Original scientific paper

Thickness measurement of immersion metal carbon slide based on image segmentation

A. Y. Zheng ; College of Mechanical Engineering, North China University of Science and Technology, Hebei, Tangshan, China *
C. Y. Chang ; College of Mechanical Engineering, North China University of Science and Technology, Hebei, Tangshan, China
W. M. Liu ; College of Mechanical Engineering, North China University of Science and Technology, Hebei, Tangshan, China
S. G. Qiao ; College of Mechanical Engineering, North China University of Science and Technology, Hebei, Tangshan, China

* Corresponding author.

Abstract

The thickness of a metal-immersed carbon slide mounted on a train’s flow shoe was measured by using machine vision and deep learning. A method for measuring the thickness of carbon slide plate based on improved U2-Net is proposed. Aiming at the problem that the edge feature extraction is not obvious, a new feature extraction module is designed. Efficient Channel Attention (ECA) mechanism and pool residual structure are used to make the network more suitable for metal-immersed carbon slide image segmentation. The experimental results show that the improved U2-Net network accuracy reaches 99,4 %, and the average absolute error is only 0,4 %. The thickness measurement accuracy of metallized carbon slide using improved U2-Net network reaches 0,5 mm.

Keywords

rail; immersion metal carbon slide; image segmentation; U²-Net

Hrčak ID:

315699

URI

https://hrcak.srce.hr/315699

Publication date:

1.7.2024.

Visits: 622 *