Transformation of a rolling mill aggregate to a cyber physical production system: from sensor retrofitting to machine learning

Publikationen: Beitrag in FachzeitschriftArtikelForschung(peer-reviewed)

Bibtex - Download

@article{153c517a40264e38bf6895b028c15a5d,
title = "Transformation of a rolling mill aggregate to a cyber physical production system: from sensor retrofitting to machine learning",
abstract = "This paper describes the transformation of a rolling mill aggregate from a stand-alone solution to a fully integrated cyberphysical production system. Within this process, already existing load cells were substituted and additional inductive andmagnetic displacement sensors were applied. After calibration, those were fully integrated into a six-layer digitalizationarchitecture at the Smart Forming Lab at the Chair of Metal Forming (Montanuniversitaet Leoben). Within this framework,two front end human machine interfaces were designed, where the first one serves as a conditionmonitoring system during therolling process. The second user interface visualizes the result of a resilient machine learning algorithm, which was designedusing Python and is not just able to predict and adapt the resulting rolling schedule of a defined metal sheet, but also to learnfrom additional rolling mill schedules carried out. This algorithm was created on the basis of a black box approach, using datafrom more than 1900 milling steps with varying roll gap height, sheet width and friction conditions. As a result, the developedprogram is able to interpolate and extrapolate between these parameters as well as different initial sheet thicknesses, servingas a digital twin for data-based recommendations on schedule changes between different rolling process steps. Furthermore,via the second user interface, it is possible to visualize the influence of this parameters on the result of the milling process.As the whole layer system runs on an internal server at the university, students and other interested parties are able to accessthe visualization and can therefore use the environment to deepen their knowledge within the characteristics and influenceof the sheet metal rolling process as well as data science and especially fundamentals of machine learning. This algorithmalso serves as a basis for further integration of materials science based data for the prediction of the influence of differentmaterials on the rolling result. To do so, the rolled specimens were also analyzed regarding the influence of the plastic strainpath on their mechanical properties, including anisotropy and materials{\textquoteright} strength.",
keywords = "Cyber physical production system, Retrofitting, Digitalization, Digital twin, Machine learning, Smart Forming Lab, Industry 4.0",
author = "Ralph, {Benjamin James} and Marcel Sorger and Karin Hartl and Andreas Schwarz-Gsaxner and Florian Messner and Martin Stockinger",
note = "Publisher Copyright: {\textcopyright} 2021, The Author(s).",
year = "2021",
month = oct,
day = "24",
doi = "10.1007/s10845-021-01856-2",
language = "English",
volume = "33.2022",
pages = "493--518",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Transformation of a rolling mill aggregate to a cyber physical production system: from sensor retrofitting to machine learning

AU - Ralph, Benjamin James

AU - Sorger, Marcel

AU - Hartl, Karin

AU - Schwarz-Gsaxner, Andreas

AU - Messner, Florian

AU - Stockinger, Martin

N1 - Publisher Copyright: © 2021, The Author(s).

PY - 2021/10/24

Y1 - 2021/10/24

N2 - This paper describes the transformation of a rolling mill aggregate from a stand-alone solution to a fully integrated cyberphysical production system. Within this process, already existing load cells were substituted and additional inductive andmagnetic displacement sensors were applied. After calibration, those were fully integrated into a six-layer digitalizationarchitecture at the Smart Forming Lab at the Chair of Metal Forming (Montanuniversitaet Leoben). Within this framework,two front end human machine interfaces were designed, where the first one serves as a conditionmonitoring system during therolling process. The second user interface visualizes the result of a resilient machine learning algorithm, which was designedusing Python and is not just able to predict and adapt the resulting rolling schedule of a defined metal sheet, but also to learnfrom additional rolling mill schedules carried out. This algorithm was created on the basis of a black box approach, using datafrom more than 1900 milling steps with varying roll gap height, sheet width and friction conditions. As a result, the developedprogram is able to interpolate and extrapolate between these parameters as well as different initial sheet thicknesses, servingas a digital twin for data-based recommendations on schedule changes between different rolling process steps. Furthermore,via the second user interface, it is possible to visualize the influence of this parameters on the result of the milling process.As the whole layer system runs on an internal server at the university, students and other interested parties are able to accessthe visualization and can therefore use the environment to deepen their knowledge within the characteristics and influenceof the sheet metal rolling process as well as data science and especially fundamentals of machine learning. This algorithmalso serves as a basis for further integration of materials science based data for the prediction of the influence of differentmaterials on the rolling result. To do so, the rolled specimens were also analyzed regarding the influence of the plastic strainpath on their mechanical properties, including anisotropy and materials’ strength.

AB - This paper describes the transformation of a rolling mill aggregate from a stand-alone solution to a fully integrated cyberphysical production system. Within this process, already existing load cells were substituted and additional inductive andmagnetic displacement sensors were applied. After calibration, those were fully integrated into a six-layer digitalizationarchitecture at the Smart Forming Lab at the Chair of Metal Forming (Montanuniversitaet Leoben). Within this framework,two front end human machine interfaces were designed, where the first one serves as a conditionmonitoring system during therolling process. The second user interface visualizes the result of a resilient machine learning algorithm, which was designedusing Python and is not just able to predict and adapt the resulting rolling schedule of a defined metal sheet, but also to learnfrom additional rolling mill schedules carried out. This algorithm was created on the basis of a black box approach, using datafrom more than 1900 milling steps with varying roll gap height, sheet width and friction conditions. As a result, the developedprogram is able to interpolate and extrapolate between these parameters as well as different initial sheet thicknesses, servingas a digital twin for data-based recommendations on schedule changes between different rolling process steps. Furthermore,via the second user interface, it is possible to visualize the influence of this parameters on the result of the milling process.As the whole layer system runs on an internal server at the university, students and other interested parties are able to accessthe visualization and can therefore use the environment to deepen their knowledge within the characteristics and influenceof the sheet metal rolling process as well as data science and especially fundamentals of machine learning. This algorithmalso serves as a basis for further integration of materials science based data for the prediction of the influence of differentmaterials on the rolling result. To do so, the rolled specimens were also analyzed regarding the influence of the plastic strainpath on their mechanical properties, including anisotropy and materials’ strength.

KW - Cyber physical production system

KW - Retrofitting

KW - Digitalization

KW - Digital twin

KW - Machine learning

KW - Smart Forming Lab

KW - Industry 4.0

UR - http://www.scopus.com/inward/record.url?scp=85116071749&partnerID=8YFLogxK

U2 - 10.1007/s10845-021-01856-2

DO - 10.1007/s10845-021-01856-2

M3 - Article

VL - 33.2022

SP - 493

EP - 518

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 2

ER -