Intelligent Prediction of Process Parameters for Bending Forming
Shengle Ren, Yinan Lai*, Guangfei Wu, Juntao Gu, Ye Dai
Identifiers and Pagination:Year: 2011
First Page: 26
Last Page: 31
Publisher Id: TOMEJ-5-26
Article History:Received Date: 26/11/2010
Revision Received Date: 19/11/2010
Acceptance Date: 20/1/2011
Electronic publication date: 29/4/2011
Collection year: 2010
open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: (https://creativecommons.org/licenses/by/4.0/legalcode). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The choice of the process parameters in the conventional tube bending forming is often based on experience and adjusted by repeated bending tests. The method of constantly testing to adjust has seriously affected the production efficiency and increased production costs. In this paper, neural network is used to establish the intelligent prediction model of the pipe forming process parameters. The obtained datum from analytical calculations, numerical simulations and experiments then serve as the training samples and test samples of neural network training. By the trained neural network, the intelligent prediction for the main process parameters including the bending moment and the boost power can be executed. The test results show that the average relative error between the simulation output and target output of bending moment and boost power is less than 2%, and the predicted process parameters, i.e. bending moment and boost power, can be directly used for actual production.