Simulation and modeling of polymer concrete panels using deep neural networks

Abstract

The most often utilized construction material worldwide is concrete. Extensive experiments are carried out each year to study the physical, mechanical, and chemical properties of concrete, which are costly and time-consuming. This study focuses on avoiding redundant tests by applying the machine learning (ML) method to predict temperature-dependent polymer concrete qualities. In this work, as a strong tool of the ML method, a deep neural network (DNN) is used to examine the five temperature-dependent mechanical characteristics of concrete, including Poisson's ratio, Young's modulus, specific heat, coefficient of thermal expansion, and thermal conductivity. A 5-fold cross-validation method was used to verify the strategy in this research and get rid of split bias in testing and training. This study demonstrates the material properties of temperature-dependent polymer concrete followed by mathematical modeling of a steel-polymer concrete panel used for various civil applications. Temperature-dependent equations are determined using constitutive heat transfer and Cartesian coordinates. In addition, a thermal shock load acts on the upper part, and the lower part becomes an isothermal state with no heat flow. In order to account for the limited speed at which temperature waves travel, two distinct theories of generalized thermoelasticity are employed: the Lord-Shulman (LS) and the Green-Lindsay (GL) theories. The Fast Laplace Inverse Transform Method (FLITM) is used to transfer the results from the Laplace domain to the time domain. In addition, a three-dimensional differential quadrature approach (3D-DQA) using three Chebyshev-Gaussian-Robat functions for solving temperature-dependent equations is presented. In conclusion, some suggestions for improving the stability of polymer concrete panels are detailed and will be compiled in a future manual.