English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Conjugate heat transfer (CHT) models are vital for the design of manyengineering systems. However, high-fidelity CHT models are computationallyintensive, which limits their use in applications such as design optimization,where hundreds to thousands of model evaluations are required. In this work, wedevelop a modular deep convolutional encoder-decoder hierarchical (DeepEDH)neural network, a novel deep-learning-based surrogate modeling methodology forcomputationally intensive CHT models. Leveraging convective temperaturedependencies, we propose a two-stage temperature prediction architecture thatcouples velocity and temperature models. The proposed DeepEDH methodology isdemonstrated by modeling the pressure, velocity, and temperature fields for aliquid-cooled cold-plate-based battery thermal management system with variablechannel geometry. A computational model of the cold plate is developed andsolved using the finite element method (FEM), generating a dataset of 1,500simulations. The FEM results are transformed and scaled from unstructured tostructured, image-like meshes to create training and test datasets. The DeepEDHmethodology's performance is examined in relation to data scaling, trainingdataset size, and network depth. Our performance analysis covers the impact ofthe novel architecture, separate field models, output geometry masks,multi-stage temperature models, and optimizations of the hyperparameters andarchitecture. Furthermore, we quantify the influence of the CHT thermalboundary condition on surrogate model performance, highlighting improvedtemperature model performance with higher heat fluxes. Compared to other deeplearning neural network surrogate models, such as U-Net and DenseED, theproposed DeepEDH methodology for CHT models exhibits up to a 65% enhancement inthe coefficient of determination ($R^{2}$).

Deep convolutional encoder-decoder hierarchical neural networks for conjugate heat transfer surrogate modeling