RESUMEN
Composite materials are commonly used in aircraft, and the integrity of these materials affects both flight and safety performance. Damage detection technology involving infrared nondestructive testing has played an important role in damage detection in aircraft composite materials. Traditional manual detection methods are inefficient, and the use of intelligent detection methods can effectively improve detection efficiency. Due to the diverse types of damage that can occur in composite materials, this damage is difficult to distinguish solely from infrared images. The introduction of infrared signals, which is temporal signals, provides the possibility of judging the type of damage. In this paper, a 1D-YOLOv4 network is established. The network is based on the YOLOv4 network and adds a changing neck and a 1D-CNN for improvement. Testing shows that the algorithm can identify infrared images and infrared signals in composite materials. Its recognition accuracy is 98.3%, with an AP of 91.9%, and a kappa of 0.997. Comparing the network in this paper with networks such as YOLOv3, YOLOv4 and YOLOv4+Neck, the results show that the proposed network is more effective. At the same time, the detection effects of the original data, the fitted data, the first derivative data and the second derivative data are studied, and the detection effect of the first derivative data has the best outcome.
RESUMEN
With the large-scale application of composite materials in military aircraft, various composite material detection technologies with infrared nondestructive and ultrasonic nondestructive testing as the core have played an important role in detecting composite material component damage in military aircraft. At present, the damage of composite materials is mostly recognized manually, which is time-consuming, laborious, and inefficient. It can effectively improve detection efficiency and accuracy by using intelligent detection methods to detect and recognize damage. Moreover, the effect of infrared detection is significantly reduced with increasing detection depth, while ultrasonic detection has shallow-blind areas. A cascade fusion R-CNN network is proposed in order to comprehensively identify composite material damage. This network realizes the intelligent fusion recognition of infrared and ultrasonic damage images of composite materials. The network is based on a cascade R-CNN network, using fusion modules and BiFPN for improvement. For the infrared image and ultrasonic C-scan image data set established in this paper, the algorithm can identify the type and location of damage detected by infrared and ultrasonic testing. Its recognition accuracy is 99.3% and mean average precision (mAP) is 90.4%. In the detection process, the characteristics of infrared and ultrasonic images are used to realize the recognition of damage depth. Compared to SSD, YOLOv4, faster R-CNN and cascade R-CNN, the network proposed in this paper is better and more effective.
RESUMEN
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.