High speed train wheel set bearing fault diagnosis method based on MEEMD permutation entropy

Abstract

The invention provides a high speed train wheel set bearing fault diagnosis method based on MEEMD permutation entropy for the disadvantages of EMD and EEMD. The high speed train wheel set bearing fault diagnosis method based on the MEEMD permutation entropy comprises the following steps in turn: signal acquisition; filtering and denoising of the original vibration signal; MEEMD decomposition; permutation entropy feature extraction; dividing the high-dimensional feature vectors into two groups; model training; and diagnosis result. In the feature extraction link, the signal features are reflected on multiple dimensions by introducing the MEEMD, and the relative single fault mode identification rate is obviously enhanced in comparison with EMD permutation entropy feature identification rate.The data required for the analysis method based on the MEEMD permutation entropy are short, and the anti-noise and anti-interference capacity is high so that the method can be effectively applied tohigh speed train wheel set bearing fault analysis.

Description

technical field [0001] The invention relates to the field of train safety diagnosis, in particular to a high-speed train wheelset bearing fault diagnosis method based on MEEMD permutation entropy. Background technique [0002] With the vigorous development of high-speed rail, the coverage of the railway network continues to expand, and more and more high-speed trains are put into operation. How to ensure the safe operation of trains has become the focus of research by experts and scholars. As a key component of the running part of the train, the wheel pair bearing functions to bear the vertical dead weight and load capacity of the train, as well as the unique lateral unsteady force between the wheel and rail of the train, which has a crucial impact on the safety of the train. As the speed of the vehicle increases, the operating mileage increases, and the dynamic load between the wheel and rail increases, which makes the operating conditions of the wheel set bearing worse, wh...

AI Technical Summary

Problems solved by technology

[0003] Empirical Mode Decomposition (EMD) is a signal analysis method with adaptive ability, especially suitable for the analysis process of nonlinear and non-stationary signals. The phenomenon of modal aliasing is generated, which makes the envelope spectrum of Intrinsic Mode Functions (IMFs) obtained by EMD decomposition messy, and it is difficult to identify the fault frequency that reflects the fault characteristics of the bearing. Fault severity assessment poses certain difficulties

[0004] The emergence of Ensemble Empirical Mode Decomposition (EEMD for short) has solved the above problems very well, but the EEMD method also has some defects. First, if the amplitude of the white noise added by EEMD is small, its decomposition cannot To suppress modal aliasing in the signal, if the amplitude of white noise added is large, it will lead to a substantial increase in the calculation of the lumped average, and it will also make it difficult to decompose the high-frequency components in the signal, and the decomposition result will also contain a large number of The residual white noise of

Second, the result obtained by decomposing the signal using the EEMD method may not be the standard IMF component, and there may even be a problem of mode splitting, that is, the same physical process is decomposed into two or more IMF components

Images