Gearbox gear fault diagnosis method

Abstract

The invention discloses a gearbox gear fault diagnosis method, and belongs to the related technical field of gear fault diagnosis methods. The invention provides the gearbox gear fault diagnosis method based on the combination of EEMD (ensemble empirical mode decomposition), sample entropy and an extreme learning machine by considering other factors such as non-stationarity, fault type and fault positioning diagnosis of a gearbox gear vibration signal. The method comprises the following steps of: decomposing an original vibration signal into a plurality of intrinsic mode function parts by adopting an EEMD decomposition method; and selecting a main part according to a principle that a correlation coefficient between the part and an original vibration signal is greater than 0.1, calculating sample entropies of the main part to form a feature vector, and importing the obtained feature vector into an extreme learning machine to carry out fault type classification recognition. Meanwhile, through a frequency domain graph obtained by carrying out fast Fourier transform on an original signal, observing and recording a fault frequency and a side frequency thereof to obtain fault gear positioning. And finally, combining the gear type with fault positioning to obtain a gear fault diagnosis comprehensive conclusion.

Description

technical field [0001] The invention belongs to the technical field related to gear fault diagnosis methods, and in particular relates to a fault diagnosis method for rotating mechanical gears. Background technique [0002] As a key component for connecting and transmitting power in mechanical equipment, gearboxes are widely used in large and complex mechanical equipment such as wind turbines, helicopters, automobiles, agricultural machinery, and metallurgical machinery. However, affected by working conditions such as harsh working environment, strong load, high speed, and long-term continuous operation, some typical components in the gearbox, such as gears and rolling bearings, are prone to various types of failures, which in turn affect the overall mechanical system The safety and reliability of operation will lead to the degradation of product or service quality, and cause huge economic losses and casualties. Therefore, it is of great significance to carry out research o...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the problem of difficult fault diagnosis of existing gearbox gears, the present invention provides a gearbox gear fault diagnosis method

Images