ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Thermal diffusion in discontinuous media: A hybrid peridynamics-based machine learning model

Ramesh Babu, J and Gopalakrishanan, S (2024) Thermal diffusion in discontinuous media: A hybrid peridynamics-based machine learning model. In: Computers and Structures, 290 .

[img] PDF
com_str_290_2024.pdf - Published Version
Restricted to Registered users only

Download (11MB) | Request a copy
Official URL: https://doi.org/10.1016/j.compstruc.2023.107179


This paper introduces a novel hybrid formulation of a peridynamics-based machine learning model for thermal diffusion analysis in one-dimensional and two-dimensional problems with evolving discontinuities. The hybrid model employs a multivariate linear regression approach to establish the relationship between the temperature values of material points, their neighboring points, and the applied external heat flux. The thermal modal analysis method uses the finite element method to generate training and testing data. An efficient numerical procedure is also developed to couple the peridynamics model and the peridynamics-based machine learning model. The model is analyzed under multiple configurations of micro-thermal conductivity functions for one-dimensional thermal bar problems, under both steady-state and transient loading conditions, to identify the configuration that exhibits superior convergence behavior towards the local solution. Furthermore, benchmark problems demonstrate the high accuracy of the formulated hybrid model, including the analysis of thermal plates with discontinuities, such as a plate with a hole, a plate with a pre-existing insulated crack, and plate with a bi-material interface with stationary and evolving discontinuances. The hybrid model effectively captures intricate discontinuities and boundaries while being computationally efficient, indicating its potential for thermal diffusion analysis in one- and two-dimensional problems with stationary and evolving discontinuities. © 2023 Elsevier Ltd

Item Type: Journal Article
Publication: Computers and Structures
Publisher: Elsevier Ltd
Additional Information: The copyright for this article belongs to the Elsevier Ltd.
Keywords: 3D modeling; Heat flux; Machine learning; Thermal conductivity; Thermal diffusion, Damage; Diffusion analysis; Hybrid model; Machine learning models; Machine-learning; Multivariate linear regressions; One-dimensional; Peridynamics; Thermal; Thermal modal analyse, Modal analysis
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 09 Dec 2023 04:51
Last Modified: 09 Dec 2023 04:51
URI: https://eprints.iisc.ac.in/id/eprint/83333

Actions (login required)

View Item View Item