Abstract
This study proposes a novel defect detection method to address the low accuracy and insufficient efficiency encountered during surface defect detection on aeroengine turbine blades (ATBs). The proposed approach employs the LDconv model to adjust the size and shape of convolutional kernels dynamically, integrates the deformable attention mechanism (DAT) to capture minute defect features effectively, and uses Focaler-CIoU to optimize the bounding box loss function of the detection network. Our approaches collectively provide precise detection of surface defects on ATBs. The results show that the proposed method achieves a mean average precision (mAP(0.5)) of 96.2%, an F-measure of 96.7%, and an identification rate (I(r)) of 98.8%, while maintaining a detection speed of over 25 images per second. The proposed method meets the stringent requirements for accuracy and real-time performance in ATB surface defect detection.