Zusammenfassung: | |
The performance of a process monitoring system is determined by the information available to it. Existing methods for selecting relevant process information (features) work offline with data of faulty processes that is often unavailable or neglect random disturbances. This increases the risk of choosing non-sensitive features. Hence, this paper investigates whether a non-sensitive feature is detectable online in an initial selection of features presumed to be sensitive. A method for quantifying and assessing trends in features online is described. In the validation with turning and drilling processes, a single non-sensitive feature was detected successfully in seven out of eight test cases. © 2020 The Authors.
|
|
Lizenzbestimmungen: | CC BY-NC-ND 4.0 Unported - https://creativecommons.org/licenses/by-nc-nd/4.0/ |
Publikationstyp: | Article |
Publikationsstatus: | publishedVersion |
Erstveröffentlichung: | 2020 |
Schlagwörter (englisch): | Feature selection, Online, Tool condition monitoring, Condition monitoring, Intelligent computing, Manufacture, Process monitoring, Wear of materials, Drilling process, Faulty process, Process information, Process monitoring system, Random disturbances, Sensitive features, Tool condition monitoring, Wear curves, Feature extraction |
Fachliche Zuordnung (DDC): | 600 | Technik, 670 | Industrielle und handwerkliche Fertigung |
Kontrollierte Schlagwörter: | Konferenzschrift |
Anzeige der Dokumente mit ähnlichem Titel, Autor, Urheber und Thema.