Locomotive traction motor bearing degradation monitoring method

Abstract

The invention discloses a locomotive traction motor bearing degradation monitoring method. The locomotive traction motor bearing degradation monitoring method comprises the steps thata motor bearing is measured to obtain full-life time domain vibration signal u(i); multiple time domain features, multiple frequency domain features, and multiple time-frequency domain multi-dimensional features are extracted based on the full-life time domain vibration signal u(i) to form a high-dimensional feature set, and normalization processing is conducted; from the three aspects of normal operation period,early failure, and failure development period, 10 features of each of three types are optimally selected for the high-dimensional feature set, an autoencoder network is used for de-redundancy processing correspondingly to obtain three features ofx<1>, x<2>, and x<3>, then the Mahalanobis distance formula is used for calculating the distance between samples to obtain the Mahalanobis distance d<ij>between each sample, similarity coefficient alpha<ij> and similarity coefficient mean value M are calculated; an adaptive neighborhood K is initially constructed and corrected, the corrected K is subjected to LLE fusion indexconstruction, a fusion index Z is obtained, processed, and exponentially fitted, exponential fit parameters are calculated, and the final fusion index is obtained; and thefinal fusion index is used for determiningdivision threshold values of four degradation stagesof the normal operation period, the early failure period, the failure development period, and a failure period.

Description

technical field [0001] The invention belongs to the technical field of signal processing analysis and fault diagnosis, in particular to a method for monitoring degradation of a traction motor bearing of a locomotive. Background technique [0002] The traction motor is suspended on the locomotive bogie and used as the power output device to pull the locomotive forward, which makes the traction motor bearing the core component of the transmission system. Therefore, the normal operation of the traction motor bearing is the key to ensure the safe operation of the locomotive, and its requirements are extremely high. Harsh. [0003] Locomotives often operate in complex, harsh, and changeable environments, which makes it difficult to monitor the operation of locomotive traction motor bearings. The manufacturers involved in the development of locomotive traction motor bearing monitoring systems are mainly companies such as Tangzhi Technology. [0004] At present, for the monitoring...

AI Technical Summary

Problems solved by technology

[0005] Relying on the monitoring of the shaft temperature trend, the ambient temperature and operating conditions in actual operation are changeable, these factors have a great adverse effect on the shaft temperature, and the reliability is not high only relying on the shaft temperature monitoring;

[0006] Relying on the real-time fault analysis of resonance demodulation, in the actual operation, the vibration of the cabin is often large, and the selection of the bandwidth of the resonance demodulation passband and other factors have a negative impact on the accuracy of the monitoring method

[0007] Tangzhi Technology’s rolling stock running part bearing cage failure pre-alarm method extracts individual features from time-domain shock data, time-domain vibration data and temperature data, and extracts a relevant index for each type of data, and analyzes its trend. Although the alarm or early warning combines the data sources of shock, vibration, and temperature, in the feature extraction of certain aspects of data, especially in the analysis of vibration data, the extracted features are single, and it is difficult to reflect the vibration data from many aspects. Information on the state of bearing degradation

[0008] Chengdu Yunda’s fault monitoring method for bogie rotating parts based on dynamic alarm threshold is based on the vibration and shock data collected by the vibration shock sensor. However, in actual locomotive operation, the vibration of the car body is often large, which has great effect on this type of monitoring. Major adverse effects

[0009] The above-mentioned means of traction motor bearing monitoring is mainly based on the analysis of shaft temperature and vibration data. The reliability and accuracy of the method used are relatively low, especially in complex environments, and the early failure and degradation status of traction motor bearings cannot be reliably and accurately detected. Effective and timely monitoring, especially in the case of changing working conditions and changing thresholds, the reliability and accuracy of monitoring will be greatly reduced

With the current incomplete monitoring system, it can only rely on planned maintenance, which in turn leads to high maintenance costs and low operating efficiency of locomotives

Images