The planetary gearbox is a critical mechanism in helicopter transmission systems. Tooth failures in planetary gear sets will cause great risk to helicopter operations. A gear pitting damage level estimation methodology has been devised in this paper by integrating a physical model for simulation signal generation, a three-step statistic algorithm for feature selection and damage level estimation for grey relational analysis. The proposed method was calibrated firstly with fault seeded test data and then validated with the data of other tests from a planetary gear set. The estimation results of test data coincide with the actual test records, showing the effectiveness and accuracy of the method in providing a novel way to model based methods and feature selection and weighting methods for more accurate health monitoring and condition prediction.Keywords: planetary gear sets; pitting damage; feature selection; grey relational analysis; damage level estimation.
TITRE FRANÇAIS DE L'ARTICLE (MAXIMUM DEUX LIGNES)
RÉSUMÉLe résumé français est obligatoire. Évidement, si l'article est rédigé en français, le titre principal et le résumé principal sont en français. Par contre, il ne faut pas traduire le texte « Received…Accession Number 0000 ».Mots-clés : premier mot-clé; deuxième mot-clé; troisième mot-clé.
INTRODUCTIONThe majority of mishaps in helicopters are caused by engine and drive train failures. To reduce these mechanically induced failures and excessive maintenance, it is vital to accurately identify and diagnose developing faults in the mechanical system. Planetary gear sets are common mechanical components and are widely used to transmit power and change speed and/or direction in rotary aircrafts. One of the most common causes of planetary gear sets failure is tooth defect due to excessive stress conditions. It results in progressive damage to gear teeth and ultimately leads to the complete failure of the planetary gear sets. This fault is particularly challenging as it is located deep inside the main transmission, suggesting it would be difficult to detect earlier.