How to extract forecast feature and distinguish degeneration status is the key problem in fault forecasting and it will influence its reliability. Combining mathematical morphology and information entropy, a method for motor bearing forecast feature extraction based on multi scale morphological decomposition spectrum entropy was proposed in the paper. On this basis, estimating the degeneration status for bearing combining with gray degree of association. Executing multi scale morphological decomposition for bearing vibration signal on different damage degree, computing its complexity indicator in different scale domain, power spectral entropy and singular spectral entropy. Take the two indicators as forecasting character vector. On this basis, standard degeneration mode matrix was obtained, processing grey relational analysis between sample vector and standard mode, distinguish the degenerate status according the value of grey relevancy. The effectiveness of this process on motor bearing degeneration status identification was verified via emulation and living example.
王 冰;李洪儒;许葆华. 基于多尺度形态分解谱熵的电机轴承预测特征提取及退化状态评估[J]. , 2013, 32(22): 124-128.
WANG Bing;LI Hong-ru;XU Bao-hua. Motor bearing forecast feature extracting and degradation status identification based on multi scale morphological decomposition spectrum entropy. , 2013, 32(22): 124-128.