Hardware in the Loop Simulation of Aircraft Inspection by an Unmanned Aerial System

Abstract

Inspection of commercial aircrafts, wind turbines, bridges and other infrastructure elements is done manually in many cases. Therefore, today's maintenance mostly is time-consuming and cost-intensive. The goal of the joint project AI inspection drone is the holistic system design of an unmanned aerial system (UAS) for the damage detection and assessment of airliners. The technical design should be based on current maintenance requirements and the overall system should be able to anticipate its own flight, evaluate the inspection data AI-based, and draw automatic conclusions. In this paper we describe the structure of the announced and partly already realized process chain. The focus is on the required interfaces between the individual components, the control engineering challenges to the UAS and the mapping of the entire process chain in a simulation environment, which also enables a hardware in the loop test of the different sensors and the carrier system itself. Based on this simulation which also includes the mapping of the technical and operational environment, different movement strategies with regard to energy requirements and flight time as well as an efficient sensor data fusion should be investigated. The results obtained are, as far as possible, validated by simulation and real experiments.