Size is one of the important bases for the level assessment of aero-engine blade damage and the disposal method selection for damaged blades. Therefore, research on in-situ damage measurement of aero-engine blades is conducted in this paper. We break the inherent pipeline of "3D reconstruction and manual annotation of keypoints" in traditional damage measurement methods, and propose an in-situ damage automatic measurement method (KBMeasure) based on the combination of damage keypoints intelligent detection and binocular 3D reconstruction. KBMeasure replaces the manual annotation of damage keypoints, improves the damage measurement efficiency, and reduces the dependence on professional inspectors. The proposed method also overcomes the problem of high computational cost and low efficiency caused by redundant 3D reconstruction of the entire damaged area. For the characteristics of large changes in damage scale, low image resolution, the requirement of high-precision keypoints positioning, limited annotated data, and lightweight deployment in aero-enginge blade damage measurement task, a novel blade damage keypoints detection model (DKeyDet) with top-down framework is designed by introducing coordinate classification, semi-supervised learning, and knowledge distillation. Then, intersecting optical axis binocular model is used to estimate the spatial coordinates of the detected keypoints and compute the size of damage. The keypoints detection average precision (AP) and average recall (AR) of our method are 87.6 and 91.3, and the damage measurement size error (SE) is 0.08, which is superior to existing methods. This research provides a new theoretical support for in-situ damage automatic measurement for aero-engine in service, and provides what we believe is a novel idea for damage measurement of industrial components in other fields.

To realize high-precision intelligent detection, location and area measurement of aviation functional surface damage, a damage location and area measurement method combining neural radiance field and improved Yolov8 network is proposed in this paper. The high-fidelity NeRF (Neural Radiance Field) and 3DGS (3D Gaussian Splatting) models are trained by acquired multi-view optical images of damaged functional surfaces. The rendered new-view images are used as a new data augmentation method to enhance the training effect of Yolov8 network. The network architecture of Yolov8 model is improved. The backbone is replaced with the latest StarNet feature extraction network, and the context feature fusion module (CFFM) proposed in this paper is used for feature fusion enhancement. The improved context-guide multi-head self-attention (CG-MHSA) is added to the detection Head. The comparison and ablation experiment results show that the improved module proposed in this paper has a good effect on the improvement of Yolov8 model, and improves the damage detection ability and location ability of the model. The application experiment results verify the effectiveness of the proposed method for calculating the damage area of a plane/camber surface, and the accuracy of the damage area measurement is high.