Probabilistic Predictions of Process-Induced Deformation in Carbon/Epoxy Composites Using a Deep Operator Network

2025-12-14

AI Summary

To address the challenge of predicting process-induced distortions (PID) in carbon fiber/epoxy composites during autoclave curing—arising from thermal expansion mismatch and resin shrinkage—this work proposes a generalizable, calibratable, and uncertainty-quantified PID prediction framework integrating physics-informed modeling and data-driven learning. We innovatively employ a FiLM-modulated DeepONet architecture that couples local cure state variables, trained via simulation-based pretraining followed by experimental end-state fine-tuning. Uncertainty quantification and inverse optimization of the cure cycle are achieved through ensemble Kalman inversion (EKI). Validated on multi-scenario non-isothermal curing of the AS4/epoxy system, the framework achieves temporal predictions of distortion, viscosity, and degree of cure with end-state errors under 5%. It further generates optimal cure profiles subject to uncertainty constraints, reducing PID by up to 22%.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Fiber reinforcement and polymer matrix respond differently to manufacturing conditions due to mismatch in coefficient of thermal expansion and matrix shrinkage during curing of thermosets. These heterogeneities generate residual stresses over multiple length scales, whose partial release leads to process-induced deformation (PID), requiring accurate prediction and mitigation via optimized non-isothermal cure cycles. This study considers a unidirectional AS4 carbon fiber/amine bi-functional epoxy prepreg and models PID using a two-mechanism framework that accounts for thermal expansion/shrinkage and cure shrinkage. The model is validated against manufacturing trials to identify initial and boundary conditions, then used to generate PID responses for a diverse set of non-isothermal cure cycles (time-temperature profiles). Building on this physics-based foundation, we develop a data-driven surrogate based on Deep Operator Networks (DeepONets). A DeepONet is trained on a dataset combining high-fidelity simulations with targeted experimental measurements of PID. We extend this to a Feature-wise Linear Modulation (FiLM) DeepONet, where branch-network features are modulated by external parameters, including the initial degree of cure, enabling prediction of time histories of degree of cure, viscosity, and deformation. Because experimental data are available only at limited time instances (for example, final deformation), we use transfer learning: simulation-trained trunk and branch networks are fixed and only the final layer is updated using measured final deformation. Finally, we augment the framework with Ensemble Kalman Inversion (EKI) to quantify uncertainty under experimental conditions and to support optimization of cure schedules for reduced PID in composites.

Problem

• Predict process-induced deformation in carbon/epoxy composites using deep learning.
• Model residual stresses from thermal and cure shrinkage in composites.
• Quantify uncertainty and optimize cure cycles to reduce deformation.

Innovation

• DeepONet surrogate model for composite deformation prediction
• Transfer learning with limited experimental data for accuracy
• Ensemble Kalman Inversion quantifies uncertainty in predictions