On the use of neural networks to evaluate performances of shell models for composites

Abstract

This paper presents a novel methodology to assess the accuracy of shell finite elements via neural networks. The proposed framework exploits the synergies among three well-established methods, namely, the Carrera Unified Formulation (CUF), the Finite Element Method (FE), and neural networks (NN). CUF generates the governing equations for any-order shell theories based on polynomial expansions over the thickness. FE provides numerical results feeding the NN for training. Multilayer NN have the generalized displacement variables, and the thickness ratio as inputs, and the target is the maximum transverse displacement. This work investigates the minimum requirements for the NN concerning the number of neurons and hidden layers, and the size of the training set. The results look promising as the NN requires a fraction of FE analyses for training, can evaluate the accuracy of any-order model, and can incorporate physical features, e.g., the thickness ratio, that drive the complexity of the mathematical model. In other words, NN can trigger fast informed decision-making on the structural model to use and the influence of design parameters without the need of modifying, rebuild, or rerun an FE model.

Metamodel-Based Uncertainty Quantification for the Mechanical Behavior of Braided Composites

“…Applications of classification for cracking detection and clustering for automated inspection of yarn deformations can be found in (Mardanshahi et al, 2020) and (Mendoza et al, 2019), respectively. Finally, non-classical effects regarding composite modeling with shell elements were evaluated combining the Carrera unified formulation and ANN in (Petrolo and Carrera, 2020) and (Petrolo and Carrera, 2021).…”

Optimal Element-Wise Distributions of Structural Theories from Neural Networks

“…NN are used as surrogate models to substitute FE models and obtain structural responses. The combined use of CUF, AAM, NDK, and Neural Networks (NN) is a promising approach to build surrogate models that can provide information on the structural theory and finite element discretization for a given problem [9,10].…”