https://doi.org/10.1140/epjp/s13360-025-06422-w
Regular Article
Nonlinear bending behavior of the bi-stable FG-GRC fluid-conveying pipes considering internal flow: snap-through and load–deflection prediction based on BPNN
School of Artificial Intelligence and Automation, Wuhan University of Science and Technology, 430081, Wuhan, Hubei, China
Received:
26
December
2024
Accepted:
13
May
2025
Published online:
5
June
2025
In this study, the BP neural network (BPNN) technology is innovatively applied to the research on the nonlinear bending behavior of bi-stable functionally graded graphene-reinforced composite fluid-conveying pipes considering internal flow. By expanding the Zhang-Fu deformation theory, a high-order displacement field is constructed. The constitutive relationship of functionally graded materials is established using the Halpin–Tsai model. Combining with the variational principle, the stability and nonlinear bending models of the pipes are obtained. The research finds that the influence of structural characteristics on the nonlinear bending behavior of the pipes presents a two-stage process based on physical configuration changes. The snap-through behavior is accompanied by the change of structural stiffness from positive to negative and then to positive. Moreover, the flow-induced initial configuration provides higher stiffness when the pipe is far from the critical instability state. The developed BPNN technology can accurately predict the nonlinear bending behavior, especially capture the snap-through phenomenon. The research results provide important theoretical basis and prediction methods for the structural design and optimization of aerospace fluid-conveying pipelines. In the future, the application of the BPNN in fluid-conveying pipes under more complex working conditions and with different structural forms can be further explored.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
