Abstract
Misalignment fault is the main factor that affects the normal running of dual-rotor system. Quantitative identification the misalignment fault is an important way to ensure the safe and stable service of the dual-rotor system, while the identification accuracy of traditional methods is low. Aiming at the above problems, this paper proposed a dual-rotor misalignment fault quantitative identification method based on DBN and D-S evidence theory improved by mutual information measure (MIMD-S). Seven groups experiments were conducted and several vibration signals were collected. By comparing it with the traditional methods D-S, and Pignistic improved D-S (PD-S) evidence theory, the results show that the method proposed in this paper improves the accuracy of the misalignment fault quantitative identification of the dual-rotor, the identification error rate was only 0.36%.
Highlights
Dual-rotor system is the key component of modern aeroengine
To solve the problem of low recognition rate of traditional methods due to the complexity and diversity of misalignment faults, This paper studies the diagnosis method based on deep belief network (DBN) and D-S evidence theory
Aiming at the problem of low identification rate of the traditional methods for dual-rotor misalignment fault quantitative identification, a dual-rotor misalignment identification method based on DBN and MIMD-S evidence theory was proposed
Summary
Dual-rotor system is the key component of modern aeroengine. Due to manufacturing and assembling errors, bearing wear and structural deformation, the dual-rotor system is prone to various types of misalignment faults [1], including coupling parallel misalignment, coupling angle misalignment, and dual-rotor misalignment [2]. The misalignment can increase the vibration amplitude of aeroengine end even cause the structural damage of rotor system, which will threaten the safe service of aero-engine [2]. If the misalignment fault parameters (type, degree) of the dual-rotor can be accurately and timely obtained by people, and maintenance measures can be taken immediately so that the accidents caused by misalignment faults can be reduced. Scholars have done some relevant studies, Lal and Tiwari [3] identified the misalignment quantitatively by finding the relationship between the fundamental frequency amplitude of vibration signal and the misalignment of rotor system. Rybczynski [4] proposed a method to estimate the misalignment
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
