Applied Composite Materials

9 papers3 directions
Applied Composite Materials is a research venue active from 2011 to 2024 that focuses on the development, characterization, and modeling of complex material systems. While its core scope encompasses materials science and mechanical engineering, the venue serves the machine learning community by hosting research on the integration of data-driven methods with physical simulations. It provides a platform for exploring the structural, thermal, and vibrational properties of materials such as carbon fiber reinforced polymers (CFRP), 3D braided composites, and epoxy resins. In the field of artificial intelligence, the venue is characterized by its focus on data-driven surrogate models for high-fidelity physics and neural surrogates for non-linear and plastic material deformation. These computational approaches are frequently applied to predict material properties, such as the equivalent elastic modulus for metal-coated lattices, and to model non-linear interactions in multi-component materials. The research often bridges the gap between meso-scale voxel models and macro-scale performance, utilizing machine learning to account for manufacturing uncertainties in injection-molded parts and fiber orientation states. Key research directions include directional heat steering in anisotropic media and the multi-scale modeling of integrated 3D textiles. Prolific authors contributing to these areas at the venue include Diantang Zhang, Kun Qian, Li Chen, and Dietmar Drummer. By publishing work that combines finite element analysis with machine learning frameworks, the venue facilitates the advancement of predictive modeling in the design and validation of advanced composite structures.

Papers by Year

2024 2
2022 1
2021 1
2019 1
2018 1
2017 1
2016 1
2011 1

Top Research Directions

Research directions most represented by papers from this venue.

Scaling Geometric and Numerical Methods to Complex Shapes 1
Limits of the Linear Elasticity Approximation 1
Accelerating High Fidelity Simulations with Machine Learning Surrogates 1

Papers

TitleYear
Copper Modified Boron Nitride And Graphene Combined To Self-Assemble Three-Dimensional Thermal Conductivity Framework to Improve the Thermal Conductivity of Epoxy Resin2024
Efficient Approximation of Varying Fiber Orientation States in Injection Molded Parts Under Consideration of Multiple Manufacturing Uncertainties2024
Prediction of Equivalent Elastic Modulus for Metal-Coated Lattice Based on Machine Learning2022
Wide Scale Characterization and Modeling of the Vibration and Damping Behavior of CFRP-Elastomer-Metal Laminates—Comparison and Discussion of Different Test Setups2021
Reversed-Air Cooling Technology for High-Quality Drilling of CFRP2019
Nonlinear Multi-Scale Modelling, Simulation and Validation of 3D Knitted Textiles2018
Multi-Scale Modeling of an Integrated 3D Braided Composite with Applications to Helicopter Arm2017
Finite Element Analysis of Warp-Reinforced 2.5D Woven Composites Based on a Meso-Scale Voxel Model under Compression Loading2016
The Secondary Buckling and Design Criterion of Composite Laminated Cylindrical Shells2011