The Airbus A350 XWB stands as the most modern and efficient commercial jetliner globally today. Since January 2015, this aircraft has been operating worldwide with an advanced and robust model-based monitoring system onboard. This significant accomplishment is the result of a collaborative effort between my research team and Airbus, beginning in the mid-2000s, to address Fault Detection, Isolation, and Recovery (FDIR) challenges in aircraft systems. With current airworthiness certification standards in civil aviation, extremely rigorous specifications must be satisfied, not only in nominal flight regimes, but also in extreme, unusual, non-standard/off-nominal and unexpected flight conditions. The certification testifies that new systems meet all requirements set by the aviation regulatory authorities — FAA (USA) and EASA (Europe) — and that they themselves do not introduce new risks. Developing flight-proven and certified model-based monitoring systems was a complex endeavor that demanded years of dedicated research and innovation, rigorous verification and validation activities, as well as in-flight tests and continuous refinement.

Five years after the first A350 commercial flight, this note posted on the IFAC Blog and IFAC social media looks back at some lessons learnt from this amazing success story. The note has been prepared by Dr. Philippe Goupil (eXpert FDIR – A/C Control Architecture & Functions, Airbus, Toulouse – France) and myself. See also IFAC Newsletter, December 2020.

A. Zolghadri – IMS Bordeaux, France

P. Goupil – Airbus, Toulouse, France

What about the aircraft of the 2030s and beyond? In civil aviation operations, the vector is pointed toward more autonomy and intelligence in the cockpit. Future avionics will have to ensure more autonomy and must provide safety functionalities at least equivalent to those of today blended-crew task environments, while coupled to a new cockpit concept. The next leap forward will be to take one pilot out of the cockpit (Single Pilot Operations, SPO). Improved flight management in SPO requires cross-domain methods for trustworthy, robust and scalable detection and mitigation of anomalous events. An exhaustive discussion can be found in (pdf file):