A novel deep learning-based modelling strategy from image of particles to mechanical properties for granular materials with CNN and BiLSTM

2021/04/24 by Pin Zhang, Zhen-Yu Yin, Zhen‐Yu Yin · 101 citations
Engineering · Environmental Science · #Artificial intelligence #Artificial neural network #Composite material #Computer science #Convolutional neural network #Discrete element method #Geology #Geotechnical Engineering and Soil Mechanics #Granular material #Isotropy #Landslides and related hazards #Materials science #Mechanics #Optics #Particle (ecology) #Physics #Rock Mechanics and Modeling #Roundness (object) #Sample (material)

paper · open access · doi:10.1016/j.cma.2021.113858

published in Computer Methods in Applied Mechanics and Engineering 382, 113858 (Elsevier BV)

openalex publication_date 2021/04/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Citations

• A discrete numerical model for granular assemblies
• Volume, Shape, and Roundness of Rock Particles
• Smoothing and Differentiation of Data by Simplified Least Squares Procedures.
• ImageNet classification with deep convolutional neural networks

Cited by

• Instant Particle Size Distribution Measurement Using CNNs Trained on Synthetic Data
• Rapid prediction of railway ballast particle motion using an acceleration-based continuous convolutional neural network
• Deep-learning-based 3D cellular force reconstruction directly from volumetric images. [europepmc]
• Use of machine learning for unraveling hidden correlations between particle size distributions and the mechanical behavior of granular materials. [europepmc]
• Introduction of Materials Genome Technology and Its Applications in the Field of Biomedical Materials. [europepmc]
• Extensive overview of soil constitutive relations and applications for geotechnical engineering problems. [europepmc]
• Image processing and neural network technique for size characterization of gravel particles. [europepmc]
• A Physics-Guided Machine Learning Model for Predicting Viscoelasticity of Solids at Large Deformation. [europepmc]
• Machine Learning Assisted Cross-Scale Hopper Design for Flowing Biomass Granular Materials. [europepmc]
• DEM study on the effect of fiber length and content on the macro-micro mechanical behavior of fiber-sand mixture. [europepmc]