The study of signature energy feature extraction method is emphasized.

侧重签名能量特征提取方法的研究。

youdao

According to the method, the energy of different frequency bands after wavelet packet decomposition constitutes the input vectors of support vector machine as feature vectors.

该方法将振动信号小波包分解后的频带能量作为特征向量，输入到由多个支持向量机构成的多故障分类器中进行故障识别和分类。

youdao

In this method, the feature factor is identified and extracted through the energy of the jamming object and differences in the undulating property, and then is classified with the help of RBF.

该方法基于干扰和目标能量和起伏特性差异确定提取特征因子，再利用RBF神经网络方法进行分类。

youdao