Abstract
Ultrasonic based Non-destructive Testing (NDT) has seen wide applications in recent years. Achieving flexible automation for such testing method is a growing research area. In this regard, enabling automated vision-guided robotic ultrasonic toolpath based NDT inspection is desirable in the manufacturing and re-manufacturing industry. The complexity of this task is augmented by the varying nature of the parts in such industries. This paper introduces an approach developed for structure from motion (SfM) based vision-guided robotic NDT inspection. An automated vision system is developed and integrated into a robotic work-cell that can produce 3D models of challenging objects with sub-millimeter accuracy. These 3D models are then used to generate the toolpath for ultrasonic probe to carry out NDT inspection. We also discuss approaches to perform image acquisition allowing to capture the object view sphere and effects of these approaches on the results of SfM. We show from experimental results that the developed automated vision system can produce high accuracy 3D models of low texture, self-similar and glossy objects, without having to perform training of input data.
How to Cite:
Khan, A. ., Mineo, C. ., Dobie, G. ., Macleod, C. N. & Pierce, S., (2019) “Introducing adaptive vision-guided robotic non-destructive inspection”, Review of Progress in Quantitative Nondestructive Evaluation .
Downloads:
Download PDF