Planetary gearbox health monitoring method based on modal reconstruction and bagging model

Abstract

The invention discloses a planetary gearbox fault diagnosis method based on modal reconstruction and a bagging model. The method comprises the following steps: firstly, acquiring vibration signals in x, y and z directions of a planetary gearbox by using a three-phase addition speed sensor; then, processing the vibration signal through variational mode decomposition (VMD) to obtain a decomposed intrinsic mode component so as to weaken the interference of noise on the vibration signal; reconstructing the intrinsic mode component according to the frequency variance of the intrinsic mode component of each order, and extracting an energy index; and finally, performing model training through a Bagging Tree integration algorithm to obtain an effective model for identifying the state of the planetary gearbox. According to the invention, health monitoring of the planetary gearbox can be realized under different service conditions.

Description

technical field [0001] The invention belongs to the technical field of planetary gearbox fault diagnosis, and in particular relates to a planetary gearbox fault diagnosis method based on modal reconstruction and bagging model. Background technique [0002] In recent years, the rapidly developing artificial intelligence theory has provided a powerful tool for the intelligent diagnosis of mechanical equipment, and has achieved certain results in the field of planetary gearbox fault diagnosis. Based on the application of EMD for bearing fault feature extraction, and combined with the good classification performance of SVM for pattern recognition, fault diagnosis was realized (Fu Dapeng, Zhai Yong, Yu Qingmin. Research on rolling bearing fault diagnosis based on EMD and support vector machine). [J]. Machine Tool and Hydraulics, 2017, 45(11): 184-187); someone uses the original vibration signal as input, and automatically extracts fault features from it by combining multi-layer n...

AI Technical Summary

Problems solved by technology

[0003] Although useful explorations have been made on rotating parts such as gears and bearings, on the one hand, due to the complex internal structure of the planetary gearbox, the excitation information is coupled with each other, showing obvious nonlinearity, which brings challenges to the interpretation and analysis of dynamic information; On the other hand, the harsh service conditions cause the dynamic information of the planetary gearbox to be seriously disturbed by noise, showing different statistical characteristics, and requiring higher generalization capabilities of the diagnostic model

Images