Optimum creep feed grinding process conditions for Rene 80 supper alloy using neural network

Creep feed grinding is widely used in manufacturing supperalloy materials. These materials are usually used in aircrafts, gas turbines, rocket engines, petrochemical equipments and other high temperature applications. The objective of this paper is to model and predict the grinding forces of the creep feed grinding of these materials using the neural network. This model is then used to select the working conditions (such as depth of cut, the wheel speed and workpiece speeds) to prevent the surface burning and to maximize the material removal rate. The results show that the combined neural network and an optimization system are capable of generating optimal process parameters. The outcomes of the paper are now used to apply the optimal working conditions for grinding the turbine blades.