Methodology for optical characterization of multi-scale morphologically complex heterogeneous media - Application to snow with soot impurities

Dai, Xiaoyu; Haussener, Sophia

doi:10.1088/1742-6596/676/1/012003

Cited by 1 publication

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attempts of using other macroscopic properties like tortuosity, mean pore diameter, chord lengths, etc., or two-point functions such as void-void, and surface-surface correlations [70] did not further improve the training results. This was in contrast to a study using ANNs to predict oxygen generation in a solar-driven porous thermochemical reactors using macroscopic properties of the porous media observed where significant improvement in predictions were observed using the inputs tortuosity, surface-void, void-void, and surface-surface correlations [54]. 4: Distribution and relative variation of macroscopic properties -φ and A -from the characterization and results from the simulationst melt , ∆P, mean values of the heat flux, q , and shear stress, τ , fields on the interface surface mesh of the macro-porous unit-cells -for random (blue) and ordered (orange) sub-structures.…”

Section: Training: Anncontrasting

confidence: 88%

“…Artificial Neural Networks (ANNs) have been applied in porous media for autonomous characterization of 3D porous samples [47,48], They have been used often for performing feature selection of macroscopic and pore-network properties to optimally characterize permeability of the porous media [49,50,51,52,53] using 3D images from CT-scans. In thermal applications context, ANNs have been used to predict the oxygen output in a solar-driven porous thermochemical reactors based on their macroscopic properties [54], and to predict radiative properties within 2D opaque and transparent porous media and packed beds [55,56] to replicate the computationally expensive Monte Carlo ray tracing-based results. The 3D CNN has been used to predict the steady state solution of the Navier-stokes laminar flow equation in a porous structure [57] with macroscopic features (Euclidean distance, maximum inscribed sphere size, and time of flight) and the binary images as inputs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Geodesic Convolutional Neural Network Characterization of Macro-Porous Latent Thermal Energy Storage

Mallya

Baqué²,

Yvernay³

et al. 2023

ASME Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

High-temperature latent heat thermal energy storage with metallic alloy phase change materials (PCMs) utilize the high latent heat and high thermal conductivity to gain a competitive edge over existing sensible and latent storage technologies. Novel macroporous latent heat storage units can be used to enhance the limiting convective heat transfer between the heat transfer fluid and the PCM to attain higher power density while maintaining high energy density. 3D monolithic percolating macroporous latent heat storage unit cells with random and ordered substructure topology were created using synthetic tomography data. Full 3D thermal computational fluid dynamics (CFD) simulations with phase change modeling was performed on 1000+ such structures using effective heat capacity method and temperature- and phase-dependent thermophysical properties. Design parameters, including transient thermal and flow characteristics, phase change time and pressure drop, were extracted as output scalars from the simulated charging process. As such structures cannot be parametrized meaningfully, a mesh-based Geodesic Convolutional Neural Network (GCNN) designed to perform direct convolutions on the surface and volume meshes of the macroporous structures was trained to predict the output scalars along with pressure, temperature, velocity distributions in the volume, and surface distributions of heat flux and shear stress. An Artificial Neural Network (ANN) using macroscopic properties—porosity, surface area, and two-point surface-void correlation functions—of the structures as inputs was used as a standard regressor for comparison. The GCNN exhibited high prediction accuracy of the scalars, outperforming the ANN and linear/exponential fits, owing to the disentangling property of GCNNs where predictions were improved by the introduction of correlated surface and volume fields. The trained GCNN behaves as a coupled CFD-heat transfer emulator predicting the volumetric distribution of temperature, pressure, velocity fields, and heat flux and shear stress distributions at the PCM–HTF interface. This deep learning based methodology offers a unique, generalized, and computationally competitive way to quickly predict phase change behavior of high power density macroporous structures in a few seconds and has the potential to optimize the percolating macroporous unit cells to application specific requirements.

show abstract

Section: Training: Anncontrasting

confidence: 88%