Multi-axis machines are growing rapidly their precision and complexity with the increasing importance of machine intelligence, automation, optimization and safety. It is necessary to identify collision risks and avoid them in manufacturing otherwise production stops may cost a huge amount to the manufacturing company. This study has focused on safe trajectory generation for CNC machines especially focusing on high risked non-functional trajectories. These machines should be able to see any unwilling situation (i.e. collisions) in their vicinity and must be able to detect and react automatically in real-time for safe tool movements. Currently CAM software and some multi-axis machines are able to detect collisions but they do not have any solution to avoid such collisions automatically. The main objective is to make multi-axis machine vision system effective enough that it can see all its activities regarding collisions and can react or command automatically online as well as off-line for real and virtual productions. In presence of obstacles during manufacturing, the proposed approach will provide decisions regarding trajectory correction and improvement automatically. The proposed vision concept is able to take into account the evolution of the scene i.e. the aspects of changes to the obstacle like shape, size or presence during production. The application presented in this paper is for 2D traversal safe online trajectories generation in virtual simulated dynamic environment, which will be adapted to the real-time real machining scenarios at shop-floor by integrating it with STEP-NC technology in future.

This content is only available via PDF.
You do not currently have access to this content.