method for diagnosing the damage degree of a bearing under different working conditions based on a GS-SVM

Abstract

The invention relates to a method for diagnosing the damage degree of a bearing under different working conditions based on a GS-SVM. The method comprises the following steps: S1, acquiring vibrationacceleration signals of the bearing under different working conditions; S2, setting parameters of a VMD algorithm; S3, calculating a time domain index and a frequency domain index of the obtained vibration acceleration signal, carrying out VMD decomposition on the obtained vibration acceleration signal, and calculating a sample entropy based on a decomposition result; S4, forming a feature vectoraccording to the obtained time domain index, frequency domain index and component sample entropy of the vibration acceleration signal, and performing normalization; S5, optimizing the penalty coefficient C and the radial basis kernel function parameter g of the support vector machine by adopting a grid search method, and inputting the training set into the support vector machine for training; AndS6, inputting the test set into the trained support vector machine, and judging the damage degree of the faulted bearing. According to the method, the optimal SVM can be constructed, and the diagnosis of the damage degree of the bearing is more accurate.

Description

technical field [0001] The invention relates to the field of intelligent diagnosis of rotating machinery faults, in particular to a GS-SVM-based method for diagnosing bearing damage degrees under different working conditions. Background technique [0002] As an indispensable part of the transmission system, the bearing's running status will directly affect the working condition of the whole equipment. Therefore, the condition monitoring and fault diagnosis of bearings have always attracted much attention. Timely detection of bearing fault types and corresponding treatment measures according to the degree of damage can effectively avoid the occurrence of cascading faults, thereby reducing equipment maintenance costs and avoiding major dangerous accidents. [0003] When the bearing fails, the signal processing method is commonly used for analysis, and then the Hilbert transform is used for envelope demodulation analysis. However, when the severity of the same fault is differ...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the purpose of the present invention is to provide a GS-SVM-based method for diagnosing the degree of bearing damage under differ

Images