Feature extraction method of rotating machinery based on wpt-ceemd

Abstract

The present invention discloses a rotating machinery feature extraction method on the basis of a WPT-CEEMD. The noise part is eliminated or useful frequency bands are extracted by utilizing the good local analysis capability of a WPT, then CEEMD adaptive decomposition is performed, and finally few frequency aliasing parts after decomposition are reused for correction by employing the WPT, so that the extraction of feature frequency signals is realized. Through combination of a WPT and a CEEMD, the rotating machinery feature extraction method on the basis of a WPT-CEEMD overcomes disadvantages of existing frequency aliasing, having no adaptability and the like in a fault diagnosis method.

Description

technical field [0001] The invention belongs to the field of fault diagnosis of mechanical equipment, and in particular relates to a feature extraction method of rotating machinery based on WPT-CEEMD. Background technique [0002] With the rapid development of modern industry and science and technology, industry has become the standard to measure the development of a country's science and technology. Mechanical equipment is the carrier of industrial development, providing key technologies for industrial development, and playing an increasingly important role in the national economy. At the same time, rotating machinery is also becoming more and more large-scale, complex, and sophisticated. The functions of mechanical equipment are increasing, the performance indicators are getting higher and higher, and its composition and structure are becoming more and more complicated. This will inevitably make The probability of failure is greatly increased. [0003] Rolling bearings a...

AI Technical Summary

Problems solved by technology

After the two methods are adaptively decomposed, although the frequency aliasing defect of EMD is effectively suppressed, there is still a small amount of modal aliasing in the low frequency part.

Images