A generalized characterization of radiative properties of porous media using engineered features and artificial neural networks

Amirsaman Eghtesad; Farhin Tabassum; Shima Hajimirza

doi:10.1016/j.ijheatmasstransfer.2023.123890

A generalized characterization of radiative properties of porous media using engineered features and artificial neural networks

Amirsaman Eghtesad, Farhin Tabassum, Shima Hajimirza

Department of Mechanical Engineering

Stevens Institute of Technology

Research output: Contribution to journal › Article › peer-review

Abstract

At the core of many engineering applications is the evaluation of the radiative responses of materials and devices, particularly at high temperatures. Researchers have focused their attention for decades on the investigation of radiation heat transport (RHT) in porous media. Monte Carlo ray tracing (MCRT) is a reliable computational alternative to the otherwise expensive or infeasible experimental measurements for RHT in heterogeneous media. Despite the accuracy, the computational cost of MCRT simulations can be burdensome given the convergence requirements, the complexity of materials (e.g., large number of particles in a porous medium), and space of input physical specifications (e.g., angle and/or location of incoming rays, wavelength, etc.). This study is an attempt to replace MCRT simulations with supervised learning algorithms. Ground truth labeling data is generated using MCRT for random overlapping and non-overlapping circular packed porous media and solving the classical radiative transfer equation (RTE). A significantly low-cost physical and geometrical-based artificial neural network (ANN) model is developed to forecast the radiative characteristics of arbitrary porous configurations, using engineered geometric features. Using the ANN model, a sensitivity analysis is conducted to assess the relative importance of the designed features. This insight helps in identifying the most crucial features to improve the learning for more complex geometries. The precision of predictions is calculated based on different hypotheses made over the training data, i.e., whole-size, wall-wise, and pointwise classes. It is shown that when overlapping circles are used as training, the designed model can predict the radiative properties of out-sample data for the first two classes with the accuracy of R²>0.944 and R²>0.787, while more directional engineering features are required to achieve higher accuracies for the former class. Results show that the current model is highly generalizable and applicable to a variety of porous configurations.

Original language	English
Article number	123890
Journal	International Journal of Heat and Mass Transfer
Volume	205
DOIs	https://doi.org/10.1016/j.ijheatmasstransfer.2023.123890
State	Published - May 15 2023

ASJC Scopus subject areas

Condensed Matter Physics
Mechanical Engineering
Fluid Flow and Transfer Processes

Keywords

Artificial neural network
Engineering features
Monte Carlo ray tracing
Porous media
Radiative properties

Access to Document

10.1016/j.ijheatmasstransfer.2023.123890

Cite this

@article{b0dffaa7ea2b4f08b073ce07263a6feb,

title = "A generalized characterization of radiative properties of porous media using engineered features and artificial neural networks",

abstract = "At the core of many engineering applications is the evaluation of the radiative responses of materials and devices, particularly at high temperatures. Researchers have focused their attention for decades on the investigation of radiation heat transport (RHT) in porous media. Monte Carlo ray tracing (MCRT) is a reliable computational alternative to the otherwise expensive or infeasible experimental measurements for RHT in heterogeneous media. Despite the accuracy, the computational cost of MCRT simulations can be burdensome given the convergence requirements, the complexity of materials (e.g., large number of particles in a porous medium), and space of input physical specifications (e.g., angle and/or location of incoming rays, wavelength, etc.). This study is an attempt to replace MCRT simulations with supervised learning algorithms. Ground truth labeling data is generated using MCRT for random overlapping and non-overlapping circular packed porous media and solving the classical radiative transfer equation (RTE). A significantly low-cost physical and geometrical-based artificial neural network (ANN) model is developed to forecast the radiative characteristics of arbitrary porous configurations, using engineered geometric features. Using the ANN model, a sensitivity analysis is conducted to assess the relative importance of the designed features. This insight helps in identifying the most crucial features to improve the learning for more complex geometries. The precision of predictions is calculated based on different hypotheses made over the training data, i.e., whole-size, wall-wise, and pointwise classes. It is shown that when overlapping circles are used as training, the designed model can predict the radiative properties of out-sample data for the first two classes with the accuracy of R2>0.944 and R2>0.787, while more directional engineering features are required to achieve higher accuracies for the former class. Results show that the current model is highly generalizable and applicable to a variety of porous configurations.",

keywords = "Artificial neural network, Engineering features, Monte Carlo ray tracing, Porous media, Radiative properties",

author = "Amirsaman Eghtesad and Farhin Tabassum and Shima Hajimirza",

note = "Publisher Copyright: {\textcopyright} 2023",

year = "2023",

month = may,

day = "15",

doi = "10.1016/j.ijheatmasstransfer.2023.123890",

language = "English",

volume = "205",

journal = "International Journal of Heat and Mass Transfer",

issn = "0017-9310",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - A generalized characterization of radiative properties of porous media using engineered features and artificial neural networks

