Structural Digital Twin Modeling and Adaptive Pretrain-Finetune Learning for Dynamic Impact Identification on Wind Turbine Blades

Identification of dynamic impacts on wind turbine blades (WTB) is critical for structural safety and predictive maintenance. Although WTBs are exposed to impact risk, data samples of transient impact responses are rare in practice. To accurately identify dynamic impacts using limited real collections, this article proposes a systematic methodology with structural digital twin (SDT) modeling and adaptive pretrain-finetune learning. Given the generated source data from the SDT, deep transfer learning is addressed for the few-shot target data from real impacts. Particularly, receptive attention mechanisms are designed in an adaptively pretraining neural network for learning the SDT data in the source domain. In addition, a self-attention switch network is proposed as an adaptively finetuning neural network for knowledge transferring to the target domain. The physical experiments on both comparison and ablation study demonstrate the effectiveness and accuracy of the proposed method. Meanwhile, the identification process achieves high computational efficiency for online implementation.