Fault Diagnosis Method Based on Principal Component Analysis and Broad Learning System
Fault Diagnosis Method Based on Principal Component Analysis and Broad Learning System
复制标题
基于主成分分析和广义学习系统的故障诊断方法
DOI：
10.1109/access.2019.2929094
复制
发表时间：
2019-07
期刊：
影响因子：
3.9
通讯作者：
Wu Deng
中科院分区：
文献类型：
--
作者：
Huimin Zhao;Jianjie Zheng;Junjie Xu;Wu Deng
采用传统的特征提取方法对信号进行特征提取，构造故障特征矩阵，存在结构复杂、相关性高、冗余等问题。这将增加复杂的故障分类，严重影响故障识别的准确性和效率。为了解决这些问题，本文提出了一种基于主元分析和广义学习系统的转子系统故障诊断方法。该方法利用揭示信号本质的主成分分析对构造的特征矩阵进行降维处理，降低数据间的线性特征相关性，消除冗余属性，从而得到保留本质特征的低维特征矩阵，用于分类模型。然后，采用时间复杂度低、分类精度高的BLS作为分类模型实现故障识别，可以有效地完成转子系统的故障分类。最后，选取转子系统的实际振动数据，验证了PABSFD方法的有效性。实验结果表明，PCA方法能有效消除特征相关性，实现特征矩阵的降维; BLS方法具有更好的适应性、更快的计算速度和更高的分类精度; PABSFD方法能高效准确地获得故障诊断结果。
Traditional feature extraction methods are used to extract the features of signal to construct the fault feature matrix, which exists the complex structure, higher correlation, and redundancy. This will increase the complex fault classification and seriously affect the accuracy and efficiency of fault identification. In order to solve these problems, a new fault diagnosis (PABSFD) method based on the principal component analysis (PCA) and the broad learning system (BLS) is proposed for rotor system in this paper. In the proposed PABSFD method, the PCA with revealing the signal essence is used to reduce the dimension of the constructed feature matrix and decrease the linear feature correlation between data and eliminate the redundant attributes in order to obtain the low-dimensional feature matrix with retaining the essential features for the classification model. Then, the BLS with low time complexity and high classification accuracy is regarded as a classification model to realize the fault identification; it can efficiently accomplish the fault classification of rotor system. Finally, the actual vibration data of rotor system are selected to test and verify the effectiveness of the PABSFD method. The experimental results show that the PCA method can effectively eliminate the feature correlation and realize the dimension reduction of the feature matrix, the BLS can take on better adaptability, faster computation speed, and higher classification accuracy, and the PABSFD method can efficiently and accurately obtain the fault diagnosis results.
登录
查看更多内容
海洋环境设计参数计算阈值选择方法研究
影响因子：
3.9
作者：
Liu Guilin;Gao Zhikang;Chen Baiyu;Fu Hanliang;Jiang Song;Wang Liping;Kou Yi
通讯作者：
Kou Yi
影响因子：
3.4
作者：
L. Saidi
通讯作者：
L. Saidi
影响因子：
3.2
作者：
Z. Ren;R. Skjetne;Zhen Gao
通讯作者：
Z. Ren;R. Skjetne;Zhen Gao
影响因子：
8.4
作者：
Xin Xia;Jian-zhong Zhou;Jian Xiao;Han Xiao
通讯作者：
Xin Xia;Jian-zhong Zhou;Jian Xiao;Han Xiao
DOI：
--
发表时间：
2018
期刊：
--
影响因子：
--
作者：
Huynh Van Luong
通讯作者：
Huynh Van Luong