Probabilistic Predictions of Process-Induced Deformation in Carbon/Epoxy Composites Using a Deep Operator Network
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 26 of its 88 references that are in the map. First posted on arXiv 15 Dec 2025.
Builds on
26 of 88 references.
References · 26
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 540
- 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 170
- 2024A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networkscited by 104
- 2018Uncertainty in Neural Networks: Approximately Bayesian Ensemblingcited by 94
- 2019GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulationcited by 75
- 2023Sequential Deep Operator Networks (S-DeepONet) for Predicting Full-field Solutions Under Time-dependent Loadscited by 47
- 2022Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priorscited by 39
14 more
- 2024Transformers as Neural Operators for Solutions of Differential Equations with Finite Regularitycited by 34
- 2023On the training and generalization of deep operator networkscited by 31
- 2024RiemannONets: Interpretable Neural Operators for Riemann Problemscited by 28
- 2024Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEscited by 15
- 2024Predicting Crack Nucleation and Propagation in Brittle Materials Using Deep Operator Networks with Diverse Trunk Architecturescited by 12
- 2021A Machine Learning Framework for Real-time Inverse Modeling and Multi-objective Process Optimization of Composites for Active Manufacturing Controlcited by 9
- 2025Scientific Machine Learning with Kolmogorov-Arnold Networkscited by 6
- 2025A Variational Framework for Residual-Based Adaptivity in Neural PDE Solvers and Operator Learningcited by 6
- 2024Uncertainty quantification for deeponets with ensemble kalman inversioncited by 4
- 2024Bridging scales in multiscale bubble growth dynamics with correlated fluctuations using neural operator learningcited by 4
- 2022Machine Learning-Driven Process of Alumina Ceramics Laser Machiningcited by 2
- 2025Scalable Bayesian Physics-Informed Kolmogorov-Arnold Networkscited by 2
- 2023Designing architectured ceramics for transient thermal applications using finite element and deep learningcited by 1
- 2025Retrofitting Earth System Models with Cadence-Limited Neural Operator Updatescited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.