[HTML][HTML] Real-time Bayesian inversion in resin transfer moulding using neural surrogates

ME Causon, MA Iglesias, MY Matveev… - Composites Part A …, 2024 - Elsevier
Abstract In Resin Transfer Moulding (RTM), local variations in reinforcement properties
(porosity and permeability) and the formation of gaps along the reinforcement edges result …

Comprehensive Composite Mould Filling Pattern Dataset for Process Modelling and Prediction

BX Chai, J Wang, TKM Dang, M Nikzad… - Journal of Composites …, 2024 - mdpi.com
The Resin Transfer Moulding process receives great attention from both academia and
industry, owing to its superior manufacturing rate and product quality. Particularly, the …

[HTML][HTML] Application of machine learning for composite moulding process modelling

Y Wang, S Xu, KH Bwar, B Eisenbart, G Lu… - Composites …, 2024 - Elsevier
Fibre-reinforced composites are commonly manufactured through moulding processes such
as Resin Transfer Moulding (RTM) due to their great reliability and scalability. State-of-the …

Comparative research of flow in tube bundle: Source term method and pressure drop method

Y Che, S Zu, L Huang - Chemical Engineering Research and Design, 2024 - Elsevier
There are two methods for calculating fluid in porous materials, namely the pressure drop
method (PDM) and the source term method (STM), which are widely utilized in their …

Sensitivity analysis using Physics-informed neural networks

JM Hanna, JV Aguado, S Comas-Cardona… - … Applications of Artificial …, 2024 - Elsevier
The goal of this paper is to provide a simple approach to perform local sensitivity analysis
using Physics-informed neural networks (PINN). The main idea lies in adding a new term in …

The accurate prediction and further optimization of thermal conductivity for 3D fully ceramic microencapsulated fuel via graph convolutional neural network

J Hou, Z Gong, X Ding, J Sun, R Tang, H Xiao… - Materials Today …, 2025 - Elsevier
Fully ceramic microencapsulated (FCM) is a new type of composite fuel in the nuclear
energy field; it has emerged as a promising candidate for accident-tolerant fuel (ATF), owing …

Variance-based loss function for improved regularization

JM Hanna, IE Vignon-Clemental - arXiv preprint arXiv:2412.13993, 2024 - arxiv.org
In deep learning, the mean of a chosen error metric, such as squared or absolute error, is
commonly used as a loss function. While effective in reducing the average error, this …

[PDF][PDF] Composites Communications

G Chao, X An, L Zhang, J Tian, W Fan, T Liu - Composites, 2021 - ohedept.mums.ac.ir
With the rapid urbanization and fast growth of transportation, noise pollution has become
one of the most serious environmental problems in front of the people worldwide, it usually …