A framework for measurement and analysis of surface defects on sphere parts

This paper presents a measurement and analysis system of surface defects on sphere parts. The purpose of the system is a requirement to assure high quality of parts. In the system, the developed surface defect detection (SDD) system using laser and CCD camera with improved accuracy, flexibility and advanced measuring efficiency advantages, and the surface defect analysis are used to identify defects. The proposed surface defect analysis approach first uses an empirical mode decomposition (EMD)-based extracting algorithm to perform initial locating of surface defects and extract the possible defects. Then, the approach applies Canny edge algorithm to narrow down the search space of these defects, and backpropagation (BP) neural network to classify five defects with complex shapes, specifically, bulge, dent, abrasion, oxidation, and exfoliation defects. Once these defects are classified, 3D surface morphology of the extracted bulge and dent defects can be obtained and evaluated. Therefore, the system can work well for surface defects on sphere parts mentioned. Experimental results on measurement and analysis of a variety of the surface defects on sphere parts are reported to show the performance of the system.