A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations

2020/09/30 by Haosu Zhou, Zhou, Haosu, Qingfeng Xu +3 · 4 citations
Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Artificial neural network #Computer science #Data mining #Engineering #Finite element method #Generalizability theory #Machine learning #Mathematics #Metal Forming Simulation Techniques #Non-Destructive Testing Techniques #Perceptron #Robustness (evolution) #Statistics #Surrogate model #Topology Optimization in Engineering #cs.CV #eess.IV

paper · pdf · doi:10.48550/arxiv.2010.03370

published in arXiv (Cornell University) (Cornell University) · 16 pages, 14 figures

arxiv created 2020/09/30 · openalex publication_date 2020/09/30 · arxiv updated 2020/10/08 · openalex created_date 2020/10/15 · openalex updated_date 2026/07/28

Abstract

In the design optimization of metal forming, it is increasingly significant to use surrogate models to analyse the finite element analysis (FEA) simulations. However, traditional surrogate models using scalar based machine learning methods (SBMLMs) fall in short of accuracy and generalizability. This is because SBMLMs fail to harness the location information of the simulations. To overcome these shortcomings, image based machine learning methods (IBMLMs) are leveraged in this paper. The underlying theory of location information, which supports the advantages of IBMLM, is qualitatively interpreted. Based on this theory, a Res-SE-U-Net IBMLM surrogate model is developed and compared with a multi-layer perceptron (MLP) as a referencing SBMLM surrogate model. It is demonstrated that the IBMLM model is advantageous over the MLP SBMLM model in accuracy, generalizability, robustness, and informativeness. This paper presents a promising methodology of leveraging IBMLMs in surrogate models to make maximum use of info from FEA results. Future prospective studies that inspired by this paper are also discussed.

Citations

• ImageNet classification with deep convolutional neural networks
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows

Cited by

• Adaptive Fusion Graph Network for 3D Strain Field Prediction in Solid Rocket Motor Grains
• Recurrent U-Net-Based Graph Neural Network (RUGNN) for Accurate Deformation Predictions in Sheet Material Forming
• Rapid feasibility assessment of components formed through hot stamping: A deep learning approach
• SuperMeshing: A New Deep Learning Architecture for Increasing the Mesh Density of Metal Forming Stress Field with Attention Mechanism and Perceptual Features

Related

• Image-based Artificial Intelligence empowered surrogate model and shape morpher for real-time blank shape optimisation in the hot stamping process
• Surrogate Modelling for Injection Molding Processes using Machine Learning
• Rapid feasibility assessment of components formed through hot stamping: A deep learning approach
• SuperMeshing: A New Deep Learning Architecture for Increasing the Mesh Density of Metal Forming Stress Field with Attention Mechanism and Perceptual Features
• Application of machine learning in predicting quality parameters in Metal Material Extrusion (MEX/M)