Planetary gear box fault diagnosis method based on low-rank sparse approximation

Abstract

The invention relates to a planetary gear box fault diagnosis method based on low-rank sparse approximation. The planetary gear box fault diagnosis method based on low-rank sparse approximation comprises the steps of: acquiring output shaft angle position signals by utilizing a built-in coder at first, then, fitting and differentiating the output shaft angle position signals by taking the mean square error as a loss function, so that instantaneous angle speed signals are obtained, on the basis of the instantaneous angle speed signals, respectively performing time-domain synchronous averaging on a planet wheel, a sun wheel and a gear ring, then, performing low-rank sparse approximation on respective time-domain synchronous averaging signals, so that sparse recovery signals of the planet wheel, the sun wheel and the gear ring are obtained, furthermore, calculating each kurtosis, and judging that the signal, the kurtosis of which is greater than a kurtosis threshold value, fails. According to the planetary gear box fault diagnosis method based on low-rank sparse approximation in the invention, by utilization of the characteristics of a low-rank sparse approximation method, acquired compound signals are decoupled; normal meshing information and fault information of a planetary gear box are separated; fault characteristics are prominent; and early weak fault diagnosis of the planetary gear box is easily realized.

Description

technical field [0001] The invention relates to the technical field of planetary gearbox fault diagnosis and signal analysis, in particular to a planetary gearbox fault diagnosis method based on low-rank-sparse approximation. Background technique [0002] As an important transmission component, the planetary gearbox is widely used in major mechanical equipment such as wind turbines and helicopters due to its high load-carrying efficiency and large transmission ratio. It is of great significance to ensure the healthy and efficient operation of the equipment. However, its low-speed and heavy-load harsh working environment makes key components such as planetary gears, sun gears, and ring gears prone to serious failures such as wear, tooth root cracks, and even broken teeth, which increases the vibration of the equipment and even paralyzes the entire operating system, resulting in serious consequences. . Therefore, the fault diagnosis of planetary gearboxes, especially the diag...

AI Technical Summary

Problems solved by technology

However, due to various factors such as the complex internal structure of the planetary gearbox, variable service conditions, and long signal transmission paths, the collected signals are severely coupled and the signal-to-noise ratio is low, which brings great challenges to fault location.

[0004] Chinese patent (application number 201810932320.9) to solve the problem of serious signal coupling, adopts the combination of MED and fuzzy entropy to diagnose the fault of planetary gearbox. The maximum value is used as the termination condition of the iteration, but directly using the kurtosis as the termination condition of the iteration is easily affected by random shocks, which makes it difficult to distinguish whether the shock is caused by a fault or the source is a random shock

The Chinese patent (application number 201711122369.X) first extracts components of the signal by singular spectrum difference, then performs EEMD decomposition, and calculates the fractal dimension of each eigenmode function to obtain the fractal dimension curve, which is consistent with the normal signal Compare with a variety of different actual fault fractal curves to judge the fault location and type; but in the singular spectrum analysis, the singular values ​​themselves are sorted according to energy. If only the first N singular values ​​are selected, the fault information may be missed, resulting in Misdiagnosis, and the method is finally compared with the fractal dimension curve in many cases, requiring a lot of prior knowledge, which limits its application range

Images