Real-time Fault Detection and Prognostics for Aircraft Actuation Systems

Prognostics and Health Management are emerging approaches to product life cycle that will improve the system safety and reliability while reducing operating and maintenance costs. We propose a data driven strategy for the nearly real-time Fault Detection and Isolation (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 allows an informed adaptive planning of maintenance and a dynamical reconfiguration of the mission profile, reducing operating costs and improving safety. In this work, we address the three phases of signal acquisition, FDI and RUL estimation which characterize the prognostic flow. To achieve a computationally light process, suitable for real time execution, we leverage strategies for signal processing and combine information from physical models of different fidelity with machine learning techniques to obtain surrogate models. Additionally, we propose a scaled Latin Hypercube sampling strategy and a novel approach to model damage propagation for dynamical systems. The methodology is assessed on a test case in the form of the FDI and RUL estimation of an aircraft electromechanical actuator (EMA) for secondary flight controls. The results show that our strategy allows for a high precision in the evaluation of the system RUL, while outperforming common model-based techniques in terms of computational time.