Development of a hybrid PHM system for flight control actuators fusing data analytics with physical knowledge
S. Autin, C. Boitard, N. Morizet, A. De Martin, A.-C. Bertolino, R. Guida, and G. Jacazio. In Proceedings of the European Conference of the PHM Society 2026, Vol.9, No.1, July 3rd 2026.
Abstract: It is well known that the development of PHM systems can be approached with a large variety of techniques. In general, the different prognostics techniques are classified as "data driven", or "physics model based", depending on whether the assessment of a system health status and its evolution with time is performed with an intelligent statistical analysis of present and historical data (data driven approach), or the system actual operating status derived from different sensors is compared with the expected system status in the same operating conditions (model based approach). When a large database of historical data is available, data driven techniques can be accurate and do not require a knowledge of the underlying physics as for the case of model-based techniques. On the other hand, a data driven approach detects only anticipated faults, while a physics-based model approach can also detect unanticipated faults, that never occurred in the past. Flight control actuators of aircraft in revenue service are a typical application in which a large historical database can be available from maintenance, repair and overhaul departments, still the prediction of their health status may fall short of the necessary accuracy without a model description of their physics. For this reason, Safran Actuation, a leading manufacturer of flight control actuators, is conducting an extensive R&D work, together with Politecnico di Torino and Forvis Mazars, aimed at developing an effective PHM system with specific reference to the spoiler actuators of the Airbus A320. This use case is of a particular interest due to the very large number of this type of aircraft in service, to their expected continued use in the years to come and to the number of actuators per aircraft. With reference to this use case, this paper shows how an intelligent fusion of data analytics with physical knowledge can be a multiplying factor in improving accuracy and reliability of the PHM system, with the objective of developing a technological demonstrator for its validation in the lab prior to the implementation of a prototype.
Commentaires