Recognition and detection of aero-engine blade damage based on Improved Cascade Mask R-CNN

Abstract

Aero-engine blades are an integral part of the aero-engine, and the integrity of these blades affects the flight performance and safety performance of an aircraft. The traditional manual detection method is time-consuming, labor-intensive, and inefficient. Hence, it is particularly important to use intelligent detection methods to detect and identify damage. In order to quickly and accurately identify the damage of the aero-engine blades, the present study proposes a network based on the Improved Cascade Mask R-CNN network-to establish the damage related to the aero-engine blades and detection models. The model can identify the damage type and locate and segment the area of damage. Furthermore, the accuracy rate can reach up to 98.81%, the Bbox-mAP is 78.7%, and the Segm-mAP is 77.4%. In comparing the Improved Cascade Mask R-CNN network with the YOLOv4, Cascade R-CNN, Res2Net, and Cascade Mask R-CNN networks, the results revealed that the network used in the present is excellent and effective.