A new comprehensive monitoring and diagnostic approach for early detection of mechanical degradation in helicopter transmission systems

Abstract

Helicopters vulnerabilities specifically lie in single-load-path critical parts that transmit the engine’s power to the rotors. A fault in even one single trans- mission’s gear component may compromise the whole helicopter, yielding high maintenance costs and safety hazards. In this work, we present an effective di- agnosis and monitoring system for the early detection of the mechanical degra- dation in such components, also capable of providing insights on the damage’s causes. The classification task is performed by an ensemble of two learners: a convolutional autoencoder and a distance&density-based unsupervised classifier that use as regressors specific Health Indexes (HIs) and flight parameters. The proposed approach employs the autoencoder reconstruction error information to infer the most probable cause of each detected fault, and enacts post-processing filtering policies that effectively reduce the number of false alarms. Extensive experimental validation witnesses the good performances and the robustness of the proposed approach.