Vortex-Induced Vibration Recognition for Long-Span Bridges Based on Transfer Component Analysis

Bridge vortex-induced vibration (VIV) refers to the vertical resonance phenomenon that occurs in a bridge when pulsating wind passes over it and causes vortices detach. In recent years, VIV events have been observed numerous long-span bridges, leading fatigue damage structure posing risks driving safety. The advancement of technologies such as structural health monitoring (SHM), machine learning, big data has opened up new research avenues for intelligent identification bridges. Machine learning algorithms can accurately identify from historical accumulated by SHM systems, thus providing an effective method recognition. Nevertheless, existing methods limitations, particularly their applicability bridges lacking data. This study introduces adaptive recognition main girders suspension based on Transfer Component Analysis (TCA). patterns real-time or data, even specific are not available target bridge. proposed exhibits suitability multiple Experimental validation is performed using datasets two results show recognize more samples compared benchmark model. When sensor 1 B source domain L-section A, F1 score TCA-based 0.836, while model 0.165. other 11 cases, higher than 0.8, which demonstrates method’s robust generalization capabilities.