Bienefeld, Christoph ; Kirchner, Eckhard ; Vogt, Andreas ; Kacmar, Marian (2022)
On the Importance of Temporal Information for Remaining Useful Life Prediction of Rolling Bearings Using a Random Forest Regressor.
In: Lubricants, 2022, 10 (4)
doi: 10.26083/tuprints-00021279
Artikel, Zweitveröffentlichung, Verlagsversion
Kurzbeschreibung (Abstract)
Rolling bearings are frequently subjected to high stresses within modern machines. To prevent bearing failures, the topics of condition monitoring and predictive maintenance have become increasingly relevant. In order to efficiently and reliably maintain rolling bearings in a predictive manner, an estimate of the remaining useful life (RUL) is of great interest. The RUL prediction quality achieved when using machine learning depends not only on the selection of the sensor data used for condition monitoring, but also on its preprocessing. In particular, the execution of so-called feature engineering has a major impact on prediction quality. Therefore, in this paper, various methods of feature engineering are presented based on rolling–bearing endurance tests and recorded structure-borne sound signals. The performance of these methods is evaluated in the context of a regression-based RUL model. Furthermore, the way in which the quality of RUL prediction can be significantly improved is demonstrated, by adding further processed, time-considering features.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Bienefeld, Christoph ; Kirchner, Eckhard ; Vogt, Andreas ; Kacmar, Marian |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | On the Importance of Temporal Information for Remaining Useful Life Prediction of Rolling Bearings Using a Random Forest Regressor |
| Sprache: | Englisch |
| Publikationsjahr: | 2022 |
| Publikationsdatum der Erstveröffentlichung: | 2022 |
| Verlag: | MDPI |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Lubricants |
| Jahrgang/Volume einer Zeitschrift: | 10 |
| (Heft-)Nummer: | 4 |
| Kollation: | 12 Seiten |
| DOI: | 10.26083/tuprints-00021279 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/21279 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichung DeepGreen |
| Kurzbeschreibung (Abstract): | Rolling bearings are frequently subjected to high stresses within modern machines. To prevent bearing failures, the topics of condition monitoring and predictive maintenance have become increasingly relevant. In order to efficiently and reliably maintain rolling bearings in a predictive manner, an estimate of the remaining useful life (RUL) is of great interest. The RUL prediction quality achieved when using machine learning depends not only on the selection of the sensor data used for condition monitoring, but also on its preprocessing. In particular, the execution of so-called feature engineering has a major impact on prediction quality. Therefore, in this paper, various methods of feature engineering are presented based on rolling–bearing endurance tests and recorded structure-borne sound signals. The performance of these methods is evaluated in the context of a regression-based RUL model. Furthermore, the way in which the quality of RUL prediction can be significantly improved is demonstrated, by adding further processed, time-considering features. |
| Freie Schlagworte: | rolling bearings, remaining useful life, machine learning, feature engineering, condition monitoring, structure-borne sound, random forest, regression |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-212793 |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 600 Technik, Medizin, angewandte Wissenschaften > 620 Ingenieurwissenschaften und Maschinenbau |
| Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Fachgebiet Produktentwicklung und Maschinenelemente (pmd) |
| Hinterlegungsdatum: | 06 Mai 2022 11:20 |
| Letzte Änderung: | 09 Mai 2022 06:27 |
| PPN: | |
| Zugehörige Links: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum