TR Dizin İndeksli Yayınlar Koleksiyonu / TR Dizin Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14365/4
Browse
2 results
Search Results
Article Comparison of Levenberg-Marquardt and Bayesian Regularization Learning Algorithms for Daily Runoff Forecasting(2025-06-17) Bor, Asli; Okan, MerveIn this study, Multilayer Perceptron (MLP) with Levenberg-Marquardt and Bayesian Regularization algorithms machine learning methods are compared for modeling of the rainfall-runoff process. For this purpose, daily flows were forecast using 5844 discharge data monitored between 1999 and 2015 of D21A001 Kırkgöze gauging station on the Karasu River operated by DSI. 6 scenarios were developed during the studies. Our findings indicate that the estimated capability of the Bayesian Regularization algorithm were close to with Levenberg-Marquardt algorithm for training and testing, respectively. This study shows that different network structures and data representing land features can improve prediction for longer lead times. We consider that the ANN model accurately depicted the Karasu flows, and that our study will serve as a guide for more research on flooding and water storage.Article Numerical Evaluation of the Performance of Uhpc Beams Under Bending and Shear Loads Using Different Material Models(2024-09-30) Akin-Adamu, Ayodele; Yalçinkaya, Çağlar; Merter, OnurThe Microplane and Menetrey-Willam concrete models are formulated on the research work of Bazant and Gambarova and Menetrey-Willam in the nineties respectively. They are used in this thesis to predict how reinforced Ultra-High-Performance Concrete (UHPC) beams will behave when subjected to flexural and shear dominant loadings. The numerical models are available in ANSYS, and they can simulate UHPC's extraordinary mechanical properties, such as high compression and tension strength, strain hardening, and softening behavior in compression and tension. In this research, four UHPC beams with dimensions of 180 wide by 270 deep by 4000 mm long with tensile reinforcements were studied using the two cementitious composite models mentioned above with the ANSYS software. The beams were investigated under flexural four-point loading and shear three-point loading with the ANSYS program. A quarter-geometric section model of the full beam was considered for the four-point loading to take advantage of symmetry in the longitudinal and transverse directions of the beam. For the three-point loading, the full geometry model of the beam was considered only because of the lack of symmetry. The results from the ANSYS finite element software were validated with an experimental study conducted by different researchers to show its capacity to predict the bending and shear behavior of reinforced UHPC beams. The comparisons of the results of both material models show that they can simulate the behavior of UHPC beams by using experimental load-deflection plots of the beam specimens and force strain plots of the longitudinal tensile reinforcements in the sample beams.