Oil film vortex motion and friction concurrent fault analysis method and analysis system

Abstract

The invention belongs to the technical field of oil film vortex motion and friction concurrent fault diagnosis, and discloses an oil film vortex motion and friction concurrent fault analysis method and analysis system. The method includes extracting a machine fault vibration signal by using double probes; preprocessing the acquired data, and extracting nine dimensionless features of a machine fault vibration signal; training by utilizing the extracted feature vectors and using logistic regression classification; and predicting the unknown label vibration signal to obtain whether the signal hasa fault or not and the type of the fault. According to the invention, the problem that feature extraction is difficult in the gear fault prediction process can be solved, the extracted features are sufficient and comprehensive, the gear fault prediction problem can be well solved, and the influence of noise on the result can be effectively reduced. According to the invention, oil film vortex motion faults and friction faults can be discovered and diagnosed.

Description

technical field [0001] The invention belongs to the technical field of oil film whirl and friction concurrent fault diagnosis, in particular to an oil film whirl and friction concurrent fault analysis method and analysis system, in particular to an oil film whirl based on nine dimensionless feature extraction and logistic regression classification Concurrent failure analysis methods with friction. Background technique [0002] At present, the structure of large-scale equipment is complex, the functions are perfect, and the internal parts of the equipment are closely connected, which makes the production process high-speed and large-scale, which also makes the failure of large-scale equipment cause huge losses, which also increases It reduces the difficulty of fault diagnosis for mainframe equipment. When an object and another object move along the tangent direction of the contact surface or have a tendency to move relative to each other, there is a force between the contact...

AI Technical Summary

Problems solved by technology

[0005] (1) In the prior art, the methods for concurrent fault detection of oil film whirl and friction can only extract a limited number of local pulses, and it is still an iterative non-optimal solution, which is not immune in a strong noise environment. prone to misdiagnosis

[0006] (2) The current commonly used methods have problems such as feature extraction difficulties and incomplete feature extraction.

Images