Abstract
This thesis deals with the design, prototype implementation and the assessment of virtual sensors for an Air Data System (ADS). The needs for the development of a virtual Air Data Sensors resides on two relevant aspects in aviation transport development: a) the opportunity to improve the safety of manned aviation, by implementing an affordable solution for ADS redundancy; b) the possibility to improve the reliability of unmanned air vehicles (UAVs), which can support their integration in non-segregated airspace. Virtual sensors are normally considered as a relevant component of Fault Detection and Isolation approaches to the Fault Tolerant Control Theory, briefly introduced in the thesis. Virtual sensors for both the Angle-of-Attack and the Indicated Air Speed have been developed and completely assessed in CIRA Laboratory test bed for Real-Time Simulation with Hardware and Pilot-in-the-Loop. In some cases, the assessment has also been achieved in flight test, on the FLARE vehicle which CIRA operates specifically for the execution of flight test of prototype technologies. The thesis first analyses and describe the basic methodologies for the virtual sensors design, identifying those better suitable for application to air data measures. In particular, both the model-based technique and the implementation of ADS Virtual Sensors through Artificial Neural Networks are described. Special attention is given to the data selection techniques aimed at network training and assessment, focusing the machine learning approach to this aspects. The study case applied to the TECNAM P92 VLA vehicle is described in detail, posing attention to the description of both the laboratory set-up realization and to the specific upgrades which have been required to the TECNAM P92 vehicle for the in-flight tests of the developed virtual sensors. The assessment of both the model-based Virtual Sensors and the ANN Virtual Sensors is finally documented.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
