Searcharxiv⌕ Search

arXiv subjects

Huanhe Dong

Publications and source records attributed to Huanhe Dong.

2 recordsLinked to original sources

Superregular Breathers in the Sasa--Satsuma Equation: Spectral Conditions and Modulation Instability

In this work, we study the superregular breathers (SRBs) of the Sasa--Satsuma (SS) equation by combining a Darboux construction with a linear stability calculation. The reduction symmetry of the scalar SS Lax pair makes the fundamental SRB construction degenerate. The paired quasi-Akhmediev branches nevertheless yield second-order SRBs in the focusing sector $n|_{γ=0}<0$; neither the defocusing sector nor the focusing sector $n|_{γ=0}\geq0$ supports this construction. Linearization about the same plane-wave background gives the modulation-instability gain and, on the admissible branches, reproduces its relation to the group-velocity difference. The carrier wavenumber $b$ enters through the background rather than as a coefficient of the SS equation, and changes the spectral roots and instability interval. In the formal NLS limit, the result reduces to the familiar NLS gain. Numerical evolution of finite-width periodic perturbations produces the predicted second-order profile over the displayed propagation interval.

nlin.SI↗

A Physics Prior-Guided Dual-Stream Attention Network for Motion Prediction of Elastic Bragg Breakwaters

Accurate motion response prediction for elastic Bragg breakwaters is critical for their structural safety and operational integrity in marine environments. However, conventional deep learning models often exhibit limited generalization capabilities when presented with unseen sea states. These deficiencies stem from the neglect of natural decay observed in marine systems and inadequate modeling of wave-structure interaction (WSI). To overcome these challenges, this study proposes a novel Physics Prior-Guided Dual-Stream Attention Network (PhysAttnNet). First, the decay bidirectional self-attention (DBSA) module incorporates a learnable temporal decay to assign higher weights to recent states, aiming to emulate the natural decay phenomenon. Meanwhile, the phase differences guided bidirectional cross-attention (PDG-BCA) module explicitly captures the bidirectional interaction and phase relationship between waves and the structure using a cosine-based bias within a bidirectional cross-computation paradigm. These streams are synergistically integrated through a global context fusion (GCF) module. Finally, PhysAttnNet is trained with a hybrid time-frequency loss that jointly minimizes time-domain prediction errors and frequency-domain spectral discrepancies. Comprehensive experiments on wave flume datasets demonstrate that PhysAttnNet significantly outperforms mainstream models. Furthermore,cross-scenario generalization tests validate the model's robustness and adaptability to unseen environments, highlighting its potential as a framework to develop predictive models for complex systems in ocean engineering.

cs.LG↗