KIT | KIT-Bibliothek | Impressum | Datenschutz

Probabilistic Estimation of Parameters for Lubrication Application with Neural Networks

Paschek, Stefan ; Förster, Frederic; Kipfmüller, Martin; Heizmann, Michael 1
1 Institut für Industrielle Informationstechnik (IIIT), Karlsruher Institut für Technologie (KIT)

Abstract:

This paper investigates the use of neural networks to predict characteristic parameters of
the grease application process pressure curve. A combination of two feed-forward neural networks
was used to estimate both the value and the standard deviation of selected features. Several neuron
configurations were tested and evaluated in their capability to make a probabilistic estimation of
the lubricant’s parameters. The value network was trained with a dataset containing the full set of
features and with a dataset containing its average values. As expected, the full network was able
to predict noisy features well, while the average network made smoother predictions. This is also
represented by the networks’ R2 values which are 0.781 for the full network and 0.737 for the mean
network. Several further neuron configurations were tested to find the smallest possible configuration.
The analysis showed that three or more neurons deliver the best fit over all features, while one or
two neurons are not sufficient for prediction. The results showed that the grease application process
pressure curve via pressure valves can be estimated by using neural networks.

Zugehörige Institution(en) am KIT Institut für Industrielle Informationstechnik (IIIT)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2024
Sprache Englisch
Identifikator ISSN: 2673-4117
KITopen-ID: 1000178504
Erschienen in Eng
Verlag MDPI AG (MDPI AG)
Band 5
Heft 4
Seiten 2428 – 2440
Vorab online veröffentlicht am 30.09.2024
Nachgewiesen in Dimensions
Scopus

Verlagsausgabe §
DOI: 10.5445/IR/1000178504
Veröffentlicht am 30.01.2025
Seitenaufrufe: 15
seit 30.01.2025
Downloads: 14
seit 31.01.2025
Cover der Publikation
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page