Data‐Driven Detection of Internal Erosion Initiation in Gap‐Graded Soils: Combining Particle‐Scale CFD‐DEM Simulation With 3D Convolutional Autoencoder

ABSTRACT Internal erosion in gap‐graded soils poses significant risks to water‐retaining structures such as earth dams. However, its underlying mechanisms at the particle scale remain poorly understood. This study couples the discrete element method (DEM) with computational fluid dynamics (CFD) to s...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal for numerical and analytical methods in geomechanics Ročník 49; číslo 17; s. 4225 - 4247
Hlavní autoři: Qi, Jie, Yousefpour, Negin, Narsilio, Guillermo A., Pouragha, Mehdi
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bognor Regis Wiley Subscription Services, Inc 01.12.2025
Témata:
anomaly detection
Artificial neural networks
CFD‐DEM
Computational fluid dynamics
Contact force
convolutional autoencoder
Dams
Deep learning
Discrete element method
Earth dams
Fluid dynamics
Hydrodynamics
internal erosion
Machine learning
Neural networks
Orbital velocity
Particle motion
sequential training
Soil
Soils
Tensors
Velocity
ISSN:0363-9061, 1096-9853
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:ABSTRACT Internal erosion in gap‐graded soils poses significant risks to water‐retaining structures such as earth dams. However, its underlying mechanisms at the particle scale remain poorly understood. This study couples the discrete element method (DEM) with computational fluid dynamics (CFD) to simulate internal erosion in gap‐graded soil assemblies and employs data‐driven techniques to detect early‐stage erosion. Particle‐scale parameters, such as contact forces, particle velocity and fluid velocity, are extracted from the transient CFD‐DEM simulations. These features are transformed into multi‐dimensional voxel‐based tensors representing the particle–fluid interactions, which are used to train deep learning models. Autoencoder models with 3D convolutional neural network (CNN) layers as encoder and decoder are developed to investigate the micro‐scale patterns within the particle‐fluid assembly. Through sequential training techniques, the temporal evolution of anomalies is captured, enabling identification of the initiation point of internal erosion. The results reveal how microscale behaviours, such as particle motion, contact forces and contact number, contribute to macroscale erosion processes. The outcome of this research can inspire further research into AI‐based early detection techniques for internal erosion in earth dams.
Bibliografie:Funding
This study was funded by the University of Melbourne's Early Career Research Grant, China Scholarship Council Scholarship, and Australian Research Council DP210100433.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0363-9061
1096-9853
DOI:10.1002/nag.70063