Sheet Metal Forming Springback Prediction Using Image Geometrics (SPIG): A Novel Approach Using Heatmaps and Convolutional Neural Network

Du Chen, Mariluz Penalva Oscoz, Yang Hai, Martin Rebe Ander, Frans Coenen, Anh Nguyen

2025

Abstract

We propose the Springback Prediction Using Image Geometrics (SPIG) approach to predict springback errors in Single Point Incremental Forming (SPIF). We achieved highly accurate predictions by converting local geometric information into heatmaps and employing ResNet based method. Augmenting the dataset twenty-four-fold through various transformations, our ResNet model significantly outperformed LSTM, SVM, and GRU alternatives in terms of the MSE and RMSE values obtained. The best performance result in an R² value of 0.9688, 4.95% improvement over alternative methods. The research demonstrates the potential of ResNet models in predicting springback errors, offering advancements over alternative methods. Future work will focus on further optimisation, advanced data augmentation, and applying the method to other forming processes. Our code and models are available at https://github.com/DarrenChen0923/SPIF.

Paper Citation

in Harvard Style

Chen D., Oscoz M., Hai Y., Ander M., Coenen F. and Nguyen A. (2025). Sheet Metal Forming Springback Prediction Using Image Geometrics (SPIG): A Novel Approach Using Heatmaps and Convolutional Neural Network. In Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN , SciTePress, pages 28-38. DOI: 10.5220/0013673100004000

in Bibtex Style

@conference{kdir25,
author={Du Chen and Mariluz Oscoz and Yang Hai and Martin Ander and Frans Coenen and Anh Nguyen},
title={Sheet Metal Forming Springback Prediction Using Image Geometrics (SPIG): A Novel Approach Using Heatmaps and Convolutional Neural Network},
booktitle={Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2025},
pages={28-38},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013673100004000},
isbn={},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Sheet Metal Forming Springback Prediction Using Image Geometrics (SPIG): A Novel Approach Using Heatmaps and Convolutional Neural Network
SN -
AU - Chen D.
AU - Oscoz M.
AU - Hai Y.
AU - Ander M.
AU - Coenen F.
AU - Nguyen A.
PY - 2025
SP - 28
EP - 38
DO - 10.5220/0013673100004000
PB - SciTePress