Integrating Virtual Twin and Deep Neural Networks for Efficient and Energy-Aware Robotic Deburring in Industry 4.0

In the context of modern manufacturing, digitalization, real-time monitoring, and simulation are integral components that contribute to efficiency and energy awareness. This research paper aims to present a comprehensive framework of an intelligent robotic deburring system that incorporates elements from Industry 4.0 and virtual twin technology. The framework includes process planning, robot programming, and the creation of a virtual twin within a robotic deburring work cell. A key aspect of this framework is the utilization of deep neural networks for accurate burr identification, coupled with human-in-the-loop process monitoring. The integration of a virtual twin enables real-time process planning and enhances adaptability and flexibility to address dynamic changes during operation. A practical evaluation of the framework demonstrates its effectiveness, with the robotics deburring process achieving a significant 31% energy saving.