Abstract:Aiming at complex features in rotor system running process, such as non-linearity, coupling, un-steady abrupt states etc., a new method based on information entropy feature extracting algorithm is proposed here to combine rotor system power analysis and parameter recognition method. Information entropy feature and change rule of respond parameters in typical rotor fault states are analyzed, such as crack, rub-impact, crack and rub-impact coupling etc., and a wavelet neural network model is established which can realize the recognition and diagnosis of different fault states. The validity of the proposed method is demonstrated by theoretical analyzing and testing experiment of the rotor system.
谢平;杜义浩. 基于信息熵的转子动力特征分析与诊断方法研究[J]. , 2009, 28(2): 77-81.
Xie ping;Du yihao. STUDY ON ROTOR DYNAMIC FEATURE ANALYSIS AND DIAGNOSIS METHOD BASED ON INFORMATION ENTROPY. , 2009, 28(2): 77-81.