispeten daha iyi sonuçlar sağladığı bulunmuştur. Sunulan tahmin modelleri, yüksek kapasiteli Apron besleyicilerin Q değerini tahmin etmek için güvenilir bir şekilde kullanılabilir. Ancak kırma-eleme tesisi tasarımcıları, düşük kapasiteli Apron besleyicileri değerlendirmek için sunulan tahmin modellerini kullanırken dikkatli olmalıdır. Elde edilen bulgulara dayanarak, bu çalışma, Apron besleyicilerinin Q değerini değerlendirmek için RSM metodolojisinin ve çeşitli yapay zekâ yöntemlerinin uygulanabilirliğini göstermiştir.
Citation - WoS: 8
Citation - Scopus: 7
Assessment of Deformation Properties of CoAl Measure Sandstones Through Regression Analyses and Artificial Neural Networks
(Polska Akad Nauk, Polish Acad Sciences, 2021) Koken, Ekin
The deformation properties of rocks play a crucial role in handling most geomechanical problems. However, the determination of these properties in laboratory is costly and necessitates special equipment. Therefore, many attempts were made to estimate these properties using different techniques. In this study, various statistical and soft computing methods were employed to predict the tangential Young Modulus (Eti, GPa) and tangential Poisson's Ratio (vti) of coal measure sandstones located in Zonguldak Hardcoal Basin (ZHB), NW Turkey. Predictive models were established based on various regression and artificial neural network (ANN) analyses, including physicomechanical, mineralogical, and textural properties of rocks. The analysis results showed that the mineralogical features such as the contents of quartz (Q, %) and lithic fragment (LF, %) and the textural features (i.e., average grain size, d50, and sorting coefficient, Sc) have remarkable impacts on deformation properties of the investigated sandstones. By comparison with these features, the mineralogical effects seem to be more effective in predicting the Eti and vti. The performance of the established models was assessed using several statistical indicators. The predicted results from the proposed models were compared to one another. It was concluded that the empirical models based on the ANN were found to be the most convenient tools for evaluating the deformational properties of the investigated sandstones.
Citation - WoS: 3
Citation - Scopus: 3
Roles of Curing Conditions on Properties of Soil Reinforced With Palm Fiber and Lime
(Ice Publishing, 2021) Qu, Jili; Wang, Junfeng; Batugin, Andrian; Zhu, Hao; Koken, Ekin; Mihaela, Cristea Lavinia; Zhang, Yawen
Due to the environment-friendly properties of palm fiber, its use was attempted to improve the quality of soil together with lime. Unconfined compressive tests were carried out on soils mixed with palm fiber and lime under the three curing conditions of immersion in water, cyclic wetting-drying and air-curing for a series of contents of additives. The static stiffness of five types of samples (the number 1 type is the control sample) was also analyzed against curing conditions, curing time and sample type. Results from the tests show that the immersion in water condition is the best for the formation of unconfined compressive strength (UCS) and static stiffness, while the air-curing condition is the worst. The highest UCS can be acquired with 1% palm fiber and 20.7% lime, and the highest static stiffness was acquired with purely 20.7% lime content. The fastest increase rate is presented by the curing condition of immersion in water. The logarithmic function is more suitable for expressing the relationship between static stiffness and curing time. It is important for site engineers to understand the curing conditions and stabilizing mechanism of palm fiber and lime for the design and construction of civil engineering projects.
Assessment of the Quality of Tuffs in Central Anatolia, Turkey: A Quantitative Classification Approach
(Acad Sci Czech Republic Inst Rock Structure & Mechanics, 2025) Koken, Ekin; Ince, Ismail
The growing global demand for dimension stones necessitates efficient and accurate evaluation methods to ensure their optimal use in various industries. To assess their suitability for various dimension stone applications, this study investigates tuffs from Central Anatolia, Turkey. For this purpose, the fundamental physical and mechanical properties of the tuffs were determined in laboratory studies, and a detailed durability assessment was conducted for each rock type. The analysis results indicate that most of the examined rocks are of low quality and more suitable for non-load-bearing applications. Based on the collected data, fuzzy clustering techniques were applied to develop a new classification system, categorising the tuffs into four classes (Class A-D) according to their potential applications. Additionally, a user-friendly MATLAB-based software tool was also developed to facilitate the implementation of the proposed classification system.