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.

A Comprehensive Study about the Role of Crosslink Density on the Tribological Behavior of DLC Coated Rubber

“…As described in Table 3 and Figure 1, a glassy ball was inserted for the following tests. We have shown that the referenced approach is a reliable measuring technique with an average standard deviation of 3% [42]. The results for the contact area of uncoated samples are shown in Figure 13a.…”