Rolling bearing fault detection method based on improved wavelet neural network

Abstract

The invention relates to a rolling bearing fault detection method based on the improved wavelet neural network. Energy distribution of each frequency band after wavelet packet decomposition is taken as a characteristic vector to input to the neural network, and the improved wavelet neural network is utilized to accomplish identification of rolling bearing fault modes. The method is advantaged in that a training speed of the wavelet neural network can be accelerated through extracting fault characteristics, and faults of the rolling bearing can be rapidly detected and positioned.

Description

A Fault Detection Method for Rolling Bearings Based on Improved Wavelet Neural Network Technical field: The invention belongs to a fault diagnosis method for a rolling bearing, in particular to a fault detection method for a rolling bearing based on an improved wavelet neural network. Background technique: The rolling bearing plays the role of supporting the transmission shaft and the parts on the shaft, and maintains the normal working position and rotation accuracy of the shaft. It is characterized by good mechanical efficiency, low power consumption during the operation of mechanical equipment, and good starting performance. Good, with good precision and speed, can meet the operation requirements of various mechanical equipment, long service life, compact structure, small size, light weight, easy installation and disassembly, easy repair and maintenance. Rolling bearings are one of the most widely used mechanical parts in aviation rotating machinery. They play a role in...

AI Technical Summary

Problems solved by technology

The essence of the Fourier transform is to decompose the waveform into the superposition of many sine waves of different frequencies. For known signals and stationary random processes, the Fourier transform is widely used in signal analysis and signal processing, but Fourier analysis uses a global The transformation of the signal is either completely in the frequency domain or completely in the time domain, so it is impossible to express the time-frequency domain properties of the signal at the same time, and this property is precisely the fundamental and key property of the non-stationary signal

Images