首先将非平稳的故障振动信号进行双树复小波包分解，得 到不同频带的分量；然后对每个分量求其峭度值和相关系数并进行比较；最后选取峭度值和相关系数较大的分量 进行软阈值降噪和双树复小波包重构，即可有效地消除振动信号中噪声的干扰，同时保留信号中的有效信息即实 现了故障特征信息的提取。-In view of the above situation, a new fault diagnosis method is proposed based on dual-tree complex wa

matlab求解峭度值，峰峰值，方差，均方差，协方差，裕度等统计学特征-Matlab solution of kurtosis, peak peak value, variance, variance, covariance, margin and other statistical characteristics