Development of an Inspection System for Defect Detection in Pressed Parts Using Laser Scanned Data

In past few decades several researches have been conducted in the field of 3D parts inspection system. The accuracy level of manufactured parts has been improved remarkably within this period. The use of laser sensors in 3D part measurement process has introduced a significant improvement in data acquisition process regarding time and cost. However for quality control process, due to lack of appropriate technique to process and inspect the scanned point cloud data, high accuracy level could not have been achieved so far. Therefore the industries are still compelled to use same traditional coordinate measuring machines (CMMs) despite of being very slow. In this paper, a robust inspecting technique to detect defects in 3D pressed parts has been proposed. Point cloud data are segmented for the extraction of features. These segmented features are used for shape matching during feature based registration process to localize them with the respective CAD model and bring into same coordinate frame. A modified Iterative closest point (ICP) algorithm is proposed for the registration process. After the registration has been completed these scanned model and CAD model are compared to find defects in the manufactured parts.