Predicting Stress and Damage in Carbon Fiber-Reinforced Composites Deformation Process using Composite U-Net Surrogate Model

2025-04-19

AI Summary

To address the challenge of high-fidelity, computationally efficient prediction of coupled stress–damage evolution—including crack initiation and propagation—during deformation of carbon fiber-reinforced composites (CFRCs), this paper proposes an autoregressive hybrid U-Net model. The method jointly predicts spatiotemporal fields of stress and damage throughout the entire deformation history by integrating U-Net-based spatial feature extraction, multiscale microstructural modeling, and autoregressive temporal modeling. High-quality training data are generated via the interface-enriched generalized finite element method (IGFEM). Under uniaxial strain loading, the model achieves microscale stress and damage evolution accuracy comparable to IGFEM, while accelerating computation by over 60×. This breakthrough substantially alleviates the time bottleneck inherent in conventional finite element methods, establishing a new paradigm for real-time, multiscale mechanical simulation of CFRCs.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Carbon fiber-reinforced composites (CFRC) are pivotal in advanced engineering applications due to their exceptional mechanical properties. A deep understanding of CFRC behavior under mechanical loading is essential for optimizing performance in demanding applications such as aerospace structures. While traditional Finite Element Method (FEM) simulations, including advanced techniques like Interface-enriched Generalized FEM (IGFEM), offer valuable insights, they can struggle with computational efficiency. Existing data-driven surrogate models partially address these challenges by predicting propagated damage or stress-strain behavior but fail to comprehensively capture the evolution of stress and damage throughout the entire deformation history, including crack initiation and propagation. This study proposes a novel auto-regressive composite U-Net deep learning model to simultaneously predict stress and damage fields during CFRC deformation. By leveraging the U-Net architecture's ability to capture spatial features and integrate macro- and micro-scale phenomena, the proposed model overcomes key limitations of prior approaches. The model achieves high accuracy in predicting evolution of stress and damage distribution within the microstructure of a CFRC under unidirectional strain, offering a speed-up of over 60 times compared to IGFEM.

Problem

• Predict stress and damage in CFRC deformation process
• Overcome computational inefficiency of traditional FEM methods
• Capture stress and damage evolution comprehensively

Innovation

• Composite U-Net predicts stress and damage
• Auto-regressive model captures deformation history
• 60x faster than IGFEM with high accuracy