Analytical finite-integral-transform and gradient-enhanced machine learning approach for thermoelastic analysis of FGM spherical structures with arbitrary properties

This study introduces a novel mathematical model that combines the finite integral transform (FIT) and gradient-enhanced physics-informed neural network (g-PINN) to address thermomechanical problems in functionally graded materials with varying properties. The model employs a multilayer heterostruct...

Full description

Saved in:
Bibliographic Details
Main Authors: Palash Das, Dipayan Mondal, Md. Ashraful Islam, Md. Abdullah Al Mohotadi, Prokash Chandra Roy
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Theoretical and Applied Mechanics Letters
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S209503492500008X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849329556294467584
author Palash Das
Dipayan Mondal
Md. Ashraful Islam
Md. Abdullah Al Mohotadi
Prokash Chandra Roy
author_facet Palash Das
Dipayan Mondal
Md. Ashraful Islam
Md. Abdullah Al Mohotadi
Prokash Chandra Roy
author_sort Palash Das
collection DOAJ
description This study introduces a novel mathematical model that combines the finite integral transform (FIT) and gradient-enhanced physics-informed neural network (g-PINN) to address thermomechanical problems in functionally graded materials with varying properties. The model employs a multilayer heterostructure homogeneous approach within the FIT to linearize and approximate various parameters, such as the thermal conductivity, specific heat, density, stiffness, thermal expansion coefficient, and Poisson’s ratio. The provided FIT and g-PINN techniques are highly proficient in solving the PDEs of energy equations and equations of motion in a spherical domain, particularly when dealing with space-time dependent boundary conditions. The FIT method simplifies the governing partial differential equations into ordinary differential equations for efficient solutions, whereas the g-PINN bypasses linearization, achieving high accuracy with fewer training data (error < 3.8%). The approach is applied to a spherical pressure vessel, solving energy and motion equations under complex boundary conditions. Furthermore, extensive parametric studies are conducted herein to demonstrate the impact of different property profiles and radial locations on the transient evolution and dynamic propagation of thermomechanical stresses. However, the accuracy of the presented approach is evaluated by comparing the g-PINN results, which have an error of less than 3.8%. Moreover, this model offers significant potential for optimizing materials in high-temperature reactors and chemical plants, improving safety, extending lifespan, and reducing thermal fatigue under extreme processing conditions.
format Article
id doaj-art-a71bd73b6a1946b1bae7cbfa7a32a785
institution Kabale University
issn 2095-0349
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Theoretical and Applied Mechanics Letters
spelling doaj-art-a71bd73b6a1946b1bae7cbfa7a32a7852025-08-20T03:47:13ZengElsevierTheoretical and Applied Mechanics Letters2095-03492025-05-0115310057610.1016/j.taml.2025.100576Analytical finite-integral-transform and gradient-enhanced machine learning approach for thermoelastic analysis of FGM spherical structures with arbitrary propertiesPalash Das0Dipayan Mondal1Md. Ashraful Islam2Md. Abdullah Al Mohotadi3Prokash Chandra Roy4Department of Mechanical Engineering, Khulna University of Engineering &amp; Technology, Khulna-9203, Bangladesh; Department of Mechanical Engineering, Bangladesh Army University of Science and Technology, Saidpur, BangladeshDepartment of Mechanical Engineering, Khulna University of Engineering &amp; Technology, Khulna-9203, Bangladesh; Corresponding author.Department of Mechanical Engineering, Khulna University of Engineering &amp; Technology, Khulna-9203, BangladeshDepartment of Mechanical Engineering, Bangladesh Army University of Science and Technology, Saidpur, BangladeshDepartment of Mechanical Engineering, Khulna University of Engineering &amp; Technology, Khulna-9203, BangladeshThis study introduces a novel mathematical model that combines the finite integral transform (FIT) and gradient-enhanced physics-informed neural network (g-PINN) to address thermomechanical problems in functionally graded