Intelligent damage recognition of composite materials based on deep learning and ultrasonic testing

Caizhi Li,Xinyu Liu,Xin Wu,Xiangfan Nie,Xiaolong Wei,Hanyi Guo,Tiejun Zhang,Weifeng He,Haojun Xu

doi:10.1063/5.0063615

Caizhi Li, Xinyu Liu + Show 7 more

Open Access

https://doi.org/10.1063/5.0063615

Copy DOI

Abstract

Ultrasonic non-destructive testing can effectively detect damage in aircraft composite materials, but traditional manual testing is time-consuming and labor-intensive. To realize the intelligent recognition of aircraft composite material damage, this paper proposes a 1D-YOLO network, in which intelligent fusion recognizes both the ultrasonic C-scan image and ultrasonic A-scan signal of composite material damage. Through training and testing the composite material damage data on aircraft skin, the accuracy of the model is 94.5%, the mean average precision is 80.0%, and the kappa value is 97.5%. The use of dilated convolution and a recursive feature pyramid effectively improves the feature extraction ability of the model. The effectively used Cascade R-CNN (Cascade Region-Convolutional Neural Network) improves the recognition effect of the model, and the effectively used one-dimensional convolutional neural network excludes non-damaged objects. Comparing our network with YOLOv3, YOLOv4, cascade R-CNN, and other networks, the results show that our network can identify the damage of composite materials more accurately.

Highlights

Composite materials are structural materials with excellent performance that have been widely used in aircraft vertical tails, flat tails, fuselages, and wing skins.1,2 During use, aircraft face complex environments, such as high-frequency vibration, foreign object impact, and high-temperature oxidation, which can cause damage to composite materials.3,4 This poses a threat to the safety of aircraft and brings challenges to the inspection and maintenance of aircraft
To realize the intelligent recognition of aircraft composite material damage, this paper proposes a 1D-YOLO network, in which intelligent fusion recognizes both the ultrasonic C-scan image and ultrasonic A-scan signal of composite material damage
Through training and testing the composite material damage data on aircraft skin, the accuracy of the model is 94.5%, the mean average precision is 80.0%, and the kappa value is 97.5%

Summary

Introduction

Composite materials are structural materials with excellent performance that have been widely used in aircraft vertical tails, flat tails, fuselages, and wing skins. During use, aircraft face complex environments, such as high-frequency vibration, foreign object impact, and high-temperature oxidation, which can cause damage to composite materials. This poses a threat to the safety of aircraft and brings challenges to the inspection and maintenance of aircraft. Composite materials are structural materials with excellent performance that have been widely used in aircraft vertical tails, flat tails, fuselages, and wing skins.. Aircraft face complex environments, such as high-frequency vibration, foreign object impact, and high-temperature oxidation, which can cause damage to composite materials.. Aircraft face complex environments, such as high-frequency vibration, foreign object impact, and high-temperature oxidation, which can cause damage to composite materials.3,4 This poses a threat to the safety of aircraft and brings challenges to the inspection and maintenance of aircraft. Used composite material non-destructive testing techniques include ultrasonic testing, infrared testing, x-ray testing, etc. Ultrasonic testing is the most widely used non-destructive testing technology due to its good directivity, strong penetrability, high sensitivity, harmlessness to the human body and the environment, and low weight

Methods

Findings

Discussion

Conclusion