StressGAN: A Generative Deep Learning Model for 2D Stress Distribution Prediction

Abstract

Using deep learning to analyze mechanical stress distributions has been gaining interest with the demand for fast stress analysis methods. Deep learning approaches have achieved excellent outcomes when utilized to speed up stress computation and learn the physics without prior knowledge of underlying equations. However, most studies restrict the variation of geometry or boundary conditions, making these methods difficult to be generalized to unseen configurations. We propose a conditional generative adversarial network (cGAN) model for predicting 2D von Mises stress distributions in solid structures. The cGAN learns to generate stress distributions conditioned by geometries, load, and boundary conditions through a two-player minimax game between two neural networks with no prior knowledge. By evaluating the generative network on two stress distribution datasets under multiple metrics, we demonstrate that our model can predict more accurate high-resolution stress distributions than a baseline convolutional neural network model, given various and complex cases of geometry, load and boundary conditions.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Striving for Simplicity: The All Convolutional Net
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Unsupervised Image-to-Image Translation Networks
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Data-driven prediction of unsteady flow fields over a circular cylinder using deep learning
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks
• Filmy Cloud Removal on Satellite Imagery with Multispectral Conditional Generative Adversarial Nets
• CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
• Deep Learning the Physics of Transport Phenomena
• Difference-Based Deep Learning Framework for Stress Predictions in Heterogeneous Media
• Robust Conditional Generative Adversarial Networks
• Deep Learning Phase Segregation

Cited by in corpus (9)

• Stress field prediction in fiber-reinforced composite materials using a deep learning approach
• Towards Reusable Surrogate Models: Graph-Based Transfer Learning on Trusses
• Variational operator learning: A unified paradigm marrying training neural operators and solving partial differential equations
• A graph-based probabilistic geometric deep learning framework with online enforcement of physical constraints to predict the criticality of defects in porous materials
• Scalar Field Prediction on Meshes Using Interpolated Multi-Resolution Convolutional Neural Networks
• A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations
• A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features
• Rapid feasibility assessment of components formed through hot stamping: A deep learning approach
• SuperMeshing: A Novel Method for Boosting the Mesh Density in Numerical Computation within 2D Domain