Evaluation of Best Theories using Neural Networks and Adaptive Sampling
Marco PETROLO, Giulio CANDITA, Alfonso PAGANI, Erasmo CARRERA
Abstract. This work presents an Adaptive Sampling-based surrogate framework for predicting the accuracy of higher-order beam theories generated within the Carrera Unified Formulation. The objective is to identify the minimal set of generalized displacement variables required to achieve a prescribed accuracy, thereby reducing the need for exhaustive high-fidelity structural analyses. Structural theories are built using Taylor-like polynomial expansions, and an Adaptive Sampling strategy based on an Extra Trees Regressor iteratively selects the most informative generalized variables by combining predicted error, uncertainty, and structural diversity. The selected dataset is then used to train a Neural Network to predict the average error in natural frequencies. The proposed strategy is evaluated using Best Theory Diagrams, which relate model accuracy to the number of degrees of freedom. Results show that Adaptive Sampling achieves accuracy comparable to, and in some cases better than, random sampling at the same sampling budget, while correctly identifying the most effective structural theories with fewer high-fidelity analyses. The framework, therefore, provides an efficient tool for data-driven selection of refined beam models.
Keywords
CUF, FEM, Structural Theories, Neural Networks, Adaptive Sampling
Published online 11/8/2026, 5 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Marco PETROLO, Giulio CANDITA, Alfonso PAGANI, Erasmo CARRERA, Evaluation of Best Theories using Neural Networks and Adaptive Sampling, Materials Research Proceedings, Vol. 73, pp 190-194, 2026
DOI: https://doi.org/10.21741/9781644904459-37
The article was published as article 37 of the book Mechanics of Advanced Materials and Structures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Euler L. De curvis elasticis. Lausanne and Geneva: Bousquet, 1744.
[2] Timoshenko S.P. On the transverse vibrations of bars of uniform cross-section. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 43(253):125-131, 1922. https://doi.org/10.1080/14786442208633855
[3] Timoshenko S.P. On the correction for shear of the differential equation for transverse vibrations of prismatic bars. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 41(245):744-746, 1921. https://doi.org/10.1080/14786442108636264
[4] Carrera E., Petrolo M., On the effectiveness of higher-order terms in refined beam theories. Journal of Applied Mechanics, 78(2):021013, 11 2010. https://doi.org/10.1115/1.4002207
[5] Carrera E., Pagani A., Petrolo M., Zappino E., Recent developments on refined theories for beams with applications. Mechanical Engineering Reviews, 2(2):14-00298-14-00298, 2015. https://doi.org/10.1299/mer.14-00298
[6] Carrera E., Cinefra M., Petrolo M., Zappino E., Finite element analysis of structures through unified formulation. John Wiley & Sons, 2014. https://doi.org/10.1002/9781118536643
[7] Petrolo M., Carrera E., Best theory diagrams for multilayered structures via shell finite elements. Advanced Modeling and Simulation in Engineering Sciences, 2019. https://doi.org/10.1186/s40323-019-0129-8
[8] Petrolo M., Iannotti, P., Best Theory Diagrams for Laminated Composite Shells Based on Failure Indexes. Aerotec. Missili Spaz. 102, 199-218, 2023. https://doi.org/10.1007/s42496-023-00158-5
[9] Kudela J., Matousek R., Recent advances and applications of surrogate models for finite element method computations: a review: J. Kudela, R. Matousek. Soft Computing, 26(24), pp.13709-13733, 2022. https://doi.org/10.1007/s00500-022-07362-8
[10] Cunha B.Z, Droz C., Zine A.M., Foulard S., Ichchou M., A review of machine learning methods applied to structural dynamics and vibroacoustic. Mechanical Systems and Signal Processing, 200, p.110535, 2023. https://doi.org/10.1016/j.ymssp.2023.110535
[11] Petrolo M., Pagani A., Carrera E., Candita G., Iannotti P., Mapping beam cross-section features to higher-order generalized variables using machine learning. Thin-Walled Structures, Volume 218, Part C, 2026. https://doi.org/10.1016/j.tws.2025.114108
[12] Petrolo M., Pagani A., Candita G., Iannotti P., Carrera E., Assessment of multi-fidelity structural theories for dynamic analyses using machine learning. In Proceedings of the ASME 2025 Aerospace Structures, Structural Dynamics, and Materials Conference SSDM2025, Houston, 2025. https://doi.org/10.1115/SSDM2025-152306
[13] Settles, B. Active learning literature survey, 2009
[14] Liu H., Ong Y.S., Cai J., A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design: H. Liu et al. Structural and Multidisciplinary Optimization, 57(1), pp.393-416, 2018. https://doi.org/10.1007/s00158-017-1739-8
[15] Ghazi Y., Alhazmi N., Tezaur R. and Farhat C., Training a neural-network-based surrogate model for aerodynamic optimisation using a Gaussian process. International Journal of Computational Fluid Dynamics, 36(7), pp.538-554, 2022. https://doi.org/10.1080/10618562.2022.2138863
