AI-empowered, low-cost and portable optical fiber sensor system for distributed monitoring and shape reconstruction in UAV structures

This paper presents the development and application of a low-cost distributed optical fiber sensor for the continuous monitoring of force and shape in Unmanned Aerial Vehicles (UAVs) wings. The sensor system includes nanoparticle-doped optical fibers with enhanced backscattering, which lead to higher sensitivity and spatial resolution in transmission–reflection analysis (TRA) systems. The acquired optical signals are fed into a neural network that provides the force distribution along the wing surface area. The results indicated the feasibility of the proposed system in which the RMSEs of 0.46 N, 13.1 mm and 5.2 mm were found for the estimation of force amplitude, location in x-axis and y-axis, respectively. Then, the distributed displacement sensing for wing shape reconstruction is evaluated and demonstrated a high accuracy in the 3D shape reconstruction with relative errors as small as 0.21%. Thus, the proposed system is a solution with the combination of low-cost, high resolution and high accuracy for the first time in aircraft monitoring distributed systems. Therefore, the proposed AI-enabled sensor system provides a low-cost distributed optical fiber sensor that can be directly integrated into the control unit of UAV due to the simplicity of the signal acquisition process. • Low-cost distributed optical fiber sensor for UAV wing force and shape monitoring. • Nanoparticle-doped fibers boost sensitivity and resolution in TRA systems. • Neural network maps force distribution from optical signals along wing surface. • Achieved RMSE: 0.46 N (force), 13.1 mm (x), 5.2 mm (y) in force estimation. • 3D wing shape reconstruction with errors as low as 0.21%, highly accurate.