A Fault Diagnosis Model for Coaxial-Rotor Unit Using Bidirectional Gate Recurrent Unit and Highway Network

Abstract

A turbojet engine is the most significant part of an Internal Combustion Engine (ICE) for Hybrid Electric Vehicles. Specifically, the coaxial-rotor unit is the key component, whose performance largely affects the working efficiency. Thereby, the fault diagnosis methods for coaxial-rotor units is a main focus. In line with our test results, the bearing circlip is the most vulnerable element while rotating. Moreover, the low-speed rotating fault diagnosis is even challenging for current methods. Since the fault diagnosis on the bearing circlip of coaxial-rotor units is absent, this paper establishes a test rig on a running coaxial-rotor unit under different working conditions. The three-directional vibration signals are collected and analyzed to demonstrate the working states. On the task of bearing circlip failure classification, a deep-learning-based model using the Bidirectional Gate Recurrent Unit and the Highway Network is developed, which is capable of capturing hidden features and removing unrelated information. For working performance evaluation, experiments on the data of different rotating speeds are carried out. Among all the fault diagnosis methods, our model is the best approach and achieves an average accuracy of 99.4%. The encouraging results reveal that the proposed model is effective in both the high-speed and low-speed fault diagnosis of bearing circlip malfunction.