Bearing fault diagnosis method based on multi-view associated feature learning

Abstract

The invention discloses a bearing fault diagnosis method based on multi-view correlation feature learning. The method is characterized in that a vibration signal and a current signal are regarded as different views, a correlation feature learning method of a gear box bearing vibration signal and a generator current feature is designed based on multi-view learning, and the method is applied to the multi-fault diagnosis of a wind power gear box bearing. The method comprises the following steps of firstly, extracting wavelet packet sub-band time domain statistical features from the vibration and current signals to obtain an initial vibration feature space and an initial current feature space, and then inputting the vibration and current feature samples into a canonical correlation learning network in pairs to carry out correlation feature learning, so that the correlation between current and vibration signal feature mapping is maximum, and the enhanced extraction of the vibration and current features is realized. According to the method, the correlation attributes in the vibration and current signals can be learned in an unsupervised mode, the common fault feature information is obtained, the comprehensive diagnosis advantage of multiple sensing signals is fully utilized, and compared with a single signal feature method, the precision and reliability of fault diagnosis are improved.

Description

technical field [0001] The invention belongs to the field of fault diagnosis, and in particular relates to a bearing fault diagnosis method based on multi-view associated feature learning. Background technique [0002] As a key component of the wind turbine transmission system, the gearbox has a complex internal structure and a harsh operating environment. It is under complex and variable alternating loads for a long time, and is prone to failure. According to statistics, 76.2% of gearbox failures are caused by bearings, of which high-speed shaft and intermediate shaft bearings account for the largest proportion. Therefore, in order to avoid huge maintenance costs and downtime loss caused by bearing failure, it is particularly important to diagnose gearbox bearing failures in a timely and accurate manner. [0003] At present, the fault diagnosis of wind power gearbox bearings mainly depends on various sensor signals, such as vibration signals, acoustic emission signals, cur...

AI Technical Summary

Problems solved by technology

[0004] In view of the limitations of single sensor signals and insufficient diagnostic capabilities in the current wind power gearbox bearing diagnosis mentioned in the above background technology, the purpose of the present invention is to provide a bearing fault diagnosis method based on multi-view correlation feature learning, from multi-view learning From the perspective of unsupervised learning, the correlation learning between vibration features and current features is realized, so as to extract enhanced fault features and improve the accuracy and reliability of bearing fault diagnosis

Images