Article: Improving geometric accuracy in incremental sheet metal forming using convolutional neural networks Journal: International Journal of Mechatronics and Manufacturing Systems (IJMMS) 2023 Vol.16 No.2/3 pp.201 - 224 Abstract: Single point incremental forming (SPIF) is a flexible sheet metal forming process. Unlike sheet metal stamping, SPIF does away with costly forming dies but instead uses a tool to incrementally form the sheet into the desired geometry. However, a key weakness of SPIF is its poor geometric accuracy, which is largely caused by material spring-back throughout the forming process. This paper presents a framework which minimises SPIF geometric error through optimisation of the forming toolpath. The approach utilises a trained convolutional neural network (CNN) to model the forming process, which provides greater flexibility and compatibility with a wide range of geometry. A geometric compensation algorithm was developed to compensate for the predicted spring-back. Experimental validation of the proposed framework demonstrated consistent accuracy improvements in both trained and untrained geometry. This paper highlights the viability of using CNNs in improving SPIF accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: Improving geometric accuracy in incremental sheet metal forming using convolutional neural networks

Authors: Darren Wei Wen Low; Chaudhari Akshay; Suwat Jirathearanat; A. Senthil Kumar

Addresses: Department of Mechanical Engineering, National University of Singapore, 9 Engineering Drive 1, Block EA, Singapore, 117576, Singapore ' Department of Mechanical Engineering, National University of Singapore, 9 Engineering Drive 1, Block EA, Singapore, 117576, Singapore ' Singapore Institute of Manufacturing Technology (SIMTech), Agency for Science, Technology and Research (A*STAR), 73 Nanyang Drive, 637662, Singapore ' Department of Mechanical Engineering, National University of Singapore, 9 Engineering Drive 1, Block EA, Singapore, 117576, Singapore

Abstract: Single point incremental forming (SPIF) is a flexible sheet metal forming process. Unlike sheet metal stamping, SPIF does away with costly forming dies but instead uses a tool to incrementally form the sheet into the desired geometry. However, a key weakness of SPIF is its poor geometric accuracy, which is largely caused by material spring-back throughout the forming process. This paper presents a framework which minimises SPIF geometric error through optimisation of the forming toolpath. The approach utilises a trained convolutional neural network (CNN) to model the forming process, which provides greater flexibility and compatibility with a wide range of geometry. A geometric compensation algorithm was developed to compensate for the predicted spring-back. Experimental validation of the proposed framework demonstrated consistent accuracy improvements in both trained and untrained geometry. This paper highlights the viability of using CNNs in improving SPIF accuracy.

Keywords: incremental sheet forming; CNN; convolutional neural networks; geometric error; forming accuracy.

DOI: 10.1504/IJMMS.2023.133393

International Journal of Mechatronics and Manufacturing Systems, 2023 Vol.16 No.2/3, pp.201 - 224

Received: 28 Oct 2022
Accepted: 15 Mar 2023
Published online: 14 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Improving geometric accuracy in incremental sheet metal forming using convolutional neural networks

Keep up-to-date