Design of ram velocity profiles for isothermal forging via nonlinear optimization

The development of realistic material behavior models, accurate nonlinear finite element codes, and computer-controlled presses makes practical the application of control techniques to metal forging. This paper considers the problem of selecting a ram velocity profile to produce a desired microstructure, given a specified die and preform geometry and forging temperature. Two approaches for doing so are successfully applied to a simple but representative problem. The first is based on classical numerical optimization techniques. The second is based on inverse neural networks, and offers potential savings in critical computations. A method for choosing the forging temperature is also presented.