Data-driven failure criteria prediction in composite wing boxes using machine learning
Source abstract
Abstract
Modern transport aircraft exploit composite wing-box architectures to maximize strength-to-weight efficiency, yet the through-thickness damage states that govern air-worthiness remain difficult to quantify by closed-form analysis. A fully labeled benchmark data set, comprising 1017 finite-element (FE) simulations of a Cirrus-class carbon-fiber wing-box (nine undamaged cases plus 1008 damage scenarios obtained by combining 28 intralaminar damage locations with four severity levels for each of nine orthotropic materials) is therefore generated. Five classical failure criteria (Max-Stress, Tsai–Wu, Tsai–Hill, Hashin and Christensen) are evaluated at the most-stressed element and adopted as supervised-learning targets. Two regression surrogates, Random Forest (RF) ensembles and Support Vector Regression (SVR), are trained on the material-property vector and damage descriptors. A material-wise leave-one-out (LOO) cross-validation strategy demonstrates that the RF model attains a root-mean-square error RMSE 0.076 for the Hashin index, while preserving RMSE 0.15 on the Max-Stress index. The resulting RF surrogate furnishes near-instant predictions of composite failure indices and provides a reliable machine-learning benchmark for operational wing-box health assessment.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Structural Health Monitoring Techniques · Vehicle Noise and Vibration Control · Probabilistic and Robust Engineering Design
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (53)
Show source-provided references
1. Advances in artificial intelligence for structural health monitoring: A comprehensive review10.1016/j.kscej.2025.100203 ↗
2. Advancements in structural health monitoring: A review of machine learning approaches for damage detection and assessment
3. Fatigue predictive modeling of composite materials for wind turbine blades using explainable gradient boosting models10.3390/coatings15030325 ↗
4. Tosti Balducci · 2024
5. Hybrid deep convolutional networks for the autonomous damage diagnosis of laminated composite structures10.1016/j.compstruct.2023.117792 ↗
6. A review of machine learning applications in polymer composites: Advancements, challenges, and future prospects10.1039/D5TA00982K ↗
7. Design of fiber-reinforced variable-stiffness composites for different open-hole geometries with fiber continuity and curvature constraints10.1016/j.compstruct.2019.111280 ↗
8. Experimental and numerical study of the additively manufactured carbon fibre reinforced polymers including fibre bragg grating sensors10.1016/j.compstruct.2022.116027 ↗
9. Structural reliability software and calculation tools: a review10.1007/s41062-020-0282-4 ↗
10. A non-linear model for in-plane shear damage and failure of composite laminates10.1007/BF03404672 ↗
11. Variable-kinematics finite elements for propagation analyses of two-dimensional waveguides
12. Wave propagation in pre-stressed structures with geometric non-linearities through carrera unified formulation
13. Wave propagation in prestressed structures with geometric nonlinearities through carrera unified formulation10.2514/1.J064695 ↗
14. Thermo-based fatigue life prediction: A review10.1111/ffe.14079 ↗
15. Research on residual life prediction method of composites based on equivalent number of cycles conversion10.1007/s11668-024-01875-0 ↗
16. Prediction of creep life using an explainable artificial intelligence technique and alloy design based on the genetic algorithm in creep-strength-enhanced ferritic 9% Cr steel10.1007/s12540-022-01312-7 ↗
17. On the use of machine learning for damage assessment in composite structures: A review10.1007/s10443-023-10161-5 ↗
18. Artificial-neural-network-based surrogate models for structural health monitoring of civil structures: A literature review10.3390/buildings12122067 ↗
19. Artificial-intelligence-based methods for structural health monitoring10.3390/app122412726 ↗
20. Deep learning for structural health monitoring: Data, algorithms, applications, challenges, and trends10.3390/s23218824 ↗
21. Damage detection in structural health monitoring using combination of deep neural networks
22. Applications of neural network models for structural health monitoring based on derived modal properties10.1016/j.measurement.2018.07.051 ↗
23. Connecting concrete technology and machine learning: proposal for application of ANNs and CNT/concrete composites in structural health monitoring10.1039/D0RA03450A ↗
24. Structural health monitoring procedure for composite structures through the use of artificial neural networks10.1007/BF03404684 ↗
25. Optimizing the acoustic properties of a meta-material using machine learning techniques
26. Failure prediction and optimization for composite pressure vessel combining FEM simulation and machine learning approach10.1016/j.compstruct.2024.118099 ↗
27. A generalised deep learning-based surrogate model for homogenisation utilising material property encoding and physics-based bounds10.1038/s41598-023-34823-3 ↗
28. Corporation · 2025
29. Toray Carbon Fibers America · 2025
30. DuPont · 2020
31. AZoM · 2023
32. Inc. · 2024
33. Brothers · 2024
34. Optimal design of composite wing structures with blended laminates10.1016/j.compositesb.2006.08.005 ↗
35. Support vector machines: Theory and applications
36. Random forests10.1023/A:1010933404324 ↗
37. Prediction of maximum tensile stress in plain-weave composite laminates with interacting holes via stacked machine learning algorithms: A comparative study10.1016/j.ymssp.2023.110315 ↗
38. Chained machine-learning model for predicting load capacity and ductility of steel fibre–reinforced concrete beams10.1111/mice.13164 ↗
39. Borisov · 2022
40. Grinsztajn · 2023
41. On the modeling of composite beam cross-sections10.1016/j.compositesb.2010.10.012 ↗
42. Static deflection of fully coupled composite timoshenko beams: An exact analytical solution10.1016/j.euromechsol.2020.103975 ↗
43. Closed-form analytical solutions for predicting stress transfers and thermo-elastic properties of short fiber composites
44. Multiscale modelling strategy for a novel wingbox structure with increased bend-twist coupling10.1016/j.compstruct.2025.119291 ↗
45. A machine learning framework for physics-based multi-fidelity modeling and health monitoring for a composite wing
46. Surrogate modeling approach to support real-time structural assessment and decision making10.2514/1.J053464 ↗
47. A multi-fidelity surrogate model for structural health monitoring exploiting model order reduction and artificial neural networks10.1016/j.ymssp.2023.110376 ↗
48. Goldblum · 2024
49. A review on machine learning implementation for predicting and optimizing the mechanical behaviour of laminated fiber-reinforced polymer composites10.1016/j.heliyon.2024.e33681 ↗
50. A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis10.1098/rsif.2017.0844 ↗
51. Machine learning-based modeling for structural engineering: A comprehensive survey and applications overview10.3390/buildings14113515 ↗
52. Deep learning-based structural health monitoring10.1016/j.autcon.2024.105328 ↗
53. A machine learning approach as a surrogate for a finite element analysis: Status of research and application to one dimensional systems10.3390/s21051654 ↗