Enhancing the Quality of Manual Spot Welding through Augmented Reality Assisted Guidance

摘要

Manual spot welding loses the comparison with automated spot welding, not because of a higher execution time, but due to an inferior quality of welded points, mostly a low repeatability. It is not a human fault. Human welder is compelled to operate without having at disposal the knowledge of significant process features that are known by the robot: exact position of the welding spot, electric parameters to be adopted for every specific point, quality of the welded spot and, based on it, possible need for repetition of a defective weld. The research shows that, using an augmented reality device, it is possible to display this very data to the human operator, in order to enhance the manual process execution. The adopted device is a tablet mounted on the welding gun. It displays the working area seen by the built-in camera. The image is augmented by the superposition of computer generated images of the welding spots and their properties. The state of the spot (welded or not) and its execution quality (good or defective weld) is transmitted by some graphic features, like point color, size and way of blinking. The paper describes the algorithms used in the development of the program for this application, focusing on the problem of real time localization of the welding gun position. The augmented reality application was actually installed on a experimental station by a welding gun manufacturer and the results of the tests are presented and discussed.