ItemArticle

Fractional MooreGibsonThomson thermoelastic analysis of nonlocal nanobeams under moving heat source with machine learning-assisted predictive modeling

Title
Fractional MooreGibsonThomson thermoelastic analysis of nonlocal nanobeams under moving heat source with machine learning-assisted predictive modeling
Creator
Singhal, Abhinav; Abass, Kasim Sakran; Hassaballa, Abaker A.; Ahmed, Nada
Description
This study presents a comprehensive investigation of thermoelastic wave propagation in nonlocal nanobeams subjected to a moving heat source within the framework of fractional MooreGibsonThomson (MGT) heat conduction theory. The model incorporates nonlocal elasticity to capture size-dependent mechanical behavior and employs a fractional-order formulation to account for thermal memory and finite-speed heat propagation. The coupled governing equations are derived and solved analytically using Laplace transform techniques to obtain the temperature, displacement, and stress distributions. A detailed parametric analysis is performed to examine the effects of fractional order, nonlocal parameter, thermal relaxation time, and source velocity on the thermoelastic response. The results reveal significant modifications in wave attenuation, temperature evolution, and stress distribution due to the combined influence of nonlocality and fractional thermal effects, particularly under moving thermal loads. To enhance computational efficiency and enable rapid prediction of system responses, a machine learning-based surrogate framework is developed using an artificial neural network (ANN). The network is trained on data generated from the present analytical model and is shown to accurately predict thermoelastic fields across a wide range of governing parameters. The ANN predictions exhibit excellent agreement with analytical results, demonstrating its capability as a reliable reduced-order modeling tool. The proposed hybrid analyticalcomputational approach provides new insights into thermoelastic behavior at the nanoscale and offers an efficient predictive framework for heat transfer applications involving moving thermal loads. This study is motivated by the need to address unresolved challenges in modeling thermoelastic behavior at the nanoscale, particularly the simultaneous incorporation of fractional heat conduction, nonlocal elasticity, and moving thermal loads within a unified framework. 2026 Published by Elsevier Ltd.
Source
International Communications in Heat and Mass Transfer;Volume;175;Issue;P3;Article No.;111154;
Date
01-01-2026
Publisher
Elsevier Ltd
Subject
Artificial neural network; Fractional MooreGibsonThomson model; Moving heat source; Nanobeam heat transfer; Nanoscale thermal waves; Nonlocal thermoelasticity; Surrogate modeling
Coverage
Singhal A., Christ University, Bengaluru, 560029, India; Abass K.S., University of Kirkuk, Kirkuk, 36001, Iraq; Hassaballa A.A., Center for Scientific Research and Entrepreneurship, Northern Border University, Arar, 73213, Saudi Arabia; Ahmed N., Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 7351933; CODEN: IHMTD
Format
online
Language
English
Type
Article

Citation

Singhal, Abhinav; Abass, Kasim Sakran; Hassaballa, Abaker A.; Ahmed, Nada, “Fractional MooreGibsonThomson thermoelastic analysis of nonlocal nanobeams under moving heat source with machine learning-assisted predictive modeling,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 19, 2026, https://archives.christuniversity.in/items/show/22283.

Output Formats