Process planning of repairing and grinding for cylindrical parts based on surface defect detection

Abstract To realize the purpose of grinding and repairing surface defects in cylindrical parts, machine vision inspection technology and automatic grinding technology are integrated in this study. These technologies are combined to detect and repair defects in cylindrical parts using an automatic grinding and repair platform. For various defect types, the dynamic threshold extraction method is used, combined with the image difference method in the spatial and frequency domains through defect screening, sensor calibration and sub-pixel edge detection. The defect features are completely extracted and the defect size is determined to guide the polishing and repair platform to repair the surface defects of parts. A grinding path planning algorithm is proposed to solve the problem of the initial installation eccentricity of the workpiece, which can adjust the grinding wheel feed and grinding position. Finally, the experimental tests show that the designed automatic grinding repair system detects all defects without omission, and the average surface roughness of the cylindrical parts Ra is 3.17 μm after repair and polishing, which meets the grinding quality requirements.