Prognostic and Health Management System for Hydraulic Servoactuators for Helicopters Main and Tail Rotor

Abstract

The research herein presented continues an initial work on this area performed at Politecnico di Torino in the past years and moves forward in the definition of an effective PHM system for Electro-Hydraulic Servo Actuators (EHSA). PHM of EHSAs is an area only little addressed, but of great interest for the aerospace industry and the air fleet operators. The PHM algorithm consists of three subroutines: the first subroutine extracts a set of relevant features from the data acquired by the sensors during a pre or post flight set of commands and mitigate their dependencies with environmental condition. Fault identification is then performed using mathematical data-driven techniques, three methods are presented: Nominal bands, Percentual error and Euclidean distance. Classification of a single and multiple degradations is performed by the second subroutine with the aid of two dual layer Neural Networks. Finally, the remaining useful life (RUL) is estimated by the third subroutine using a particle filter framework, where the feature evolution model is estimated online. Electro-hydraulic Servo-valves (EHSV) faults are widely addressed with the aid of a nonlinear model and the performance of the PHM algorithm is assessed using relevant metrics.