复合材料科学与工程Issue(2)：129-136,8.DOI:10.19936/j.cnki.2096-8000.20250228.016
基于多注意力机制的双通道模型对风机叶片表面目标识别
Dual-channel model based on multi-attention mechanism for wind turbine blade surface target recognition
摘要
Abstract
At present,the identification of defects in wind turbine blades mainly relies on two methods:tele-scopes and shutdown gondolas,but these methods have problems in accuracy and safety.With the widespread appli-cation of drone technology,the use of drones to identify surface defects on wind turbine blades has become a high-profile option.In this paper,a medium scale network combining Swin Transformer and lightweight neural network was proposed to identify the surface target of wind turbine blade using computer vision method.A dataset comprising 1 275 blade images from a coastal wind farm in East China was collected,and data augmentation techniques were employed to expand the dataset by a factor of five.In the model,the Swin Transformer served as the primary feature extractor,while the lightweight neural network functioned as the auxiliary feature extractor.The CBAM attention mechanism was introduced to enhance the model's focus on crucial local information,and the learning rate was ad-justed using the CosineAnnealingWarmRestarts strategy to optimize model performance.Experimental results show that the accuracy and F1-score of the model proposed in this paper reached 97.8%and 96.35%respectively,which are both ahead of the mainstream models of the same magnitude,providing a new method for wind turbine blade surface target recognition.关键词
风机叶片/复合材料/图像识别/Swin Transformer/轻量级神经网络/注意力机制Key words
wind turbine blades/composites/image identification/Swin Transformer/CNN/attention mechanism引用本文复制引用
柯灿阳,文传博..基于多注意力机制的双通道模型对风机叶片表面目标识别[J].复合材料科学与工程,2025,(2):129-136,8.基金项目
国家自然科学基金(61973209) （61973209）
