Locomotive motor bearing automatic diagnostic method based on vibration acceleration signal

Abstract

The invention discloses a locomotive motor bearing automatic diagnostic method based on a vibration acceleration signal, comprising the steps of: acquiring a vibration acceleration signal and a speed key phase signal of a motor bearing; performing order tracking and constant-angle incremental sampling, and converting the vibration acceleration signal into an angular-domain vibration acceleration signal; calculating an FFT spectrum and an EEVS enhanced envelope spectrum; setting effective frequency bands in the FFT spectrum and the EEVS enhanced envelope spectrum according to a bearing fault frequency; calculating the fault probability of each component of the bearing according to the band energy in the FFT spectrum and the EEVS enhanced envelope spectrum; setting weights and calculating the weighted probability of each component of the bearing; comparing a preset fault reference probability with the weighted probability of the current bearing so as to automatically determine a fault type and representing the severity of the fault by the weighted probability.

Description

technical field [0001] The disclosure belongs to the field of signal processing analysis and fault diagnosis, and in particular relates to an automatic diagnosis method for locomotive motor bearings based on vibration acceleration signals. Background technique [0002] Motor bearings are fault-prone parts of railway locomotives, which seriously affect the safety of locomotive operation. Accurate and automatic fault diagnosis can significantly reduce the troubleshooting workload of motor design and locomotive maintenance departments. At present, the vibration acceleration signal has been widely used in the fault diagnosis of locomotive motor bearings. By collecting the vibration acceleration signal, not only the fault degree can be warned but also the fault location can be realized. Among them, the fault degree early warning indicators mainly include: peak-to-peak value, mean square amplitude, and kurtosis value; fault location methods mainly include: FFT spectrum analysis me...

AI Technical Summary

Problems solved by technology

The above alarm indicators are easily disturbed by noise and are not sensitive to faults, causing serious problems of misdiagnosis and missed diagnosis; the above fault location method needs to rely on professionals to interpret fault results, which is very dependent on personal experience, resulting in huge labor costs

In addition, with the development of artificial intelligence, although there are some automatic algorithms for motor bearing fault diagnosis, such as K-means clustering, knowledge vector machine SVM, convolutional neural network CNN and more complex deep networks, these methods require A large amount of data, and the results are unstable and lack of interpretability, still facing great difficulties in engineering applications

Images