Polat, Alper; Kaya, Yusuf

In this study, the problem of discontinuous contact in two functionally graded (FG) layers resting on a rigid plane and loaded by two rigid blocks is solved by the finite element method (FEM). Separate analyzes are made for the cases where the top surfaces of the problem layers are metal, the bottom surfaces are ceramic and the top surfaces are ceramic and the bottom surfaces are metal. For the problem, it is accepted that all surfaces are frictionless. A two-dimensional FEM analysis of the problem is made by using a special macro added to the ANSYS package program The solution of this study, which has no analytical solution in the literature, is given with FEM. Analyzes are made by loading different Q and P loads on the blocks. The normal stress (sigma y) distributions at the interfaces of FG layers and between the substrate and the rigid plane interface are obtained. In addition, the starting and ending points of the separations between these surfaces are determined. The normal stresses (sigma x, sigma y) and shear stresses (tau xy) at the point of separation are obtained along the depth. The results obtained are shown in graphics and tables. With this method, effective results are obtained in a very short time. In addition, analytically complex and long problems can be solved with this method.

Ünlü, Ramazan

Over the years, several machine learning approaches have been proposed and utilized to create a prediction model for the high-performance concrete (HPC) slump flow. Despite HPC is a highly complex material, predicting its pattern is a rather ambitious process. Hence, choosing and applying the correct method remain a crucial task. Like some other problems, prediction of HPC slump flow suffers from abnormal attributes which might both have an influence on prediction accuracy and increases variance. In recent years, different studies are proposed to optimize the prediction accuracy for HPC slump flow. However, more state-of-the-art regression algorithms can be implemented to create a better model. This study focuses on several methods with different mathematical backgrounds to get the best possible results. Four well-known algorithms Support Vector Regression, M5P Trees, Random Forest, and MLPReg are implemented with optimum parameters as base learners. Also, redundant features are examined to better understand both how ingredients influence on prediction models and whether possible to achieve acceptable results with a few components. Based on the findings, the MLPReg algorithm with optimum parameters gives better results than others in terms of commonly used statistical error evaluation metrics. Besides, chosen algorithms can give rather accurate results using just a few attributes of a slump flow dataset.