The ever increasing adoption of electrical power as secondary form of on-board power is\nleading to an increase in the usage of electromechanical actuators (EMAs). Thus, in order to maintain\nan acceptable level of safety and reliability, innovative prognostics and diagnostics methodologies\nare needed to prevent performance degradation and/or faults propagation. Furthermore, the use\nof effective prognostics methodologies carries several benefits, including improved maintenance\nschedule capability and relative cost decrease, better knowledge of systems health status and\nperformance estimation. In this work, a novel, real-time approach to EMAs prognostics is proposed.\nThe reconstructed back electromotive force (back-EMF), determined using a virtual sensor approach,\nis sampled and then used to train an artificial neural network (ANN) in order to evaluate the current\nsystem status and to detect possible coils partial shorts and rotor imbalances.
Loading....