materials with varying properties. The model employs a multilayer heterostructure homogeneous approach within the FIT to linearize and approximate various parameters, such as the thermal conductivity, specific heat, density, stiffness, thermal expansion coefficient, and Poisson’s ratio. The provided FIT and g-PINN techniques are highly proficient in solving the PDEs of energy equations and equations of motion in a spherical domain, particularly when dealing with space-time dependent boundary conditions. The FIT method simplifies the governing partial differential equations into ordinary differential equations for efficient solutions, whereas the g-PINN bypasses linearization, achieving high accuracy with fewer training data (error < 3.8%). The approach is applied to a spherical pressure vessel, solving energy and motion equations under complex boundary conditions. Furthermore, extensive parametric studies are conducted herein to demonstrate the impact of different property profiles and radial locations on the transient evolution and dynamic propagation of thermomechanical stresses. However, the accuracy of the presented approach is evaluated by comparing the g-PINN results, which have an error of less than 3.8%. Moreover, this model offers significant potential for optimizing materials in high-temperature reactors and chemical plants, improving safety, extending lifespan, and reducing thermal fatigue under extreme processing conditions.http://www.sciencedirect.com/science/article/pii/S209503492500008XFinite integral transformGradient- enhanced physics-informed neural networkTransient heat conductionThermoelastic stressesShock loadsFunctionally graded materials sphere
spellingShingle Palash Das
Dipayan Mondal
Md. Ashraful Islam
Md. Abdullah Al Mohotadi
Prokash Chandra Roy
Analytical finite-integral-transform and gradient-enhanced machine learning approach for thermoelastic analysis of FGM spherical structures with arbitrary properties
Theoretical and Applied Mechanics Letters
Finite integral transform
Gradient- enhanced physics-informed neural network
Transient heat conduction
Thermoelastic stresses
Shock loads
Functionally graded materials sphere
title Analytical finite-integral-transform and gradient-enhanced machine learning approach for thermoelastic analysis of FGM spherical structures with arbitrary properties
title_full Analytical finite-integral-transform and gradient-enhanced machine learning approach for thermoelastic analysis of FGM spherical structures with arbitrary properties
title_fullStr Analytical finite-integral-transform and gradient-enhanced machine learning approach for thermoelastic analysis of FGM spherical structures with arbitrary properties
title_full_unstemmed Analytical finite-integral-transform and gradient-enhanced machine learning approach for thermoelastic analysis of FGM spherical structures with arbitrary properties
title_short Analytical finite-integral-transform and gradient-enhanced machine learning approach for thermoelastic analysis of FGM spherical structures with arbitrary properties
title_sort analytical finite integral transform and gradient enhanced machine learning approach for thermoelastic analysis of fgm spherical structures with arbitrary properties
topic Finite integral transform
Gradient- enhanced physics-informed neural network
Transient heat conduction
Thermoelastic stresses
Shock loads
Functionally graded materials sphere
url http://www.sciencedirect.com/science/article/pii/S209503492500008X
work_keys_str_mv AT palashdas analyticalfiniteintegraltransformandgradientenhancedmachinelearningapproachforthermoelasticanalysisoffgmsphericalstructureswitharbitraryproperties
AT dipayanmondal analyticalfiniteintegraltransformandgradientenhancedmachinelearningapproachforthermoelasticanalysisoffgmsphericalstructureswitharbitraryproperties
AT mdashrafulislam analyticalfiniteintegraltransformandgradientenhancedmachinelearningapproachforthermoelasticanalysisoffgmsphericalstructureswitharbitraryproperties
AT mdabdullahalmohotadi analyticalfiniteintegraltransformandgradientenhancedmachinelearningapproachforthermoelasticanalysisoffgmsphericalstructureswitharbitraryproperties
AT prokashchandraroy analyticalfiniteintegraltransformandgradientenhancedmachinelearningapproachforthermoelasticanalysisoffgmsphericalstructureswitharbitraryproperties