Detection of surface defects and dimensions of graphite seal ring based on machine vision

Abstract

In order to solve the problems of low efficiency of surface defects and size detection of graphite seal ring, and reduce influence of human factors, a method of surface defects and size detection of graphite seal ring based on machine vision was proposed. On the one hand, image preprocessing and canny algorithm were used to extract the edge of the graphite seal ring, and then the least square circular fitting method was used to complete the edge fitting, so as to calculate the inner and outer diameters of the seal ring. On the other hand, the surface defect of seal ring was identified by template matching algorithm. The experimental results show that this method can detect the defects in the graphite seal ring, the defect recognition rate is 85.7%. The precision of dimension measurement can reach 0.06mm, which meets the requirement of measurement precision.