中国电机工程学报Issue(21)：132-137,6.
谐波窗分解样本熵与灰色关联度在转子故障识别中的应用
Harmonic Window Decomposition Sample Entropy and Grey Relation Degree in Rotor Fault Recognition
摘要
Abstract
Considering the non-stationary features of vibration signal from rotor and the difficulty to obtain enough fault samples in practice, a novel comprehensive fault recognition method was presented based on the harmonic window decomposition (HWD), sample entropy and grey relation degree. Firstly, the idea of circle statistics was introduced to improve the shortcoming of traditional morphological filter and the rank-order morphological filter was defined; then the line structure element was selected for rank-order morphological filter to denoise the original signal. Secondly, the six feature frequency bands which contain the typical fault information were extracted by harmonic window decomposition that need not decomposition; then the nonlinear dynamic parameter sample entropy was used as a feature and calculated for five rotor conditions. Finally, due to the grey relation degree has good performance in small-sample classification, these sample entropies could serve as the feature vectors, then the grey relation degree of different vibration signals was calculated to identify the fault pattern and condition. Practical results show that this method can identify rotor fault patterns effectively.关键词
谐波窗分解/灰色关联度/样本熵/顺序形态滤波/转子故障识别Key words
harmonic window decomposition (HWD)/grey relation degree/sample entropy/rank-order morphological filtering/rotor fault recognition分类
机械制造引用本文复制引用
张文斌,郭德伟,普亚松,滕瑞静,王鹏,苏艳萍..谐波窗分解样本熵与灰色关联度在转子故障识别中的应用[J].中国电机工程学报,2013,(21):132-137,6.基金项目
云南省教育厅科研基金项目(2012C197)。Scientific Research Foundation of Education Bureau of Yunnan Province (2012C197) （2012C197）
