3D Vision-Guided the metal parts loading
Project background: In this terminal automobile factory, the Dexforce intelligent 3D vision system was introduced to complete the automatic loading and unloading operation of nut welding and other workpieces at the grasping station of its welding workshop, and realized the flexible switching and grasping of multiple models. The construction cost and utilization rate of the station have been greatly optimized, and it has been stably put into production, thereby reducing the time and labor force of manual operation, shortening the production cycle and improving production efficiency.
- Project advantages:
- Training deep learning model based on Dexforce self-developed DexVerse™ embodies intelligent engine can identify bearings of various sizes and shapes, without repeated model training, and has strong applicability;
- Support the configuration of multiple product models at the same time, according to the robot signal switch operation; There is no need to stop production to collect annotated data, and the deep learning model training of the new workpiece can be completed in 8 hours, and the production can be quickly launched.
- Zero code, zero programming, direct adjustment of parameters can achieve visual positioning, the fastest 5 minutes to complete visual configuration, 20 minutes to cooperate with the robot to grasp debugging.
- Application results:
The traditional feeding method often relies on manual operation, which is not only inefficient, but also easy to be affected by human factors, resulting in unstable product quality. The application of 3D vision technology can realize the accurate identification and positioning of the inertial ring, greatly improve production efficiency and product quality, and reduce production costs and losses.
