基于复合多尺度模糊熵的滚动轴承故障诊断方法?

为了精确地提取滚动轴承振动信号非线性故障特征，针对多尺度熵（Multi-scale entropy，MSE）中粗粒化方式的不足，提出一种新的衡量时间序列自相似性和复杂性的方法--复合多尺度模糊熵（Composite multi-scale Fuzzy entropy，CMFE）。与MSE相比，CMFE综合同一尺度下多个粗粒化序列的信息，随着尺度因子的增加，熵值变化更加稳定，一致性更好。在此基础上，结合Fisher得分特征选择和支持向量机模式分类，提出了一种新的滚动轴承智能故障诊断方法。将提出的方法应用于滚动轴承实验数据分析，通过对比结果验证了所提出方法的有效性和优越性。

Composite Multi-scale Fuzzy Entropy based Rolling Bearing Fault diagnosis method

To precisely extract the linear fault features from rolling bearing vibration signal, a novel method for measuring the self-similarity and complexity of time series termed composite multi-scale fuzzy entropy (CMFE) is proposed, aiming at the coarse-grained way of multi-scale entropy (MSE). Compared with MSE, CMFE combines the information of multiple coarse-grained sequences and obtains more stable values with a better consistency. Based on the CMFE, Fisher score for feature selection and support vector machines, a newly intelligent rolling bearing fault diagnosis method is proposed. The proposed method is applied to analyze the rolling bearing experimental data by comparisons and the results have verified its effectiveness and superiority.