Diagnosis and Prognosis of AH64D Tail Rotor Gearbox Bearing Degradation

Abstract

Most research work has been performed within laboratory environments with seeded defects or accelerated testing and there is little published in the public domain on in-service defects with operational helicopter HUMS data. This study focuses on the actual service experience gathered from HUMS equipped AH64D helicopter belonging to the Republic of Singapore Air Force. Operational HUMS data from three helicopters with similar in-service defects found on their Tail Rotor Gearbox are analyzed and correlated with tear-down inspection findings. From analysis of the HUMS vibration spectrum, fault patterns which show the progression from localised to generalised damage in the bearing can be observed consistently across the defective gearboxes. The observed fault patterns are extracted as Condition Indicators (CI) to diagnose the different stages of bearing degradation within the gearbox. As the defects between the gearboxes are similar, the historical trends of the extracted CIs are used to developed prognostic model using parameter estimation approach.

Detection and Classification of Aircraft Fixation Elements during Manufacturing Processes Using a Convolutional Neural Network

“…In the aerospace industry, artificial vision techniques, combined with machine learning, have been used to identify defects and problems associated with the wear of engine components [38], assess corrosion in metallic systems [39], measure large panels by 3D systems [8] and inspect automated wheels [4]. However, they have not been employed to classify fastening elements of large structures with structural responsibility because of the technological difficulties entailing their practical application to manufacturing processes in an industrial environment.…”

Diagnosis for gear tooth surface damage by empirical mode decomposition in cyclic fatigue test

“…Consequently, failure diagnosis especially early detection of the gear damage is crucial to prevent the mechanical system from malfunction. Researchers have developed many techniques to detect gear faults using vibration signal (Koide, et al, 2013, Hood, et al, 2013, Lim and Mba, 2013, acoustic emission (Al-Balushi, and Samanta, 2002), tooth root strain (Board, 2003), laser scattering (Tanaka, et al, 2011) and so on. Especially, analyzing the vibration signal of gear motion is one of the most effective methods applied in the detection of gear failures.…”