A novel approach for in-situ detection of machining defects

Integrating inspection procedures in the machining process contributes to process optimization. The use of in situ measurement allows a better reactivity for corrective actions. However, to be highly efficient, Machining and Inspection Process Planning must reach a high level of integration. It is here essential to focus on the compromise measurement time vs. precision: the time dedicated to inspection must be limited, but not to the detriment of measurement quality. A measurement process for in situ machining defect detection is proposed based on a stereo-DIC. The proposed method allows the direct comparison between images of the machined part and the CAD model by means of a CAD model-based calibration method which links the camera frame to the CAM frame. Therefore, starting from a meshed-model representation of the part, local regions of interest are defined corresponding to the projection of each facet onto the two images. An optimization of each facet configuration is then performed in order to minimize a cross-correlation coefficient, and the obtained facet displacement is used to detect machining defects. The robustness of the method is assessed through an illustration of measurement in the machine-tool environment.