基于IRP和TD2DPCA的轴承故障诊断方法

发布时间：2019-01-04 22:29

【摘要】：针对轴承振动信号的非平稳特征和现实中难以提取故障参数的情况,提出了一种基于图像的轴承故障诊断方法即基于递归灰度图(Improved Recurrence Plots,IRP)和双向二维主成分分析(Two directional,Two dimensional Principal Component Analysis,TD2DPCA)的轴承故障诊断法。该方法对递归图(Recurrence Plots,RP)中阈值选取的问题进行了优化,提出了IRP算法,对采集到的轴承振动信号进行IRP分析,生成递归灰度图;然后用TD2DPCA对生成的递归灰度图进行特征参数提取,得到系数编码矩阵;最后采用分类器对上述编码矩阵直接进行模式识别,以实现轴承故障的自动化诊断。将该方法应用在轴承4种典型工况的故障诊断实例中,识别率高达99.8%,结果表明:基于IRP和TD2DPCA的轴承故障诊断方法能够自适应的对轴承进行故障诊断,具有故障识别精度高、噪声鲁棒性好等优点,为轴承振动诊断探索了一条新途径。
[Abstract]:In view of the non-stationary feature of bearing vibration signal and the fact that it is difficult to extract fault parameters in reality, a method of bearing fault diagnosis based on image is proposed, which is based on recursive grayscale graph (Improved Recurrence Plots,IRP) and bidirectional two-dimensional principal component analysis (Two directional,). Two dimensional Principal Component Analysis,TD2DPCA) for bearing fault diagnosis. The method optimizes the threshold selection in recursive graph (Recurrence Plots,RP), and proposes a IRP algorithm, which is used to analyze the vibration signal of bearing by IRP and generate the recursive gray scale image. Then TD2DPCA is used to extract the feature parameters of the generated recursive gray image, and the coefficient coding matrix is obtained. Finally, the classifier is used to directly recognize the above coding matrix, so as to realize the automatic diagnosis of bearing fault. The method is applied to four typical cases of bearing fault diagnosis, and the recognition rate is as high as 99.8. The results show that the bearing fault diagnosis method based on IRP and TD2DPCA can self-adaptively diagnose the bearing fault. It has the advantages of high fault identification accuracy and good noise robustness, which provides a new way for bearing vibration diagnosis.
【作者单位】：火箭军工程大学理学院;火箭军工程大学五系;
【基金】：国家自然科学基金(51405498) 陕西省自然科学基金(2013JQ8023) 中国博士后基金(2015M582642)
【分类号】：TH133.3

【相似文献】