0
research-article

Hierarchical metamodeling of the air bending process

[+] Author and Article Information
Matteo Strano

Dipartimento di Meccanica, Politecnico di Milano, Via La Masa 1, 20156 Milan (Italy)
matteo.strano@polimi.it

Quirico Semeraro

Dipartimento di Meccanica, Politecnico di Milano, Via La Masa 1, 20156 Milan (Italy)
quirico.semeraro@polimi.it

Lorenzo Iorio

MUSP Lab, Str. della Torre della Razza, 29122 Piacenza (Italy)
lorenzo.iorio@polimi.it

Roberto Sofia

AMADA ENGINEERING EUROPE, Via Giovanni Agnelli, 15 – 10026 Santena (TO, Italy)
roberto.sofia@amada-engineering.eu

1Corresponding author.

ASME doi:10.1115/1.4040025 History: Received June 14, 2017; Revised April 11, 2018

Abstract

Despite the tremendous effort of researchers and manufacturing engineers in improving the predictability of the air bending process, there is still a strong need for comprehensive and dependable prediction models. Currently available modeling approaches all present some relevant limitations in practical applications. In this paper, we propose a new method, which represents an improvement over all existing modeling and prediction techniques. The proposed method can be used for accurate prediction of the main response variables of the air bending process: the angle after springback and the bend deduction. The metamodeling method is based on the hierarchical fusion of different kinds of data: the deterministic low-fidelity response of numerical FEM simulations and the stochastic high fidelity response of experimental tests. The metamodel has been built over a very large database, unprecedented in the scientific literature on air bending, made of more than 500 numerical simulations and nearly 300 experimental tests. The fusion is achieved first by interpolating the FEM simulations with a kriging predictor; then, the hierarchical metamodel is built as a linear regression model of the experimental data, using the kriging predictor among the regressors. The accuracy of the method has been proved using a variant of the leave-one-out cross validation technique. The quality of the prediction yielded by the proposed method significantly over-performs the current prediction of the press brake on-line numerical control.

Copyright (c) 2018 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In