Tool path planning of consecutive free-form sheet metal stamping with deep learning

File Description SizeFormat 
2022 JMPT - Liu et al Tool path planning with deep learning-accepted copy.pdfFile embargoed for 24 months after publication date 2.19 MBAdobe PDF    Request a copy
Title: Tool path planning of consecutive free-form sheet metal stamping with deep learning
Authors: Liu, S
Xia, Y
Liu, Y
Shi, Z
Yu, H
Li, Z
Lin, J
Item Type: Journal Article
Abstract: Sheet metal forming technologies, such as stamping and deep drawing, have been widely used in automotive, rail and aerospace industries for lightweight metal component manufacture. It requires specially customised presses and dies, which are very costly, particularly for low volume production of extra-large engineering panel components. In this paper, a novel recursive tool path prediction framework, impregnated with a deep learning model, is developed and instantiated for the forming sequence planning of a consecutive rubber-tool forming process. The deep learning model recursively predicts the forming parameters, namely punch location and punch stroke, for each deformation step, which yields the optimal tool path. Three series of deep learning models, namely single feature extractor, cascaded networks (including state-of-the-art deep networks) and long short-term memory (LSTM) models are implemented and trained with two datasets with different amounts of data but the same data diversity. The learning results show that the single LSTM model trained with the larger dataset has the most superior learning capability and generalisation among all models investigated. The promising results from the LSTM indicate the potential of extending the proposed recursive tool path prediction framework to the tool path planning of more complex sheet metal components. The analysis on different deep networks provides instructive references for model selection and model architecture design for sheet metal forming problems involving tool path design
Issue Date: May-2022
Date of Acceptance: 13-Feb-2022
URI: http://hdl.handle.net/10044/1/95899
DOI: 10.1016/j.jmatprotec.2022.117530
ISSN: 0924-0136
Publisher: Elsevier BV
Start Page: 117530
End Page: 117530
Journal / Book Title: Journal of Materials Processing Technology
Volume: 303
Copyright Statement: © 2022 Elsevier B.V. All rights reserved
Sponsor/Funder: AVIC Manufacturing Technology Institute
Funder's Grant Number: N/A
Keywords: Science & Technology
Technology
Engineering, Industrial
Engineering, Manufacturing
Materials Science, Multidisciplinary
Engineering
Materials Science
Deep learning
Convolutional neural network (CNN)
Cascaded network
Long short-term memory (LSTM)
Intelligent manufacturing
Sheet metal tool path planning
0910 Manufacturing Engineering
0912 Materials Engineering
0913 Mechanical Engineering
Materials
Publication Status: Published online
Embargo Date: Embargoed for 24 months after publication date
Article Number: 117530
Online Publication Date: 2022-02-17
Appears in Collections:Mechanical Engineering