Development of mobile indoor flight test rig for VTOL UAV application

Vertical take-off and landing (VTOL) Unmanned aerial vehicles (UAVs) significantly contribute to various industries, such as agriculture, geospatial mapping and logistic services. The flying condition of this type of drone is affected by various factors, such as wind disturbance and battery performance. It should be in stable condition to achieve full performance during operation. Flying condition monitoring ensures efficient, high-quality, and reliable operation. Prediction of flying health conditions will reduce catastrophic failures that may cause severe damage, prolonged downtime, harmful incidents, and loss due to higher repair costs and major maintenance services. The rising complexity of VTOL UAV maintenance mechanisms necessitates smart diagnosis and prediction systems. This paper describes the design and implementation of a mobile flight test rig for indoor monitoring VTOL UAV flying conditions using motion detection systems. The primary aim is to utilise motion signals captured from the monitoring setup to develop an intelligent VTOL UAV fault detection and identification system using machine learning algorithms. The emergence of machine learning techniques and signal processing methods exposed research opportunities for constructing highaccuracy learning algorithms for smart VTOL UAV flying health diagnoses. Comprehensive utilisation of massive flying data will increase the accuracy of the learning algorithm, significantly reducing unnecessary maintenance tasks and the high cost of corrective maintenance.