working frequency vibration diagnosis of turbine bearings based on Bayesian network
HUANG Hai-zhou1,2, JI Feng 1, YUAN Xiao-yang1, ZHU Jun 1
1. Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi'an Jiaotong University, Xi'an Shaanxi 710049;2. Hubei Electric Power Testing & Research Institute, Wuhan Hubei 430077
Abstract:Bayesian network method was studied for the vibration diagnosis of steam turbine bearings. According to practical engineering experience,a nature Bayesian network on working frequency vibration diagnosis were built, in which diagnostic information such as vibration frequency spectrum, phase, and operating conditions were all considered.The reasoning computation was completed by adopting LabVIEW platform.The diagnosis results were verified by serveral real cases.It shows the method in this paper can be used to diagnose single and combined bearing vibration failures effectively.