Flow curve prediction of cold forging steel by artificial neural network model

A limited number of material models or flow curves are available in commercial finite element softwares at varying temperature and strain rate ranges for plasticity analysis. To obtain more realistic finite element results, flow curves at wide temperature and strain rate ranges are required. For this purpose, a material model for a medium carbon alloy steel material which is used for fastener production was prepared. Firstly, flow curves of the material were obtained at 4 temperatures (20, 100, 200, 400 °C) and 3 strain rates (1, 10, 50 s ^-1). Then, experimental data was used to construct an artificial neural networks model (ANN) for the material. 75% of the experimental data was used to train the model and the rest was employed for validation and verification. ANN model used in flow curve prediction was developed using the scikit-learn library on Python. Temperature, strain rate and strain were employed as input parameters and flow stress as output parameter in ANN model. In order to increase the accuracy of the ANN model, the number of hidden layers and the number of neurons were also optimized by mean squared error approach. As a result of studies, an ANN-based material model that can be used for wide range of temperature and strain rate values were developed based on the experimental data.