The System for Fatigue Crack Propagation Detection Based on Machine Vision

Abstract

This paper introduces a machine vision-based system design that is a promising solution for such a problem like a technology detecting the fatigue crack propagation. Fatigue cracks propagate because of alternating mechanical stresses. In technical components they usually start on surfaces at points of stress concentration. The system uses USB 3.0 camera with the Sony IMX264 CMOS sensor delivers 35 frames per second at 5.0 MP resolution in cooperation of PC based NI VisionBuilder software. Various segmentation methods have been explored to extract region of interest in acquired images and compared based on the capability of segmentation in real-time. The paper presents results of algorithm outputs taken on fatigue crack propagation samples and implementation of a machine vision system.