• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Artikel
  4. A U-Net Based Approach for Automating Tribological Experiments
 
  • Details
  • Full
Options
2020
Journal Article
Titel

A U-Net Based Approach for Automating Tribological Experiments

Abstract
Tribological experiments (i.e., characterizing the friction and wear behavior of materials) are crucial for determining their potential areas of application. Automating such tests could hence help speed up the development of novel materials and coatings. Here, we utilize convolutional neural networks (CNNs) to automate a common experimental setup whereby an endoscopic camera was used to measure the contact area between a rubber sample and a spherical counterpart. Instead of manually determining the contact area, our approach utilizes a U-Net-like CNN architecture to automate this task, creating a much more efficient and versatile experimental setup. Using a 5× random permutation cross validation as well as additional sanity checks, we show that we approached human-level performance. To ensure a flexible and mobile setup, we implemented the method on an NVIDIA Jetson AGX Xavier development kit where we achieved ~18 frames per second by employing mixed-precision training.
Author(s)
Staar, Benjamin
BIBA-Bremer Institut für Produktion und Logistik GmbH, University of Bremen, University of Bremen, Faculty of Production Engineering
Bayrak, Suleyman
Fraunhofer-Institut für Fertigungstechnik und Angewandte Materialforschung IFAM
Paulkowski, Dominik
Fraunhofer-Institut für Fertigungstechnik und Angewandte Materialforschung IFAM
Freitag, Michael
BIBA-Bremer Institut für Produktion und Logistik GmbH, University of Bremen, University of Bremen, Faculty of Production Engineering
Zeitschrift
Sensors. Online journal
Thumbnail Image
DOI
10.3390/s20226703
Externer Link
Externer Link
Language
English
google-scholar
Fraunhofer-Institut für Fertigungstechnik und Angewandte Materialforschung IFAM
Tags
  • convolutional neural ...

  • tribology

  • Semantic Segmentation...

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022