Hybrid modeling of induction hardening processes

A simple hybrid model, integrating observation (black-box) and physical knowledge (white-box), is employed to model an induction heating process. A neural network is used to estimate the unknown physical process parameter in the physical model. Most relevant to induction hardening is the temperature...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Mohammad Zhian Asadzadeh, Peter Raninger, Petri Prevedel, Werner Ecker, Manfred Mücke
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://doaj.org/article/237c6dcc4e8b454f96ce9fb5144601e9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:237c6dcc4e8b454f96ce9fb5144601e9
record_format dspace
spelling oai:doaj.org-article:237c6dcc4e8b454f96ce9fb5144601e92021-12-01T05:05:50ZHybrid modeling of induction hardening processes2666-496810.1016/j.apples.2020.100030https://doaj.org/article/237c6dcc4e8b454f96ce9fb5144601e92021-03-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666496820300303https://doaj.org/toc/2666-4968A simple hybrid model, integrating observation (black-box) and physical knowledge (white-box), is employed to model an induction heating process. A neural network is used to estimate the unknown physical process parameter in the physical model. Most relevant to induction hardening is the temperature evolution in a layer under the surface of a sample, in our case a cylindrical sample. We show that with a hybrid model, in which a simple ordinary differential equation describes the heating rate, the experimental data can be approximated better than using a black-box only. The hybrid model extrapolates better and it is easier to interpret. The hybrid model can be used as a prediction tool to operate and optimize induction heating processes.Mohammad Zhian AsadzadehPeter RaningerPetri PrevedelWerner EckerManfred MückeElsevierarticleNeural networksHybrid modelingElectromagneticInduction heatingEngineering (General). Civil engineering (General)TA1-2040ENApplications in Engineering Science, Vol 5, Iss , Pp 100030- (2021)
institution DOAJ
collection DOAJ
language EN
topic Neural networks
Hybrid modeling
Electromagnetic
Induction heating
Engineering (General). Civil engineering (General)
TA1-2040
spellingShingle Neural networks
Hybrid modeling
Electromagnetic
Induction heating
Engineering (General). Civil engineering (General)
TA1-2040
Mohammad Zhian Asadzadeh
Peter Raninger
Petri Prevedel
Werner Ecker
Manfred Mücke
Hybrid modeling of induction hardening processes
description A simple hybrid model, integrating observation (black-box) and physical knowledge (white-box), is employed to model an induction heating process. A neural network is used to estimate the unknown physical process parameter in the physical model. Most relevant to induction hardening is the temperature evolution in a layer under the surface of a sample, in our case a cylindrical sample. We show that with a hybrid model, in which a simple ordinary differential equation describes the heating rate, the experimental data can be approximated better than using a black-box only. The hybrid model extrapolates better and it is easier to interpret. The hybrid model can be used as a prediction tool to operate and optimize induction heating processes.
format article
author Mohammad Zhian Asadzadeh
Peter Raninger
Petri Prevedel
Werner Ecker
Manfred Mücke
author_facet Mohammad Zhian Asadzadeh
Peter Raninger
Petri Prevedel
Werner Ecker
Manfred Mücke
author_sort Mohammad Zhian Asadzadeh
title Hybrid modeling of induction hardening processes
title_short Hybrid modeling of induction hardening processes
title_full Hybrid modeling of induction hardening processes
title_fullStr Hybrid modeling of induction hardening processes
title_full_unstemmed Hybrid modeling of induction hardening processes
title_sort hybrid modeling of induction hardening processes
publisher Elsevier
publishDate 2021
url https://doaj.org/article/237c6dcc4e8b454f96ce9fb5144601e9
work_keys_str_mv AT mohammadzhianasadzadeh hybridmodelingofinductionhardeningprocesses
AT peterraninger hybridmodelingofinductionhardeningprocesses
AT petriprevedel hybridmodelingofinductionhardeningprocesses
AT wernerecker hybridmodelingofinductionhardeningprocesses
AT manfredmucke hybridmodelingofinductionhardeningprocesses
_version_ 1718405528830345216