This paper presents a comparative study of different methods, such as the analytical method, finite element method (FEM), and multilayer perceptron (MLP) for analyzing a frictionless receding contact problem. The problem consists of two layers resting on a Winkler foundation. The top layer is functionally graded (FG) along the depth and pressed using a rigid cylindrical stamp, whereas the bottom layer is homogeneous. We assumed that the contact between the two layers, and that between the FG layer and the rigid cylindrical stamp are frictionless; additionally, compressive normal tractions can be transmitted through the interface. First, the problem was solved analytically using the theory of elasticity and integral transform techniques. Second, the finite element solution of the problem was obtained using ANSYS software. Finally, the problem was extended based on the MLP, which an artificial neural network used for different problem parameters. The results of this study showed that the variations in the contact lengths at the interface between the rigid cylindrical stamp and the FG layer, those between the homogeneous layer and the FG layer, and the maximum contact pressures at these interfaces depended on various dimensionless quantities such as the stamp radius, stiffness parameter, shear modulus ratio, and elastic spring constant ratio. We observed that the results obtained with the three different methods, namely the analytical method, FEM, and MLP, are extremely compatible with each other, thus proving the accuracy of these results.
Read full abstract