Operations with Unmanned Aerial Vehicles (UAVs) require reliability to execute missions. With the correct diagnostic, it is possible to predict vehicle failure during or before the flight. The objective of this work is to present a testing tool, which analyzes and evaluates drones during the flight in indoor environments. For this purpose, the framework Ptolemy II was extended for communication with real drones using the High-Level Architecture (HLA) for data exchanging and synchronization. The presented testing environment is extendable for other testing routines and is ready for integration with other simulation and analysis tools. In this paper, two failure detection experiments were performed, with a total of 20 flights for each one, which 80\% were used to train a decision tree algorithm, and the other 20% flights to test the algorithm in which one of the propellers had an anomaly. The failure rate or detection rate was 70\% for the first experiment and 90% for the second one.

No abstract