Regression mode collapse in deep learning surrogates for stochastic structural response prediction
Authors:
- Xiaodong XuXXXiaodong Xu
- Xing LinXLXing Lin
- Yuanyuan ZengYZYuanyuan Zeng
- Yan-Ping LiangYLYan-Ping Liang
- Shixue LiangSLShixue Liang
- 10 September 2026
- journal article
- Published by Elsevier in Probabilistic Engineering Mechanics
- Vol. 86
Abstract
No abstract availableFunding Information
- Zhejiang Sci-Tech University (24052126-Y)
- State Key Laboratory for Disaster Reduction in Civil Engineering (SLDRCE25-F-10)
- National Natural Science Foundation of China (51808499)
This publication has 31 references indexed in Scilit:
- Failure mechanism and probabilistic capacity reduction of reinforced concrete cooling towers with spatial geometric imperfectionsEngineering Failure Analysis, 2026
- Micrometer: Micromechanics transformer for predicting full field mechanical responses of heterogeneous materialsComputer Methods in Applied Mechanics and Engineering, 2025
- Novel gradient-enhanced Bayesian neural networks for uncertainty propagationComputer Methods in Applied Mechanics and Engineering, 2024
- Prediction of local elasto-plastic stress and strain fields in a two-phase composite microstructure using a deep convolutional neural networkComputer Methods in Applied Mechanics and Engineering, 2024
- Efficient stochastic finite element analysis of irregular wall structures with inelastic random field properties over manifoldComputational Mechanics, 2021
- On the BFGS monolithic algorithm for the unified phase field damage theoryComputer Methods in Applied Mechanics and Engineering, 2020
- A geometrically regularized gradient-damage model with energetic equivalenceComputer Methods in Applied Mechanics and Engineering, 2018
- Behaviour of U-shaped RC walls under quasi-static cyclic diagonal loadingEngineering Structures, 2016
- Variability in concrete mechanical properties as a source of in-plan irregularity for existing RC framed structuresEngineering Structures, 2014
- Thermodynamically consistent phase‐field models of fracture: Variational principles and multi‐field FE implementationsInternational Journal for Numerical Methods in Engineering, 2010