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

2025-10-15

AI Summary

To address the insufficient generalization capability of elastic Bragg breakwaters in predicting motion responses under unknown sea conditions, this paper proposes a physics-informed dual-stream attention network. Methodologically, it introduces a novel attenuated bidirectional self-attention mechanism—explicitly modeling natural signal decay—and a phase-difference-guided cross-attention module—capturing wave–structure interaction dynamics—both enhanced with learnable temporal decay factors and phase biases. The architecture further incorporates global contextual fusion and a hybrid time–frequency loss function for robust optimization. Experimental evaluation on physical flume test data demonstrates that the proposed model significantly outperforms state-of-the-art deep learning approaches. Cross-sea-condition testing confirms its strong robustness and exceptional generalization to unseen hydrodynamic environments. This work establishes a new paradigm for intelligent, physics-aware response prediction of marine engineering structures.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Hardware-aware ML
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• Predicting motion responses of elastic Bragg breakwaters for marine safety
• Overcoming poor generalization of deep learning in unseen sea states
• Addressing inadequate modeling of wave-structure interaction and decay phenomena

Innovation

• Learnable temporal decay in attention mechanism
• Cosine-based bias for bidirectional wave-structure interaction
• Hybrid time-frequency loss for training optimization