AI system detects damage in offshore wind turbines with 95% accuracy
Researchers have developed an AI network that identifies structural damage in floating wind turbines by analyzing vibration patterns, achieving 95% accuracy. The breakthrough matters because offshore wind farms operate in harsh conditions far from repair crews, making early damage detection critical to preventing costly failures and maintaining power generation.
Originaltitel: A Novel Residual Dual Attention Multiscale Network for Vibration-Based Damage Recognition in Floating Wind Turbine Structural Health Monitoring.
Flytande vindkraftverk kräver kontinuerlig övervakning för att säkerställa operativ säkerhet, men vibrationssignaler från havsmiljöer är svåra att analysera på grund av icke-stationär och flerskalig karaktär. Forskare från institutioner i Kina och Sverige presenterar RDAMNet, ett neuronnätverksarkitektur designat för skadeerkenning baserat på vibrationsmönster. Nätverket använder en flerskalig dekopplingsstrategi och dual attention-mekanismer för att extrahera skadkänsliga signalkarakteristika på flera tidsskalor samtidigt. På testdataset uppnår modellen 95,39 procent korrekthet och behåller över 94 procent noggrannhet även när vindförhållandena varierar. Med endast 663 783 parametrar och en inferenstid på 5,35 millisekunder per sample erbjuder RDAMNet en gynnsam balans mellan prestanda och effektivitet. För operatörer av offshoreanläggningsmöjliggör denna metod automatiserad felsökning som kan minska underhållskostnader och förlängad drifttid.
Floating wind turbines (FWTs) are key equipment for deep-sea clean energy exploitation, and their structural health condition is directly related to operational safety and energy output. However, FWT vibration signals exhibit significant non-stationary and multi-scale characteristics, with damage-sensitive features of different damage patterns spanning multiple temporal scales. Existing methods fail to sufficiently extract and fuse multi-scale damage-sensitive features. To this end, this paper proposes a novel Residual Dual Attention Multiscale Network (RDAMNet). The network innovatively designs a signal-level multi-scale decoupling strategy that extracts damage-sensitive features at different scales from complementary signal representations through a multi-branch differentiated architecture. Furthermore, an ECA-SE dual attention mechanism is designed to collaboratively enhance damage-related channel responses at both the feature extraction and fusion stages. Multiple independent experimental results on a publicly available dataset demonstrate that RDAMNet achieves a mean damage recognition accuracy and a weighted F1-score of 95.39% and 95.37%, respectively, significantly outperforming five compared methods. Cross-condition generalization experiments further demonstrate that RDAMNet maintains mean accuracies exceeding 94% across different wind speed and wind direction combinations, validating its stability across operating conditions. Moreover, RDAMNet only contains 663,783 parameters with a single-sample GPU inference time of 5.35 ms, exhibiting a favorable performance-efficiency trade-off. The ablation study verifies the effective contribution of each core component, and branch importance analysis, together with Grad-CAM visualization, further substantiates the multi-scale feature learning capability of the network. The proposed method provides an effective technical approach for intelligent structural health monitoring of FWTs in complex oceanic environments.