In this paper neural networks are utilized to represent the rheological behaviour of nickel-base superalloys under hot forging conditions. A feedforward back-propagation neural network has been trained and tested on rheological data, obtained from hot compression experiments, performed under single- and multi-step deformation conditions, both at constant and varying strain rates. The good agreement between experimental and calculated flow curves shows that a properly trained neural network can be successfully employed in representing a material response to hot forging cycles.
BarianiP. F.BruschiS.Dal NegroT.The need for new testing procedures in multi-step hot deformation studies. In Proceedings of the 6th International Conference on Technology of Plasticity (ICTP), Nuremberg, Germany, 1999.
2.
DeanT. A.HuZ. M.The increasing requirements of empirical data for use in metalforming process simulation packages. In Proceedings of the 6th International Conference on Technology of Plasticity (ICTP), Nuremberg, Germany, 1999.
3.
BarianiP. F.Dal NegroT.Material response to continuously varying rate of straining during hot forging operations. Ann. CIRP, 1999, 48(1), 183–186.
4.
BarianiP. F.BruschiS.Dal NegroT.Sensitivity of the flow stress to varying strain rate conditions in hot forging of Nimonic 80A. In Proceedings of V Manufacturing Italian Association Conference (AITEM), Bari, Italy, 2001.
5.
KongL. X.HodgsonP. D.CollinsonD. C.Extrapolation prediction for the hot strength of austenitic steels with a combined constitutive and ANN model. J. Mater. Processing Technol., 2000, 102, 84–89.
6.
QiungbinL.ZhongJ.MabaoL.ShichunW.Acquiring the constitutive relationship for a thermal visco-plastic material using an artificial neural network. J. Mater. Processing Technol., 1996, 62, 206–210.
7.
RaoK. P.PrasadY. K. D. V.Neural network approach to flow stress evaluation in hot deformation. J. Mater. Processing Technol., 1995, 53, 552–566.
8.
BarianiP. F.BruschiS.Dal NegroT.The use of neural networks to represent rheological data in multi-step hot forging. In Proceedings of the 2nd International Conference on Intelligent Computation in Mechanical Engineering (ICME), Capri, Italy, 2000.
9.
BarianiP. F.BertiG.BruschiS.Dal NegroT.Application of neural networks to represent the rheological behaviour of nickel-base superalloys under varying hot deformation conditions. In Proceedings of the 4th European Scientific Association for Material Forming Conference (ESAFORM), Liege, Belgium, 2001.
10.
LippmannR. P.An introduction to computing with neural nets. IEEE Acoust., Speech and Signal Processing Mag., 1987, 1, 4–21.
