Skip to Main Content
Skip Nav Destination
ASME Press Select Proceedings
Intelligent Engineering Systems through Artificial Neural Networks, Volume 20
Cihan H. Dagli
Cihan H. Dagli
Search for other works by this author on:
No. of Pages:
ASME Press
Publication date:

Cold rolling is used to eliminate void defects in cast materials, thus improving the material performance during service. A comprehensive procedure is developed using finite element analysis and neural network to predict the degree of void closure. A three-dimensional nonlinear dynamic finite element model is used to study the mechanism of void deformation. Experiments were conducted and the results are compared to finite element predictions to validate the model. As finite element simulation is time-consuming, a back-propagation neural network model is developed to predict void closure behavior. Based on correlation analysis, the reduction in sheet thickness, the dimension of the void and the size of the rollers are selected as the inputs for the neural network. The neural network model is trained based on results obtained from finite element analysis for various simulation cases. The trained neural network model provides an accurate and efficient procedure to predict void closure behavior in cold rolling.

Finite Elment Modeling
Neural Network Modeling
Results and Discussion
This content is only available via PDF.
You do not currently have access to this chapter.
Close Modal

or Create an Account

Close Modal
Close Modal