Designing architectured ceramics for transient thermal applications using finite element and deep learning

TL;DR

This paper introduces a machine learning approach using CNNs and MLPs trained on finite element analysis data to efficiently design architectured ceramics with enhanced thermo-mechanical properties for transient thermal applications.

Contribution

It presents a novel method combining FEA and deep learning to predict optimal ceramic architectures, reducing the need for extensive simulations.

Findings

CNN and MLP models effectively predict thermo-mechanical responses.

Optimal design achieved with approximately 30% reduction in edge temperature.

Limited FEA data suffices for accurate neural network training.

Abstract

Topologically interlocking architectures can generate tough ceramics with attractive thermo-mechanical properties. This concept can make the material design pathway a challenging task, since modeling the whole design space is neither effective nor feasible. We propose an approach to design high-performance architectured ceramics using machine learning (ML) with data from finite element analysis (FEA). Convolutional neural networks (CNNs) and Multilayer Perceptrons (MLPs) are used as the deep learning approaches. A limited set of FEA simulation data containing a variety of architectural design parameters is used to train our neural networks, including learning how independent and dependent design parameters are related. A trained network is then used to predict the optimum structure from the configurations. A FEA simulation is run on the best predictions of both MLP and CNN algorithms to evaluate the performance of our networks. Although a limited amount of simulation data are available, our networks are effective in predicting the transient thermo-mechanical responses of possible panel designs. For example, the optimal design after using CNN prediction resulted in $\approx \! 30\%$ improvement in terms of edge temperature.