Planetary gear fault diagnosis method based on dual-tree complex wavelet transform-entropy feature fusion

Abstract

The invention discloses a planetary gear fault diagnosis method based on dual-tree complex wavelet transform-entropy feature fusion. The method comprises the following steps of collecting integration simulation experiment table data and acquiring a planetary gear shell original vibration signal; using dual-tree complex wavelet transform to decompose an original vibration signal and extracting a signal component of each frequency band; constructing an entropy feature extraction model from multiple angles and acquiring a high-dimension original feature; using a nucleus Fisher discriminant analysis method to carry out dimension reduction processing on an original feature set formed by a plurality of entropy features, determining a group of optimum discriminant vectors, extracting a projection of the original feature in the optimum discriminant vectors and taking as a sensitive fault feature so as to determine a fault type; verifying a necessity of describing feature information from the multiple angles and multiple spaces and validity of carrying out feature dimension reduction by using a KFDA method based on that. The method is suitable for the non-linear and non-stable planetary gear vibration signal with a high coupling feature. By using the method, the sensitive fault feature can be effectively extracted and accurate diagnosis of the planetary gear is realized.

Description

technical field [0001] The invention belongs to the technical field of planetary gear fault diagnosis, and in particular relates to a planetary gear fault diagnosis method based on dual-tree complex wavelet transform-entropy feature fusion. Background technique [0002] Planetary gears are often used in low-speed, heavy-load, high-intensity, high-pollution workplaces, and their failures have become the main factor affecting the reliable and stable operation of equipment. Since the planetary gear itself is a strongly nonlinear system, and it is disturbed by the external working environment during the working process, the failure of the planetary gear is difficult to detect, and the collected vibration signals show nonlinear, non-stationary, and strong coupling characteristics. Researching a signal processing method suitable for dealing with non-stationary vibration signals generated by planetary gear faults, and realizing accurate diagnosis of planetary gear faults are the di...

AI Technical Summary

Problems solved by technology

Among them, STFT transformation and Wigner-Ville distribution have good analysis results for stationary signals, but they are not suitable for complex non-stationary vibration signals.

EMD decomposition is an adaptive signal decomposition method, which decomposes complex non-stationary signals into simple intrinsic mode functions, but EMD decomposition has two very obvious shortcomings, namely, mode mixing and endpoint leakage.

After years of development, wavelet decomposition has been successfully applied to the field of complex non-stationary vibration signal decomposition and processing, but wavelet decomposition also has shortcomings such as frequency leakage, frequency aliasing, translation sensitivity, and less direction selection, which lead to loss of signal details. or inaccurate results, etc.

Images