Gear fault detection method based on improved sparse decomposition algorithm

Abstract

The invention discloses a gear fault detection method based on an improved sparse decomposition algorithm, and relates to the technical field of fault detection. The method is based on traditional sparse reconstruction based on a parameter dictionary, and preprocessing of signals and optimization design of a parameter dictionary are added; signal preprocessing is realized by combining dual-tree complex wavelet decomposition with a maximum kurtosis principle; the influence of noise on subsequent processing is greatly reduced; target characteristic parameters are determined based on related filtering of Laplace wavelets so as to construct an over-complete dictionary; the dictionary redundancy can be effectively reduced, the designed dictionary is enabled to be more similar to the fault features, and finally, a matching pursuit algorithm is combined to realize extraction of the impact features in the vibration signals to realize fault detection; and the method can improve the calculationefficiency of sparse representation and realize effective fault diagnosis.

Description

technical field [0001] The invention relates to the technical field of fault detection, in particular to a gear fault detection method based on an improved sparse decomposition algorithm. Background technique [0002] As one of the indispensable components in rotating machinery, gears are widely used in modern industrial equipment such as electric power, petroleum, transportation, and agriculture. Due to the complex and changeable working conditions of gears in actual engineering, failures are inevitable. According to statistics, 80% of equipment failures in traditional machinery are caused by gears. Therefore, effective fault diagnosis of gears is very important for reducing economic losses and personnel. Casualties are of great significance. [0003] At present, the diagnosis method based on vibration analysis is one of the important ways to identify the faults of rotating machinery. The time domain, frequency domain and time domain characteristics of vibration signals ar...

AI Technical Summary

Problems solved by technology

[0003] At present, the diagnosis method based on vibration analysis is one of the important ways to identify the faults of rotating machinery. The time domain, frequency domain and time domain characteristics of vibration signals are an important basis for fault diagnosis. However, in practical applications, due to the influence of background noise and early faults The characteristics are not obvious, making fault diagnosis very difficult, and it is difficult for ordinary time-frequency analysis methods to carry out effective fault identification

In recent years, sparse representation theory has been applied in the field of fault diagnosis, and feature extraction based on sparse decomposition has become a new research hotspot. However, there are still many problems in the application of sparse decomposition in fault diagnosis. Because the actual vibration signal is very complex, in order to ensure Collecting complete fault information requires a large amount of data, which leads to a sharp increase in the amount of calculation. In addition, constructing a suitable over-complete dictionary plays a vital role in the effect of sparse reconstruction

Images