BROWSE
Detail
Conference Paper
Autonomous Drone Flight Using Object Detection in X-Ray Images for Wind Turbine Blade Internal Inspection
- Authors
- HyunYong Lee, YuMin Hwang, HyunChol Jung, Seok-Kap Ko
- Issue Date
- 2025-10
- Citation
- European Conference on Artificial Intelligence (ECAI) 2025, pp.5319-5326
- Language
- English
- Type
- Conference Paper
- Abstract
- As a crucial component of wind turbines, blades require careful maintenance. Issues affecting power generation can occur inside and outside the blades, but most existing works focus on the blade external maintenance. This paper introduces a method for inspecting the blade internals, specifically the down conductor cable that protects the blades from lightning, to which wind turbines are easily exposed. We mount a lightweight X-ray device on two synchronized drones to image the blade internals and perform inspection through X-ray image-based object detection. For autonomous inspection, the drones must be able to track the down conductor cable inside the blade while capturing X-ray images. In this paper, we propose a method to estimate the orientation of detected objects in the currently captured X-ray image by manipulating the input images to the model and comparing outputs of the model without modifying the object detection model used for the inspection, and to determine the direction the drone should fly for the next X-ray imaging. Through field tests with actual operating wind turbines, we verified that the drones can track, image, and inspect the down conductor cable, thus realizing autonomous drone inspection.
- KSP Keywords
- Detection model, Field Test, Image-based, Power generation, Wind turbine blade, X-ray images, object detection, wind turbine(WT), x-ray imaging
This work is distributed under the term of Creative Commons License (CCL)
(CC BY NC)
(CC BY NC)
