基于IRP和TD2DPCA的轴承故障诊断方法

Roller bearing fault diagnosis by using IRP and TD2DPCA

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。

The vibration signals of bearings are usually non-stationary and it is difficult to extract the fault parameters in reality. A fault diagnosis method was proposed based on the Improved Recurrence Plots（ IRP） and Two directional Two dimensional Principal Component Analysis（ TD2 DPCA）. For selecting and optimizing the Recurrence Plots（ RP） threshold,the IRP was applied in bearing vibration acceleration signals to obtain IRP images. On this basis,in order to get parameters code matrixes,the TD-2 DPCA was used to process the bearing IRP images. A classifier was then used to the code matrixes for pattern recognition so as to realize the automatic diagnosis of bearing IRP images. The proposed method has been used in four kinds of bearing vibration signals and the fault diagnosis accuracy is up to 100%.The results show that： the roller bearing fault diagnosis method using the IRP and TD2 DPCA has the ability of adaptive bearing fault diagnosis,and is of good recognition accuracy and noise robustness,which explores a new way for the bearing vibration diagnosis.