Exact solutions of the (2+1)-dimensional BLMP equation via neural network based symbolic computation
Advances in Differential Equations and Control Processes · 01.12.2025 · 32 (4)
DOI: 10.59400/adecp3589 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Differential Equations and Control Processes, online erschienen am 01.12.2025. Verfasst von Jiang-Long Shen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper introduces a neural network-based symbolic computation framework for deriving exact analytical solutions to nonlinear partial differential equations (NLPDEs). By integrating the expressive capability of neural networks with the interpretability of symbolic methods, the approach offers a flexible, generalizable, and computationally efficient alternative to traditional techniques. Its architecture is straightforward, requiring minimal prior assumptions about the equation structure, thus enabling broad applicability across mathematical physics. As a case study, we investigate the (2+1)-dimensional Boiti-Leon-Manna-Pempinelli (BLMP) equation, a fundamental model describing wave propagation in fluid dynamics, nonlinear optics, and plasma physics. By systematically varying hidden-layer configurations and activation functions, we construct six distinct neural network models—comprising both single- and double-hidden-layer designs. These yield multiple novel exact analytical solutions, revealing diverse dynamic behaviors such as localized wave structures, periodic oscillations, and energy-localized modes. The physical characteristics of the obtained solutions are visualized through three-dimensional surface plots, contour maps, density distributions, and temporal evolution graphs. These illustrations elucidate key features including waveform stability, soliton localization, and nonlinear interactions. Unlike conventional methods such as the Hirota bilinear transformation or inverse scattering, the proposed framework avoids complex algebraic manipulations and does not rely on specialized transformations. Compared to physics-informed neural networks, it achieves higher interpretability and reduced computational dependency. This work expands the solution space of the (2+1)-dimensional BLMP equation and highlights the potential of neural-symbolic computation for discovering exact solutions in complex nonlinear systems.
Zitieren
APA
Shen, J., Zhang, R., Huang, J., Gao, Y., & Liang, J. (2025). Exact solutions of the (2+1)-dimensional BLMP equation via neural network based symbolic computation. Advances in Differential Equations and Control Processes, 32(4). https://doi.org/10.59400/adecp3589
Vancouver
Shen J, Zhang R, Huang J, Gao Y, Liang J. Exact solutions of the (2+1)-dimensional BLMP equation via neural network based symbolic computation. Advances in Differential Equations and Control Processes. 2025;32(4). doi:10.59400/adecp3589
BibTeX
@article{Shen2025,
author = {Shen, Jiang-Long and Zhang, Run-Fa and Huang, Jing-Wen and Gao, Yu and Liang, Jing-Bin},
title = {Exact solutions of the (2+1)-dimensional BLMP equation via neural network based symbolic computation},
journal = {Advances in Differential Equations and Control Processes},
year = {2025},
volume = {32},
number = {4},
doi = {10.59400/adecp3589}
}
EUVIMED