Next Article in Journal
Experimental Comparison of IR-UWB Radar and FMCW Radar for Vital Signs
Previous Article in Journal
SodSAR: A Tower-Based 1–10 GHz SAR System for Snow, Soil and Vegetation Studies
Letter

A U-Net Based Approach for Automating Tribological Experiments

1
BIBA—Bremer Institut für Produktion und Logistik GmbH, University of Bremen, Hochschulring 20, 28359 Bremen, Germany
2
University of Bremen, Faculty of Production Engineering, Badgasteiner Straße 1, 28359 Bremen, Germany
3
Fraunhofer Institute for Manufacturing Technology and Advanced Materials IFAM, Wiener Strasse 12, 28359 Bremen, Germany
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(22), 6703; https://doi.org/10.3390/s20226703
Received: 30 September 2020 / Revised: 13 November 2020 / Accepted: 18 November 2020 / Published: 23 November 2020
(This article belongs to the Section Intelligent Sensors)
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. View Full-Text
Keywords: convolutional neural network; tribology; semantic segmentation convolutional neural network; tribology; semantic segmentation
Show Figures

Figure 1

MDPI and ACS Style

Staar, B.; Bayrak, S.; Paulkowski, D.; Freitag, M. A U-Net Based Approach for Automating Tribological Experiments. Sensors 2020, 20, 6703. https://doi.org/10.3390/s20226703

AMA Style

Staar B, Bayrak S, Paulkowski D, Freitag M. A U-Net Based Approach for Automating Tribological Experiments. Sensors. 2020; 20(22):6703. https://doi.org/10.3390/s20226703

Chicago/Turabian Style

Staar, Benjamin, Suleyman Bayrak, Dominik Paulkowski, and Michael Freitag. 2020. "A U-Net Based Approach for Automating Tribological Experiments" Sensors 20, no. 22: 6703. https://doi.org/10.3390/s20226703

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop