Symbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process

Hybrid semiparametric models integrate physics-based (“white-box”, parametric) and data-driven (“black-box”, non-parametric) submodels. Black-box models are often implemented using artificial neural networks (ANNs). In this work, we investigate the fitness of symbolic regression (SR) for black-box m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohammad Zhian Asadzadeh, Hans-Peter Gänser, Manfred Mücke
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Hybrid modelling Symbolic regression Genetic programming Knowledge discovery Metal sheet bending Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/23e3f6d474f24dd5b62bafff29428b69
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:23e3f6d474f24dd5b62bafff29428b69
record_format	dspace
spelling	oai:doaj.org-article:23e3f6d474f24dd5b62bafff29428b692021-12-01T05:06:08ZSymbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process2666-496810.1016/j.apples.2021.100049https://doaj.org/article/23e3f6d474f24dd5b62bafff29428b692021-06-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666496821000157https://doaj.org/toc/2666-4968Hybrid semiparametric models integrate physics-based (“white-box”, parametric) and data-driven (“black-box”, non-parametric) submodels. Black-box models are often implemented using artificial neural networks (ANNs). In this work, we investigate the fitness of symbolic regression (SR) for black-box modelling. The main advantage of this approach is that a trained hybrid model can be expressed in closed form as an algebraic equation. We examine and test the idea on a simple example, namely the v-shape bending of a metal sheet, where an analytical solution for the stamping force is readily available. We explore unconstrained and hybrid symbolic regression modelling to show that hybrid SR models, where the regression tree is partly fixed according to a-priori knowledge, perform much better than purely data-driven SR models based on unconstrained regression trees. Furthermore, the generation of algebraic equations by this method is much more repeatable, which makes the approach applicable to process knowledge discovery.Mohammad Zhian AsadzadehHans-Peter GänserManfred MückeElsevierarticleHybrid modellingSymbolic regressionGenetic programmingKnowledge discoveryMetal sheet bendingEngineering (General). Civil engineering (General)TA1-2040ENApplications in Engineering Science, Vol 6, Iss , Pp 100049- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Hybrid modelling Symbolic regression Genetic programming Knowledge discovery Metal sheet bending Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	Hybrid modelling Symbolic regression Genetic programming Knowledge discovery Metal sheet bending Engineering (General). Civil engineering (General) TA1-2040 Mohammad Zhian Asadzadeh Hans-Peter Gänser Manfred Mücke Symbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process
description	Hybrid semiparametric models integrate physics-based (“white-box”, parametric) and data-driven (“black-box”, non-parametric) submodels. Black-box models are often implemented using artificial neural networks (ANNs). In this work, we investigate the fitness of symbolic regression (SR) for black-box modelling. The main advantage of this approach is that a trained hybrid model can be expressed in closed form as an algebraic equation. We examine and test the idea on a simple example, namely the v-shape bending of a metal sheet, where an analytical solution for the stamping force is readily available. We explore unconstrained and hybrid symbolic regression modelling to show that hybrid SR models, where the regression tree is partly fixed according to a-priori knowledge, perform much better than purely data-driven SR models based on unconstrained regression trees. Furthermore, the generation of algebraic equations by this method is much more repeatable, which makes the approach applicable to process knowledge discovery.
format	article
author	Mohammad Zhian Asadzadeh Hans-Peter Gänser Manfred Mücke
author_facet	Mohammad Zhian Asadzadeh Hans-Peter Gänser Manfred Mücke
author_sort	Mohammad Zhian Asadzadeh
title	Symbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process
title_short	Symbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process
title_full	Symbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process
title_fullStr	Symbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process
title_full_unstemmed	Symbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process
title_sort	symbolic regression based hybrid semiparametric modelling of processes: an example case of a bending process
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/23e3f6d474f24dd5b62bafff29428b69
work_keys_str_mv	AT mohammadzhianasadzadeh symbolicregressionbasedhybridsemiparametricmodellingofprocessesanexamplecaseofabendingprocess AT hanspeterganser symbolicregressionbasedhybridsemiparametricmodellingofprocessesanexamplecaseofabendingprocess AT manfredmucke symbolicregressionbasedhybridsemiparametricmodellingofprocessesanexamplecaseofabendingprocess
_version_	1718405529255018496

Symbolic regression based hybrid semiparametric modelling of processes: An example case of a bending process

Ejemplares similares