Bearing running state recognition based on non-extensive wavelet feature scale entropy and support vector machine
Bearing running state recognition based on non-extensive wavelet feature scale entropy and support vector machine
复制标题
基于非广延小波特征尺度熵和支持向量机的轴承运行状态识别
DOI：
10.1016/j.measurement.2013.07.011
复制
发表时间：
2013-12-01
期刊：
影响因子：
5.6
通讯作者：
Chen, Renxiang
中科院分区：
文献类型：
--
作者：
Dong, Shaojiang;Tang, Baoping;Chen, Renxiang
为了有效识别轴承运行状态，提出了一种基于非扩展小波特征尺度熵和Morlet小波核支持向量机的轴承运行状态识别方法。首先对采集到的振动信号进行小波分解，得到相应的小波系数;然后，在非广延熵与小波系数相结合的基础上，利用小波特征尺度熵进行特征提取。然而，提取的特征仍然是高维的，仍然存在过多的冗余信息。为此，引入流形学习算法局部保持投影（LPP）来提取特征并进行降维。将提取的特征量输入多小波支持向量机中进行训练，构建轴承运行状态识别模型，实现轴承运行状态的识别。对试验和实际故障案例进行了分析。实验结果验证了该算法的有效性。(C)2013爱思唯尔有限公司保留所有权利。
In order to effectively recognize the bearing running state, a new method based on non-extensive wavelet feature scale entropy and the Morlet wavelet kernel support vector machine (MWSVM) was proposed. Firstly, the gathered vibration signals were decomposed by the wavelet to obtain the corresponding wavelet coefficients. Then, based on the integration of non-extensive entropy and the coefficients, the features were extracted by the wavelet feature scale entropy. However, the extracted features remained high-dimensional and excessive redundant information still existed. Therefore, the manifold learning algorithm locality preserving projection (LPP) was introduced to extract the characteristic features and to reduce the dimension. The extracted characteristic features were inputted into the MWSVM to train and construct the running state identification model; the bearing running state identification was thereby realized. Cases of test and actual fault were analyzed. The results validate the effectiveness of the proposed algorithm. (C) 2013 Elsevier Ltd. All rights reserved.