Neural Surrogate Modeling with Odd-Symmetric Activation for Cyclic Response Prediction and Multiobjective Optimization
Symmetry · 16.11.2026 · 18 (11) · 1916
DOI: 10.3390/sym18111916 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 16.11.2026. Verfasst von Mingyuan Hu und 7 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Provincial Natural Science Foundation, Dezhou Key Laboratory of Advanced Electric Energy Conversion and Intelligent Control.
Abstract (Originalsprache)
A fractional-inspired neural surrogate is developed for cyclic performance prediction and multiobjective exploration of reinforced concrete (RC) bridge piers. Its signed-power pre-activation, with exponent α = 0.8, satisfies h(−z) = −h(z), preserving sign-reversal symmetry locally. Positive response indicators retain their physical definitions; odd symmetry is imposed only on the internal transformation. An experimentally calibrated OpenSees fiber model provides 1000 converged cyclic simulations generated by Latin hypercube sampling over five design parameters. Calibration errors are 3.60% and 1.16% for positive and negative peak forces and 7.46% for cumulative energy. Under five-fold cross-validation, the neural surrogate exceeds random forest, XGBoost, and gradient boosting regression in reported predictive accuracy. The respective R2 values for initial stiffness, yield displacement, peak lateral resistance, ultimate displacement, unloading stiffness, and cumulative hysteretic energy are 0.9944, 0.9955, 0.9953, 0.9726, 0.9486, and 0.9973. TreeSHAP analysis of tree surrogates assigns 41.6% of summed mean absolute peak-resistance attribution to shear span ratio and identifies opposing axial load and confinement associations with ductility. NSGA-II yields representative cost–ductility configurations of 0.77, 1.03, and 1.31 kRMB with predicted ductilities of 4.94, 8.30, and 11.35, respectively. These results connect activation-level symmetry with surrogate-assisted exploration of cyclic pier behavior within the sampled domain. Methodologically, the scientific novelty of FANN stems from embedding a sublinear power transformation into the pre-activation mapping, whose derivative dampens extreme gradient spikes during multi-target fitting of quantities spanning diverse physical scales. The mathematical odd symmetry of the activation strictly enforces sign-reversal parity invariance under cyclic reversals, which is decoupled from, yet synergistic with, the sublinear scaling that governs global generalization.
Förderung
- Shandong Provincial Natural Science Foundation
- Dezhou Key Laboratory of Advanced Electric Energy Conversion and Intelligent Control
Zitieren
APA
Hu, M., Li, H., Wang, R., Gu, Y., Hu, J., An, Z., Zhang, L., & Li, S. (2026). Neural Surrogate Modeling with Odd-Symmetric Activation for Cyclic Response Prediction and Multiobjective Optimization. Symmetry, 18(11), 1916. https://doi.org/10.3390/sym18111916
Vancouver
Hu M, Li H, Wang R, Gu Y, Hu J, An Z, et al. Neural Surrogate Modeling with Odd-Symmetric Activation for Cyclic Response Prediction and Multiobjective Optimization. Symmetry. 2026;18(11):1916. doi:10.3390/sym18111916
BibTeX
@article{Hu2026,
author = {Hu, Mingyuan and Li, Hao and Wang, Rixia and Gu, Yaqing and Hu, Jingbo and An, Zhiliang and Zhang, Lei and Li, Sheng},
title = {Neural Surrogate Modeling with Odd-Symmetric Activation for Cyclic Response Prediction and Multiobjective Optimization},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {11},
pages = {1916},
doi = {10.3390/sym18111916}
}
EUVIMED