Predicting creep behavior in composites from microstructural features using deep learning
Source abstract
Abstract
This study uses a multilayer perceptron deep learning model to predict creep strain vs time curves in composite materials based on their microstructural features. Finite element simulations generate ground truth data for model training and validation. The multilayer perceptron model, trained on this comprehensive dataset, effectively captures the complex relationships between the microstructure and creep behavior, achieving high accuracy. Comparative analysis with traditional models shows the multilayer perceptron model’s superior performance. This demonstrates the model’s potential for reliable application in various engineering fields, offering improved predictions of composite material behavior under creep conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Innovative concrete reinforcement materials · Concrete Properties and Behavior · Asphalt Pavement Performance Evaluation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Hydraulic Science and Engineering, Yangzhou University 1 , Yangzhou 225009,
Department of Engineering Science, Bethany Lutheran College 2 , Mankato, Minnesota 56001,
References (19)
Show source-provided references
1. Creep failure time prediction of polymers and polymer composites10.1016/j.compscitech.2012.03.018 ↗
2. Deep learning model to predict complex stress and strain fields in hierarchical composites10.1126/sciadv.abd7416 ↗
3. Predicting the effective thermal conductivity of composites from cross sections images using deep learning methods10.1016/j.compscitech.2019.107861 ↗
4. Application of deep neural network learning in composites design10.1080/26889277.2022.2053302 ↗
5. Creep of polymer composites10.1016/s0266-3538(97)00104-8 ↗
6. Deformation and failure processes during tensile creep of fibre and whisker reinforced SiC/Al2O3 composites10.1016/s0921-5093(99)00451-7 ↗
7. Creep behavior and failure mechanisms of CVI and PIP SiC/SiC composites at temperatures to 1650 °C in air10.1016/j.jeurceramsoc.2021.05.059 ↗
8. Woods and composites cantilever beam: A comprehensive review of experimental and numerical creep methodologies10.1016/j.jmrt.2020.01.013 ↗
9. Identification of plasticity-controlled creep and fatigue failure mechanisms in transversely loaded unidirectional thermoplastic composites10.1177/0021998320964252 ↗
10. Tensile creep behaviour of unidirectional flax fibre reinforced bio-based epoxy composites10.1016/j.coco.2019.12.010 ↗
11. Tensile creep behavior of short-carbon-fiber reinforced polyetherimide composites10.1016/j.compositesb.2021.108717 ↗
12. Enhanced creep resistance of GFRP composites through interpenetrating polymer network10.1016/j.ijmecsci.2021.106728 ↗
13. Characterization and modeling of the creep behavior of fiber composites with tension and compression asymmetry10.1016/j.ijmecsci.2019.105340 ↗
14. Modeling creep behavior in ceramic matrix composites10.1016/j.ceramint.2021.01.125 ↗
15. A deep learning based life prediction method for components under creep, fatigue and creep-fatigue conditions10.1016/j.ijfatigue.2021.106236 ↗
16. Predicting creep failure by machine learning-which features matter?10.1016/j.finmec.2022.100141 ↗
17. Deep learning accelerates the development of Ni-based single crystal superalloys: A physical-constrained neural network for creep rupture life prediction10.1016/j.matdes.2023.112174 ↗
18. A physics-informed neural network for creep-fatigue life prediction of components at elevated temperatures10.1016/j.engfracmech.2021.108130 ↗
19. Modeling and sensitivity analysis of concrete creep with machine learning methods10.1061/(asce)mt.1943-5533.0003843 ↗