In this study of a 3D rolling process, an incremental updated Lagrangian elasto-plastic finite-element method and a neural network have been integrated to predict the rolling force and the maximum surface error during the rolling process. A series of 27 sets of tools of different geometry were used for simulation of the rolling process, with different variations of die radius, rolling ratio, and matching for the different thicknesses of the products. The results of the rolling force and of the deformation of the surface are then input to a neural network to establish a model for the rolling variables. The results of rolling processing by this developed abductive network can be accurately predicted, once the rolling control parameters are given. This work achieved a satisfactory result based on a demonstration of the simulation, proving that this is a new and feasible approach which can be used for control of the rolling process for materials.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
ID="A1"Correspondance and offprint requests to: Professor J. C. Lin, Depart-mentof Mechanical Design Engineering, National Huwei Institute of Technology, Yunlin 632, Taiwan. E-mail: linrc@sunws.nhit.edu.tw
Rights and permissions
About this article
Cite this article
Lin, J. Prediction of Rolling Force and Deformation in Three-Dimensional Cold Rolling by Using the Finite-Element Method and a Neural Network. Int J Adv Manuf Technol 20, 799–806 (2002). https://doi.org/10.1007/s001700200219
Issue Date:
DOI: https://doi.org/10.1007/s001700200219