Introducing ANN-GP algorithm to estimate transient bending of the functionally graded graphene origami-enabled auxetic metamaterial structures

Abstract

This article presents a new method called the artificial neural networks-genetic programming (ANNs-GP) algorithm, which effectively predicts the bending behavior of functionally graded graphene origami-enabled auxetic metamaterial (FG-GORAM) structures under transient conditions. Functionally graded materials (FGMs) display spatial heterogeneity in their composition and microstructure, resulting in distinctive mechanical characteristics that make them well-suited for a wide range of engineering applications. The objective of this study is to create a prediction model that can accurately capture the intricate transient bending behavior of FGM structures. To do this, the researchers have used the ANN-GP technique, which combines ANNs with GP. The ANN component acquires knowledge from a dataset including actual or simulated bending data, while the GP component fine-tunes the structure and parameters of the neural network to improve its ability to make accurate predictions. The proposed algorithm combines the strengths of ANNs and GP to accurately predict the bending behavior of FG-GORAM structures. This algorithm is robust and efficient, allowing designers and engineers to optimize the performance and reliability of these structures in various applications. The effectiveness of the ANN-GP method is proved by comparing it to experimental or simulated data. This shows that the algorithm has the potential to be a useful tool for designing and analyzing sophisticated materials and structures.