Direct Load Recognition to Estimate the Damper Load on the H175 Fleet

Caroline del Cistia Gallimard (1, 2) , Konstanca Nikolajevic (2) , Frederic Beroul (2) , Julien Denoulet (1) , Bertrand Granado (1) , Christophe Marsala (3)

1 SYEL - Systèmes Electroniques
2 Airbus Helicopters
3 LFI - Learning, Fuzzy and Intelligent systems

This paper presents an application of the Direct Load Recognition (DLR) methodology to estimate the main rotor damper load on customer flights. The DLR producing good results on the prototype flight test data, this paper elaborates the steps to develop a virtual sensor for estimating the loads using the customer data. The DLR methodology is based on the combination of a harmonic decomposition and the use of Machine Learn-ing algorithms. First of all, the approach consists in building and evaluating the DLR methodology on proto-type flight test data to estimate the main rotor damper loads from a set of recorded flight parameters. This development phase shows the feasibility of the DLR to estimate the damper load. Then, this paper focuses on the application of the constructed model with DLR on customer flights. From the damper load estimation, a damage is derived and summed up for each aircraft of the H175 fleet, showing that the customer flights are well below the Design Usage Spectrum. Finally, the results of the study indicate that the aircraft maintenance could be adapted on the helicopter usage.

Mots clés: Machine learning; Signal; Aeronautic; Helicopter; Virtual sensor; Condition Based Maintenance

Domaines: Intelligence artificielle [cs.AI]; Traitement du signal et de l'image [eess.SP]

Caroline del Cistia Gallimard, Konstanca Nikolajevic, Frederic Beroul, Julien Denoulet, Bertrand Granado, et al.. Direct Load Recognition to Estimate the Damper Load on the H175 Fleet. European Rotorcraft Forum, Sep 2023, Bückeburg, Germany. ⟨hal-04201718⟩