Výsledky vyhledávání - "Mirkhalaf, Mohsen"

Report

Test-time data augmentation: improving predictions of recurrent neural network models of composites

Recurrent Neural Networks (RNNs) have emerged as an interesting alternative to conventional material modeling approaches, particularly for nonlinear path dependent materials. Remarkable computational enhancements are obtained using RNNs compared to c

Externí odkaz: http://arxiv.org/abs/2409.02478

Zobrazit plný text záznamu

Report

A novel Taguchi-based approach for optimizing neural network architectures: application to elastic short fiber composites

Autor: Nikzad, Mohammad Hossein, Heidari-Rarani, Mohammad, Mirkhalaf, Mohsen

This study presents an innovative application of the Taguchi design of experiment method to optimize the structure of an Artificial Neural Network (ANN) model for the prediction of elastic properties of short fiber reinforced composites. The main goa

Externí odkaz: http://arxiv.org/abs/2407.19802

Zobrazit plný text záznamu

Report

Augmentation of scarce data -- a new approach for deep-learning modeling of composites

Autor: Cheung, Hon Lam, Uvdal, Petter, Mirkhalaf, Mohsen

High-fidelity full-field micro-mechanical modeling of the non-linear path-dependent materials demands a substantial computational effort. Recent trends in the field incorporates data-driven Artificial Neural Networks (ANNs) as surrogate models. Howev

Externí odkaz: http://arxiv.org/abs/2311.14557

Zobrazit plný text záznamu

Report

Recurrent neural networks and transfer learning for elasto-plasticity in woven composites

Autor: Ghane, Ehsan, Fagerström, Martin, Mirkhalaf, Mohsen

As a surrogate for computationally intensive meso-scale simulation of woven composites, this article presents Recurrent Neural Network (RNN) models. Leveraging the power of transfer learning, the initialization challenges and sparse data issues inher

Externí odkaz: http://arxiv.org/abs/2311.13434

Zobrazit plný text záznamu