Aircraft Skin Damage Visual Testing System Using Lightweight Devices with YOLO: An Automated Real-Time Material Evaluation System

Abstract

Inspection and material evaluation are some of the critical factors to ensure the structural integrity and safety of an aircraft in the aviation industry. These inspections are carried out by trained personnel, and while effective, they are prone to human error, where even a minute error could result in a large-scale negative impact. Automated detection devices designed to improve the reliability of inspections could help the industry reduce the potential effects caused by human error. This study aims to develop a system that can automatically detect and identify defects on aircraft skin using relatively lightweight devices, including mobile phones and unmanned aerial vehicles (UAVs). The study combines an internet of things (IoT) network, allowing the results to be reviewed in real time, regardless of distance. The experimental results confirmed the effective recognition of defects with the mean average precision (mAP@0.5) at 0.853 for YOLOv9c for all classes. However, despite the effective detection, the test device (mobile phone) was prone to overheating, significantly reducing its performance. While there is still room for further enhancements, this study demonstrates the potential of introducing automated image detection technology to assist the inspection process in the aviation industry.