Bearing fault detection method for unbalanced data SVM (support vector machine)

Abstract

The invention aims at providing a bearing fault detection method for an unbalanced data SVM (support vector machine), and the method comprises the following steps of: collecting a vibration signal; determining a time interval of embedding dimension and delay; reconfiguring a normal sample phase space; determining the quantity of samples required to be deleted and increased; respectively utilizingan ODR (optimization of decreasing reduction) algorithm and a BSNOTE (border synthetic minority over-sample technique) algorithm to delete the normal samples and increase artificial fault samples; training an SVM detector; adjusting the specific value between the quantity of the normal samples required to be deleted and the difference value between the normal sample quantity and the fault sample quantity; and then putting into the SVM detector for training until the detected performance index reaches 0.6; inputting bearing data samples to be tested in the SVM detector to realize rolling bearing fault detection. The method can be used for improving the data sample sampling, thus, the method has strong capability of removing redundant information and noise in the normal state sample, and further can be used for improving the detection performance of the unbalanced data SVM bearing fault detector.

Description

technical field [0001] The invention relates to a detection method for a bearing fault. Background technique [0002] In the industrial field, the impact of rolling bearings on the overall mechanical equipment is crucial. Real-time monitoring of the working status of rolling bearings during mechanical operation can effectively ensure the safety of the overall mechanical equipment operation. [0003] At present, the most commonly used method for bearing fault detection is the neural network method, but the neural network method is prone to problems such as dimensionality disaster and local extremum, and the detection effect is often not very ideal. Support vector machine (support vector machine: SVM) is a new learning method based on statistical learning theory and structural risk minimization. Compared with traditional intelligent learning methods, SVM can better solve problems such as disaster of dimensionality, small sample learning, nonlinearity and local extremum, espec...

AI Technical Summary

Problems solved by technology

There are several ways to achieve data balance: The first method is the fault sample oversampling method, which is currently the most used method, but this method increases the number of fault samples and is prone to generate a large amount of repeated information, and it is not easy to generate a large number of duplicate information in normal samples. There is a large amount of redundant information and noise in the SVM detector, which will have a negative impact on the SVM detector; the second method is the normal sample undersampling method. The currently commonly used undersampling method is the random undersampling method, but this method reduces the number of normal samples. At the same time, there is a large randomness, it is easy to lose useful information in normal samples, and the removal of redundant information and noise is not thorough

Images