A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features
Preprint
Abstract
The purpose of this work is to train an Encoder-Decoder Convolutional Neural Networks (CNN) to automatically add local fine-scale stress corrections to coarse stress predictions around unresolved microscale features. We investigate to what extent such a framework provides reliable stress predictions inside and outside particular training sets. Incidentally, we aim to develop efficient offline data generation methods to maximise the domain of validity of the CNN predictions. To achieve these ambitious goals, we will deploy a Bayesian approach providing not point estimates, but credible intervals of the fine-scale stress field to evaluate the uncertainty of the predictions. This will automatically encompass the lack of knowledge due to unseen macro and micro features. The uncertainty will be used in a Selective Learning framework to reduce the data requirements of the network. In this work we will investigate stress prediction in 2D porous structures with randomly distributed circular holes.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- A deep convolutional neural network for topology optimization with perceptible generalization abilityEngineering Optimization, 2021
- StressNet - Deep learning to predict stress with fracture propagation in brittle materialsnpj Materials Degradation, 2021
- A Single-Stream Segmentation and Depth Prediction CNN for Autonomous DrivingIEEE Intelligent Systems, 2020
- Dropout vs. batch normalization: an empirical study of their impact to deep learningMultimedia Tools and Applications, 2020
- Simulation of hyperelastic materials in real-time using deep learningMedical Image Analysis, 2020
- Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift2019
- Dropout-Based Active Learning for Regression2018
- Enhanced Deep Residual Networks for Single Image Super-Resolution2017
- Deeply-Recursive Convolutional Network for Image Super-Resolution2016
- Deep Residual Learning for Image Recognition2016