Browsing by Author "Aghdam, Mohammad Mohammadi"

Now showing 1 - 2 of 2

Citation - WoS: 2
Citation - Scopus: 2
Large Deflection Analysis of Functionally Graded Reinforced Sandwich Beams With Auxetic Core Using Physics-Informed Neural Network
(Taylor & Francis inc, 2025) Nopour, Reza; Fallah, Ali; Aghdam, Mohammad Mohammadi
This paper aims to investigate the large deflection behavior of a sandwich beam reinforced with functionally graded (FG) graphene platelets (GPL) together with an auxetic core, rested on a nonlinear elastic foundation. The nonlinear governing equations of the problem are derived using Hamilton's principle based on the Euler-Bernoulli beam theory for large deflections. Five different distributions are considered to describe the dispersion of GPL in the top and bottom faces of the sandwich beam. The Physics-Informed Neural Network (PINN) method is employed to model the nonlinear deflection of the beam under various boundary conditions. This study highlights the effectiveness of PINN in handling the complexities of nonlinear structural analyses. The findings underscore the impact of the core auxeticity, GPL amount and distribution, and elastic foundation coefficient on the nonlinear deflection of the sandwich beam under different loading scenarios. For instance, using Type I configuration can reduce the deflection of the beam by nearly half compared to using Type IV. Furthermore, a nonlinear foundation with a unit coefficient results in a 48% reduction in deflection compared to the scenario without an elastic foundation.
Citation - WoS: 2
Citation - Scopus: 2
Physics-Informed Neural Network for Nonlinear Bending Analysis of Nano-Beams: A Systematic Hyperparameter Optimization
(MDPI, 2025) Esfahani, Saba Sadat Mirsadeghi; Fallah, Ali; Aghdam, Mohammad Mohammadi
This paper investigates the nonlinear bending analysis of nano-beams using the physics-informed neural network (PINN) method. The nonlinear governing equations for the bending of size-dependent nano-beams are derived from Hamilton's principle, incorporating nonlocal strain gradient theory, and based on Euler-Bernoulli beam theory. In the PINN method, the solution is approximated by a deep neural network, with network parameters determined by minimizing a loss function that consists of the governing equation and boundary conditions. Despite numerous reports demonstrating the applicability of the PINN method for solving various engineering problems, tuning the network hyperparameters remains challenging. In this study, a systematic approach is employed to fine-tune the hyperparameters using hyperparameter optimization (HPO) via Gaussian process-based Bayesian optimization. Comparison of the PINN results with available reference solutions shows that the PINN, with the optimized parameters, produces results with high accuracy. Finally, the impacts of boundary conditions, different loads, and the influence of nonlocal strain gradient parameters on the bending behavior of nano-beams are investigated.