Automation of forging processes is important for both safety and efficiency in today's advanced manufacturing operations. This work supports the development of an Intelligent Open Die Forging System which will integrate state-of-the-art modelling techniques, automatic die selection and sequencing, full system dynamic simulation, automatic machine programming and coordination, and sensor-based process control to enable the production of more general and complex workpiece geometries than are achievable using current forging methods. Effective automation of this open die forging system requires the coordination and control of the major system components: press, robot, and furnace. In particular, forces exerted on the robot through its manipulation of the workpiece during forging must be minimized to avoid damage to the manipulator mechanism. In this paper, the application of neural networks for compliance control of the forging robot to minimize these forces is investigated. Effectiveness of the neural network-based compliance control module is evaluated through a full dynamic system simulation, which will later form a central part of the complete Intelligent Forging System. Dynamic simulation of the robot is achieved using an efficient O(N) recursive algorithm, while material flow of the workpiece is modeled with a finite element approach. Simulation and timing results for the complete processing system for a specific open die forging example are presented.
Read full abstract