A Characterization of Hot Flow Behaviors of Invar36 Alloy by an Artificial Neural Network with Back-Propagation Algorithm

In order to investigate the hot deformation behaviors of Invar36 alloy, isothermal compressive tests were conducted on a Gleeble 1500 thermo-mechanical simulator at temperatures 873, 948, 1023, 1098 and 1173 K strain rates 0.01, 0.1, 1 10 s−1. The effects strain, temperature rate flow stress analyzed, dynamic recrystallization type softening characteristic with unimodal behavior is determined. An artificial neural network based back-propagation algorithm was proposed handle complex characteristics. ANN model evaluated in terms correlation coefficient average absolute relative error. A comparative study performed constitutive equation by regression method for alloy. Finally, applied finite element simulation, an experimental trial forming V-shaped part demonstrate precision simulation predicted data model. results have sufficiently showed that well-trained BP able deal alloy has great application potentiality deformation.