Damages Detection of Aeroengine Blades via Deep Learning Algorithms

To solve the problem of detecting the damages of aeroengine blades in harsh environments and reduce the aviation safety hazards caused by visual reasons, such as careless observation and delayed reporting of blade damages, the detection model of damages for aeroengine blades via deep learning algorithms is proposed in this article. First, the gamma correction method is used to process the dataset captured by the borescope to enhance the characterization ability. Second, the improved convolutional block attention module (CBAM) is embedded into the head and the end of backbone network of the YOLOv7 model. Meanwhile, a branch is added to the channel attention module of CBAM to optimize its network structure. Finally, in order to improve the accuracy and convergence speed, complete intersection over union $\rm (CIOU)$ is replaced by $\rm Alpha_{-}GIOU$ as a coordinate loss function in the YOLOv7 model, and a new flowchart of detection for aeroengine blade damages is proposed. Detection experiment results demonstrate that the mean average precision (mAP) of the improved YOLOv7 model in this article is 96.1%, which is 1.0% higher than the original model. The improved YOLOv7 module has remarkable effects compared with YOLOv5s, YOLOv4, single shot multibox detector (SSD), and Faster region-convolutional neural network (R-CNN) models. Meanwhile, the improved YOLOv7 model has better generalization performance, which provides a more reliable support for the real-time and visualization of damages detection of aeroengine blades.