A computer vision-based, in-situ springback monitoring technique for bending of large profiles
Academic Article
Overview
Research
Identity
Other
View All
Overview
abstract
Bending processes have various advantages, such as less processing time, lower number of tooling parts, and cost compared to other manufacturing processes. However, one of the disadvantages of a bending process is the inevitable springback problem, which entails geometrical inaccuracy. Many researchers have made attempts to effectively measure springback in-line to control product quality and compensate for variability. While measurement tools and machines are available to measure springback, they might not be able to accommodate large products due to the size limit of measurement devices. Nevertheless, sensor-based monitoring is becoming critical to control product quality and to move towards Industry 4.0. In this paper, an in-situ springback monitoring technique for bending of large-size profiles is proposed to overcome the measurement restrictions for such profiles. A computer vision technique with the circular Hough transform was used to evaluate springback. The marked points on a profile were used to track the deformation of the workpiece. However, a weakness with image processing is to recognize the points from the complex background. Instead of employing global search for the points in an image frame, the marked points were detected by locally setting regions based on forming parameters such as a bending angle and stretching level. Springback was calculated by the change of position of those points. The results of springback monitoring were validated with the physically measured data from experiments. Based on this measurement technique, the feasibility of a computer vision-based springback monitoring in large-size profile bending is discussed in detail.
