A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Artificial neural network modeling to predict the hot deformation behavior of an A356 aluminum alloy
Highlights ► Developing a feed-forward back propagation ANN model to predict the flow stress. ► An ANN with single hidden layer composing of 20 neurons yielded the best results. ► High reliability of the proposed ANN model compared to constitutive equations.
Abstract Prediction of the material flow behavior is an essential step to optimize the design of any forming process. In this context, artificial neural network (ANN) may be used as a reliable modeling method for simulating and predicting the flow behavior of materials under different thermomechanical conditions. In the present study, an ANN model has been established to estimate the high temperature flow behavior of a cast A356 aluminum alloy. A series of isothermal compression tests was conducted in the temperature range of 400–540°C and strain rates of 0.001–0.1s−1. A feed-forward back propagation ANN with single hidden layer composing of 20 neurons was employed to simulate the flow behavior. The neural network has been trained using an in-house database obtained from hot compression tests. Finally, in comparison with a strain-dependent Arrhenius type constitutive equation, the reliability of the proposed ANN model has been evaluated using standard statistical indices. The results indicate that the trained ANN model is a robust tool to predict the high temperature flow behavior of cast A356 aluminum alloy.
Artificial neural network modeling to predict the hot deformation behavior of an A356 aluminum alloy
Highlights ► Developing a feed-forward back propagation ANN model to predict the flow stress. ► An ANN with single hidden layer composing of 20 neurons yielded the best results. ► High reliability of the proposed ANN model compared to constitutive equations.
Abstract Prediction of the material flow behavior is an essential step to optimize the design of any forming process. In this context, artificial neural network (ANN) may be used as a reliable modeling method for simulating and predicting the flow behavior of materials under different thermomechanical conditions. In the present study, an ANN model has been established to estimate the high temperature flow behavior of a cast A356 aluminum alloy. A series of isothermal compression tests was conducted in the temperature range of 400–540°C and strain rates of 0.001–0.1s−1. A feed-forward back propagation ANN with single hidden layer composing of 20 neurons was employed to simulate the flow behavior. The neural network has been trained using an in-house database obtained from hot compression tests. Finally, in comparison with a strain-dependent Arrhenius type constitutive equation, the reliability of the proposed ANN model has been evaluated using standard statistical indices. The results indicate that the trained ANN model is a robust tool to predict the high temperature flow behavior of cast A356 aluminum alloy.
Artificial neural network modeling to predict the hot deformation behavior of an A356 aluminum alloy
Haghdadi, N. (author) / Zarei-Hanzaki, A. (author) / Khalesian, A.R. (author) / Abedi, H.R. (author)
2012-12-31
6 pages
Article (Journal)
Electronic Resource
English
Artificial neural network modeling to predict the hot deformation behavior of an A356 aluminum alloy
| British Library Online Contents | 2013
Severe plastic deformation of rheoforged aluminum alloy A356
| British Library Online Contents | 2012
Severe plastic deformation of rheoforged aluminum alloy A356
| British Library Online Contents | 2012
Microstructure of liquidus casting aluminum alloy A356
| British Library Online Contents | 2001
Artificial neural network modelling to predict hot deformation behaviour of zinc-aluminium alloy
| British Library Online Contents | 2013