Improving additive manufacturing by image processing and robotic milling

This paper describes an improvement of Additive Manufacturing (AM) to process products with complex inner and outer geometries such as turbine blades by using a combination of AM, optical measuring techniques and robotics. One problem of AM is the rough surface caused by the layer-by-layer 3D printing with granular material, so the geometries need to be post-processed with milling techniques. To overcome this problem, we implement an inline quality control management to post-process several manufactured layers by a integrated imaging and robotic techniques, especially while the geometries are still accessible. The produced surfaces are measured by an inline stereo vision system and are compared with the real 3D CAD model data. Detected differences are translated to movements of a robot arm which then follows the contours to smoothen the surfaces with a milling tool. We show our current state on the 3D imaging, on developing the driver for the deployed robot arm and on a 3D simulation using the Robot Operating System (ROS).