Material Data Identification in an Induction Hardening Test Rig with Physics-Informed Neural Networks
Physics-Informed neural networks (PINNs) have demonstrated remarkable performance in solving partial differential equations (PDEs) by incorporating the governing PDEs into the network’s loss function during optimization. PINNs have been successfully applied to diverse inverse and forward problems. T...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Materials |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1944/16/14/5013 |
_version_ | 1797588523968102400 |
---|---|
author | Mohammad Zhian Asadzadeh Klaus Roppert Peter Raninger |
author_facet | Mohammad Zhian Asadzadeh Klaus Roppert Peter Raninger |
author_sort | Mohammad Zhian Asadzadeh |
collection | DOAJ |
description | Physics-Informed neural networks (PINNs) have demonstrated remarkable performance in solving partial differential equations (PDEs) by incorporating the governing PDEs into the network’s loss function during optimization. PINNs have been successfully applied to diverse inverse and forward problems. This study investigates the feasibility of using PINNs for material data identification in an induction hardening test rig. By utilizing temperature sensor data and imposing the heat equation with initial and boundary conditions, thermo-physical material properties, such as specific heat, thermal conductivity, and the heat convection coefficient, were estimated. To validate the effectiveness of the PINNs in material data estimation, benchmark data generated by a finite element model (FEM) of an air-cooled cylindrical sample were used. The accurate identification of the material data using only a limited number of virtual temperature sensor data points was demonstrated. The influence of the sensor positions and measurement noise on the uncertainty of the estimated parameters was examined. The study confirms the robustness and accuracy of this approach in the presence of measurement noise, albeit with lower efficiency, thereby requiring more time to converge. Lastly, the applicability of the presented approach to real measurement data obtained from an air-cooled cylindrical sample heated in an induction heating test rig was discussed. This research contributes to the accurate offline estimation of material data and has implications for optimizing induction heat treatments. |
first_indexed | 2024-03-11T00:53:16Z |
format | Article |
id | doaj.art-dd4ce394b8b34326a72c7a131b25111d |
institution | Directory Open Access Journal |
issn | 1996-1944 |
language | English |
last_indexed | 2024-03-11T00:53:16Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Materials |
spelling | doaj.art-dd4ce394b8b34326a72c7a131b25111d2023-11-18T20:16:39ZengMDPI AGMaterials1996-19442023-07-011614501310.3390/ma16145013Material Data Identification in an Induction Hardening Test Rig with Physics-Informed Neural NetworksMohammad Zhian Asadzadeh0Klaus Roppert1Peter Raninger2Materials Center Leoben Forschung GmbH (MCL), Roseggerstraße 12, 8700 Leoben, AustriaInstitute of Fundamentals and Theory of Electrical Engineering, Technical University of Graz, Inffeldgasse 18/I, 8010 Graz, AustriaMaterials Center Leoben Forschung GmbH (MCL), Roseggerstraße 12, 8700 Leoben, AustriaPhysics-Informed neural networks (PINNs) have demonstrated remarkable performance in solving partial differential equations (PDEs) by incorporating the governing PDEs into the network’s loss function during optimization. PINNs have been successfully applied to diverse inverse and forward problems. This study investigates the feasibility of using PINNs for material data identification in an induction hardening test rig. By utilizing temperature sensor data and imposing the heat equation with initial and boundary conditions, thermo-physical material properties, such as specific heat, thermal conductivity, and the heat convection coefficient, were estimated. To validate the effectiveness of the PINNs in material data estimation, benchmark data generated by a finite element model (FEM) of an air-cooled cylindrical sample were used. The accurate identification of the material data using only a limited number of virtual temperature sensor data points was demonstrated. The influence of the sensor positions and measurement noise on the uncertainty of the estimated parameters was examined. The study confirms the robustness and accuracy of this approach in the presence of measurement noise, albeit with lower efficiency, thereby requiring more time to converge. Lastly, the applicability of the presented approach to real measurement data obtained from an air-cooled cylindrical sample heated in an induction heating test rig was discussed. This research contributes to the accurate offline estimation of material data and has implications for optimizing induction heat treatments.https://www.mdpi.com/1996-1944/16/14/5013neural networksinverse problemsPINNSinduction heatingmaterial data |
spellingShingle | Mohammad Zhian Asadzadeh Klaus Roppert Peter Raninger Material Data Identification in an Induction Hardening Test Rig with Physics-Informed Neural Networks Materials neural networks inverse problems PINNS induction heating material data |
title | Material Data Identification in an Induction Hardening Test Rig with Physics-Informed Neural Networks |
title_full | Material Data Identification in an Induction Hardening Test Rig with Physics-Informed Neural Networks |
title_fullStr | Material Data Identification in an Induction Hardening Test Rig with Physics-Informed Neural Networks |
title_full_unstemmed | Material Data Identification in an Induction Hardening Test Rig with Physics-Informed Neural Networks |
title_short | Material Data Identification in an Induction Hardening Test Rig with Physics-Informed Neural Networks |
title_sort | material data identification in an induction hardening test rig with physics informed neural networks |
topic | neural networks inverse problems PINNS induction heating material data |
url | https://www.mdpi.com/1996-1944/16/14/5013 |
work_keys_str_mv | AT mohammadzhianasadzadeh materialdataidentificationinaninductionhardeningtestrigwithphysicsinformedneuralnetworks AT klausroppert materialdataidentificationinaninductionhardeningtestrigwithphysicsinformedneuralnetworks AT peterraninger materialdataidentificationinaninductionhardeningtestrigwithphysicsinformedneuralnetworks |