学术文献库

Prognostics and Health Management (PHM) are emerging approaches to product life cycle that will maintain system safety and improve reliability, while reducing operating and maintenance costs. This is particularly relevant for aerospace systems, where high levels of integrity and high performances are required at the same time. We propose a novel strategy for the nearly real-time Fault Detection and Identification (FDI) of a dynamical assembly, and for the estimation of Remaining Useful Life (RUL) of the system. The availability of a timely estimate of the health status of the system will allow for an informed adaptive planning of maintenance and a dynamical reconfiguration of the mission profile, reducing operating costs and improving reliability. This work addresses the three phases of the prognostic flow - namely (1) signal acquisition, (2) Fault Detection and Identification, and (3) Remaining Useful Life estimation - and introduces a computationally efficient procedure suitable for real-time, on-board execution. To achieve this goal, we propose to combine information from physical models of different fidelity with machine learning techniques to obtain efficient representations (surrogate models) suitable for nearly real-time applications. Additionally, we propose an importance sampling strategy and a novel approach to model damage propagation for dynamical systems. The methodology is assessed for the FDI and RUL estimation of an aircraft electromechanical actuator (EMA) for secondary flight controls. The results show that the proposed method allows for a high precision in the evaluation of the system RUL, while outperforming common model-based techniques in terms of computational time.