Rolling bearing fault diagnosis method based on composite multi-scale permutation entropies

Abstract

The invention discloses a rolling bearing fault diagnosis method based on composite multi-scale permutation entropies, and belongs to the technical field of fault diagnosis. The method comprises the following steps: measuring a vibration signal of a faulty object; extracting composite multi-scale permutation entropies from the vibration signal; reducing the dimension of the composite multi-scale permutation entropies with use of a Laplacian score; taking the first multiple composite multi-scale permutation entropies with low scores after dimension reduction as fault feature vectors and dividing the fault feature vectors into multiple training samples and multiple test samples; inputting the multiple training samples into a multi-fault classifier established based on a support vector machine to perform learning so as to classify the test samples; and identifying the working mode and the fault type of the faulty object according to the classifying result. According to the fault diagnosis method disclosed by the invention, feature extraction is highly innovative, and the degree of identification is high in the process of fault mode identification.

Description

technical field [0001] The present invention relates to the technical field of rolling bearing fault diagnosis, in particular to a feature selection based on composite multi-scale permutation entropy (Composite multi-scale permutation entropy, CMPE), Laplacian score (Laplacian score, LS) and support vector machine (Support vector machine). vector machine (SVM) rolling bearing fault diagnosis method. Background technique [0002] Due to the complexity of the mechanical system, friction, vibration and load will inevitably occur during the operation of the equipment, and the vibration signal of the system often exhibits nonlinear behavior. Therefore, the nonlinear analysis method has more unique advantages than the linear analysis method in extracting fault features, and can extract fault feature information hidden in vibration signals that cannot be extracted by other methods. In recent years, many nonlinear analysis methods, such as fractal, approximate entropy, sample entro...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the problem that the permutation entropy value in the multi-scale permutation entropy has a large deviation with the increase of the scale factor, and at the same time to improve the efficiency of fault diagnosis and reduce the influence of human experience factors on the diagnosis result, the present invention provides a method based on composite multi-scale permutation entropy. Rolling bearing fault diagnosis method based on scale permutation entropy, Laplacian score and support vector machine; the present invention can better extract the nonlinear features of vibration signals in the feature extraction process, and also has higher accuracy in the pattern recognition process Fault identification

Images