Researchers have developed an adaptive-trunk DeepONet model to improve the prediction of localized structural responses in long-span roadway bridges. This new framework uses a k-nearest neighbors (KNN) strategy to dynamically create a load-dependent learning domain, enabling the network to focus on critical structural influence zones. The model incorporates distance-aware features and a physics-based reconstruction method, achieving FEM-level accuracy with significantly reduced computational time, up to 60x faster overall and four orders of magnitude faster for inference alone. AI
IMPACT This AI model significantly accelerates structural analysis for bridges, enabling faster digital twin applications and infrastructure assessment.
RANK_REASON The cluster contains a research paper published on arXiv detailing a new AI model for structural analysis.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
