Gearbox fault diagnosis method and system

Abstract

The invention discloses a gearbox fault diagnosis method and system. The method comprises the steps of acquiring a horizontal vibration signal and a vertical vibration signal of a gearbox shaft through an acceleration sensor arranged on a wind driven generator; extracting feature data of the horizontal vibration signal and the vertical vibration signal of the gearbox shaft; inputting the extractedfeature data into a deep convolutional neural network module to obtain a fault diagnosis result, wherein the deep convolutional neural network module is a fault diagnosis model established by learning in advance according to horizontal and vertical vibration signal feature data of different fault gearbox shafts of the gearbox, the feature data extraction of the horizontal vibration signal and thevertical vibration signal of the gearbox shaft comprises multi-scale time domain feature extraction and deep noise reduction feature extraction. According to the invention, the fault diagnosis accuracy and automation level of the wind driven generator gearbox are improved, the working condition of the wind driven generator gearbox can be monitored in real time, and the labor intensity of the personnel is reduced.

Description

technical field [0001] The invention relates to a gear box fault diagnosis method and system, in particular to a gear box fault diagnosis method and system based on a multi-feature fusion convolutional neural network. Background technique [0002] The gearbox plays an important role in realizing the functions of transmission, speed change and speed regulation in the wind turbine. Especially with the development of wind power technology, in order to better realize the conversion of wind energy to mechanical energy and then to electrical energy, the gearbox is also moving towards The development in the direction of complexity and precision leads to complex vibration signals generated at fault points, and the difficulty of fault diagnosis increases. The traditional fault judgment method generally first uses feature extraction, such as time-frequency analysis, to analyze the time-frequency characteristics of vibration signals, and then extracts features through Fourier transform...

AI Technical Summary

Problems solved by technology

[0002] The gearbox plays an important role in realizing transmission, speed change, speed regulation and other functions in the wind turbine. Especially with the development of wind power technology, in order to better realize the conversion of wind energy to mechanical energy and then to electrical energy, the gearbox is also moving towards The development in the direction of complexity and precision leads to complex vibration signals generated at fault points and increases the difficulty of fault diagnosis

The traditional fault judgment method generally first uses feature extraction, such as time-frequency analysis, to analyze the time-frequency characteristics of vibration signals, and then extracts features through Fourier transform, wavelet transform, etc., and then through expert systems and support vector machines. The traditional method has strong theoretical support, but in the process of dealing with nonlinear and non-stationary vibration signals, it is often impossible to dig deep into the deep information, resulting in misjudgment of faults, resulting in unnecessary economic loss

Images