AU - Eghtesad, Amirsaman

AU - Tabassum, Farhin

AU - Hajimirza, Shima

PY - 2023/5/15

Y1 - 2023/5/15

N2 - At the core of many engineering applications is the evaluation of the radiative responses of materials and devices, particularly at high temperatures. Researchers have focused their attention for decades on the investigation of radiation heat transport (RHT) in porous media. Monte Carlo ray tracing (MCRT) is a reliable computational alternative to the otherwise expensive or infeasible experimental measurements for RHT in heterogeneous media. Despite the accuracy, the computational cost of MCRT simulations can be burdensome given the convergence requirements, the complexity of materials (e.g., large number of particles in a porous medium), and space of input physical specifications (e.g., angle and/or location of incoming rays, wavelength, etc.). This study is an attempt to replace MCRT simulations with supervised learning algorithms. Ground truth labeling data is generated using MCRT for random overlapping and non-overlapping circular packed porous media and solving the classical radiative transfer equation (RTE). A significantly low-cost physical and geometrical-based artificial neural network (ANN) model is developed to forecast the radiative characteristics of arbitrary porous configurations, using engineered geometric features. Using the ANN model, a sensitivity analysis is conducted to assess the relative importance of the designed features. This insight helps in identifying the most crucial features to improve the learning for more complex geometries. The precision of predictions is calculated based on different hypotheses made over the training data, i.e., whole-size, wall-wise, and pointwise classes. It is shown that when overlapping circles are used as training, the designed model can predict the radiative properties of out-sample data for the first two classes with the accuracy of R2>0.944 and R2>0.787, while more directional engineering features are required to achieve higher accuracies for the former class. Results show that the current model is highly generalizable and applicable to a variety of porous configurations.

AB - At the core of many engineering applications is the evaluation of the radiative responses of materials and devices, particularly at high temperatures. Researchers have focused their attention for decades on the investigation of radiation heat transport (RHT) in porous media. Monte Carlo ray tracing (MCRT) is a reliable computational alternative to the otherwise expensive or infeasible experimental measurements for RHT in heterogeneous media. Despite the accuracy, the computational cost of MCRT simulations can be burdensome given the convergence requirements, the complexity of materials (e.g., large number of particles in a porous medium), and space of input physical specifications (e.g., angle and/or location of incoming rays, wavelength, etc.). This study is an attempt to replace MCRT simulations with supervised learning algorithms. Ground truth labeling data is generated using MCRT for random overlapping and non-overlapping circular packed porous media and solving the classical radiative transfer equation (RTE). A significantly low-cost physical and geometrical-based artificial neural network (ANN) model is developed to forecast the radiative characteristics of arbitrary porous configurations, using engineered geometric features. Using the ANN model, a sensitivity analysis is conducted to assess the relative importance of the designed features. This insight helps in identifying the most crucial features to improve the learning for more complex geometries. The precision of predictions is calculated based on different hypotheses made over the training data, i.e., whole-size, wall-wise, and pointwise classes. It is shown that when overlapping circles are used as training, the designed model can predict the radiative properties of out-sample data for the first two classes with the accuracy of R2>0.944 and R2>0.787, while more directional engineering features are required to achieve higher accuracies for the former class. Results show that the current model is highly generalizable and applicable to a variety of porous configurations.

KW - Artificial neural network

KW - Engineering features

KW - Monte Carlo ray tracing

KW - Porous media

KW - Radiative properties

UR - http://www.scopus.com/inward/record.url?scp=85147590205&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85147590205&partnerID=8YFLogxK

U2 - 10.1016/j.ijheatmasstransfer.2023.123890

DO - 10.1016/j.ijheatmasstransfer.2023.123890

M3 - Article

SN - 0017-9310

VL - 205

JO - International Journal of Heat and Mass Transfer

JF - International Journal of Heat and Mass Transfer

M1 - 123890

ER -

A generalized characterization of radiative properties of porous media using engineered features and artificial neural networks

Abstract

ASJC Scopus subject areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this