Rosemeyer, Jannik ; Neunzig, Christian ; Akbal, Cem ; Metternich, Joachim ; Kuhlenkötter, Bernd (2024)
A maturity model for digital ML tools to be used in manufacturing environments.
doi: 10.26083/tuprints-00026519
Report, Erstveröffentlichung, Verlagsversion
Kurzbeschreibung (Abstract)
Low or no code machine learning platforms, whereof tools such as KNIME, DataRobot or WEKA are among the best-known, have facilitated the implementation of machine learning applications in industrial environments in recent years by transferring programming tasks to an assistance system instead of demanding users to provide the respective skills. Despite the high number of innovations, to the best of the authors’ knowledge, there is no comprehensive classification scheme to assess the autonomy of those tools. Hence, this paper demonstrates a maturity model that classifies the assistance level of existing digital machine learning tools with respect to the requirements of manufacturing environments. It is based on the levels of driving automation and concretized by the so-called CRISP-ML(Q) procedure model. The model allows researchers to rate newly developed tools against existing ones and aims to serve as a baseline for future research. To evaluate the added value to the research landscape, semi-structured interviews with four ML experts were conducted. Finally, five commercial tools were categorized in the model to show its applicability.
| Typ des Eintrags: | Report |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Rosemeyer, Jannik ; Neunzig, Christian ; Akbal, Cem ; Metternich, Joachim ; Kuhlenkötter, Bernd |
| Art des Eintrags: | Erstveröffentlichung |
| Titel: | A maturity model for digital ML tools to be used in manufacturing environments |
| Sprache: | Englisch |
| Publikationsjahr: | 15 Januar 2024 |
| Ort: | Darmstadt |
| Kollation: | 9 ungezählte Seiten |
| DOI: | 10.26083/tuprints-00026519 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/26519 |
| Kurzbeschreibung (Abstract): | Low or no code machine learning platforms, whereof tools such as KNIME, DataRobot or WEKA are among the best-known, have facilitated the implementation of machine learning applications in industrial environments in recent years by transferring programming tasks to an assistance system instead of demanding users to provide the respective skills. Despite the high number of innovations, to the best of the authors’ knowledge, there is no comprehensive classification scheme to assess the autonomy of those tools. Hence, this paper demonstrates a maturity model that classifies the assistance level of existing digital machine learning tools with respect to the requirements of manufacturing environments. It is based on the levels of driving automation and concretized by the so-called CRISP-ML(Q) procedure model. The model allows researchers to rate newly developed tools against existing ones and aims to serve as a baseline for future research. To evaluate the added value to the research landscape, semi-structured interviews with four ML experts were conducted. Finally, five commercial tools were categorized in the model to show its applicability. |
| Freie Schlagworte: | machine learning; digital assistance systems; autonomy levels, levels of driving automation |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-265198 |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau 600 Technik, Medizin, angewandte Wissenschaften > 670 Industrielle und handwerkliche Fertigung |
| Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Institut für Produktionsmanagement und Werkzeugmaschinen (PTW) 16 Fachbereich Maschinenbau > Institut für Produktionsmanagement und Werkzeugmaschinen (PTW) > CiP Center für industrielle Produktivität |
| Hinterlegungsdatum: | 15 Jan 2024 13:08 |
| Letzte Änderung: | 16 Jan 2024 07:24 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum