Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
4 results
Search Results
Article Citation - WoS: 24Citation - Scopus: 24Prediction of Mechanical Properties of Coal From Non-Destructive Properties: A Comparative Application of MARS, ANN, and GA(Springer, 2021-10-06) 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.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 - WoS: 5Citation - Scopus: 5Evaluation of Soft Computing Methods for Estimating Tangential Young Modulus of Intact Rock Based on Statistical Performance Indices(Springer, 2022-04-06) Koken, Ekin; Kadakci Koca, TumayThe 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.Article Citation - WoS: 1Citation - Scopus: 2Estimating Uniaxial Compressive Strength of Pyroclastic Rocks Using Soft Computing Techniques(Shahrood Univ Technology, 2024) Koken, EkinIn 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.