Digitization Workflow for Data Mining in Production Technology applied to a Feed Axis of a CNC Milling Machine

Publikation: Beitrag in FachzeitschriftKonferenzartikelBeigetragenBegutachtung

Abstract

Condition monitoring and predictive maintenance applications receive ongoing scientific attention in production technology. Larger companies, especially machine and component manufacturers, already offer related products. Small and medium-sized enterprises (SMEs) in particular show interest in developing and offering solutions in this market themselves to gain economic advantages, to improve resource utilization of their machines or to be able to offer these advantages to their own customers. In the development process, however, they often encounter problems already in the digitization of the machines. The first hurdle is to obtain an analysis-capable data set. This is due to the fact that common and established general data mining development process models, such as CRISP-DM, do not focus on production technology, causing difficulties for engineers during deployment. A problem with existing process models is the limited practicality in the engineering domain due to restricted adaptability. In a previous paper, a guideline for engineers for data mining suitable digitization of production machines was developed in order to solve these problems. The related results were provided in the context of a project for condition monitoring of mixing machines. In this paper, the proposed method is applied to components of a 5-axis CNC milling machine in three different monitoring use cases. A complete workflow is presented, including effect analysis, sensor selection, formulation of predictive scenarios, data preparation, training of machine learning algorithms and vizualization. Data and documentation are provided alongside this publication.

Details

OriginalspracheEnglisch
Seiten (von - bis)169-182
Seitenumfang14
FachzeitschriftProcedia Computer Science
Jahrgang232
PublikationsstatusVeröffentlicht - 2024
Peer-Review-StatusJa

Konferenz

Titel5th International Conference on Industry 4.0 and Smart Manufacturing
KurztitelISM 2023
Veranstaltungsnummer5
Dauer22 - 24 November 2023
Webseite
BekanntheitsgradInternationale Veranstaltung
OrtIscte - University Institute of Lisbon
StadtLisbon
LandPortugal

Externe IDs

ORCID /0000-0001-7540-4235/work/160952786

Schlagworte

ASJC Scopus Sachgebiete

Schlagwörter

  • Anomaly Detection, Classification, Condition Monitoring, Data Mining, Digitization, Machine Learning, Production Engineering, Production Technology, UAI, Usable Artificial Intelligence