Carbon fiber and fiberglass composite panels are commonly used in the aerospace and automotive industries. During the manufacturing process, composite panels undergo surface treatment processes such as priming and coating. For coating layers to adhere strongly to the surface, the part surface must be free of any contamination such as grease. Detection and removal of contamination is an important step in the manufacturing of composite panels, particularly in the aerospace industry. This thesis develops a novel vision-based framework to enable fully automated inspection and robotic abrasion of free-form composite panels. The first aim of the thesis is to automatically locate arbitrarily placed composite panels within the robot workplace. The proposed method employs iterative closest point (ICP) registration technique for locating the part in the robot cell. An additional module based on vision-based error correction is developed in the thesis for improving the accuracy of part localization. The proposed part localization technique eliminates the need for manual calibration of part placement in each robot cycle.
The ASTM-F22 water-break test is widely used for detecting hydrophobic contamination on a surface. As the second aim in this thesis, vision-based algorithms are developed to allow for the automated detection (inspection) of hydrophobic contamination during the water-break test. The developed vision-based algorithms can successfully detect the layer of hydrophobic contamination on the free-form panel. The third aim of this thesis is to automatically generate robotic abrasion tool paths to remove detected contamination. In the proposed framework, the panel surface is divided into multiple grids. The point clouds of each grid are first used to reconstruct continuous parametric B-spline surfaces. B-spline surfaces are then used to make an abrasion tool path for each grid. The developed vision-based inspection algorithm determines which grids contain contamination and therefore must be abraded. To conclude, the overarching goal of this thesis is to develop a fully automated vision-based framework for the detection and removal (robotic abrasion) of contamination on free-form composite panels. The developed techniques have been successfully implemented and verified on a Kuka KR6 industrial robot equipped with 2D and 3D vision cameras.