Method for extracting fault feature of antifriction bearing based on sliding entropy-ICA algorithm

Abstract

A method for extracting the fault feature of an antifriction bearing based on a sliding entropy-ICA algorithm is provided. The method comprises main steps of: (1) subjecting a single-channel actually measured signal to EMD to obtain respective IMF components; (2) screening out effective IMF components by using a sliding entropy cross correlation coefficient to form a virtual channel signal; (3) integrating the single-channel actually measured signal with the effective IMF components to form a composite signal matrix, separating the composite signal matrix by using a FastICA algorithm to obtain respective source signal estimated values; (4) retaining a source signal containing a bearing fault feature, and extracting a plurality of time-domain feature parameters and frequency-domain feature parameters to form a feature parameter set; and (5) subjecting a high-dimensional feature set to data fusion by using an LLE algorithm to obtain an accurate low-dimensional feature parameter. The method uses the sliding entropy-ICA algorithm in combination with the LLE algorithm, is suitable for extracting the fault feature of rotating machines including the antifriction bearing, and can extract the source signal containing fault information just by using the single-channel signal. The low-dimensional feature parameter obtained by the method can describe bearing fault information.

Description

[0001] Technical field: [0002] The invention relates to the field of mechanical fault diagnosis, in particular to a method for extracting fault features of rolling bearings. [0003] Background technique: [0004] As one of the commonly used parts in rotating machinery, rolling bearings are also one of the most easily damaged parts due to their small structure and large load capacity. They are often used as the main monitoring object for mechanical fault diagnosis. Due to the advantages of rich information and convenient collection, signal processing and analysis of vibration signals is one of the important means of bearing fault diagnosis commonly used at present. However, the working environment is complex during mechanical operation, and the measured signals collected by vibration sensors are usually many The result of the mutual coupling of two source signals, and the transmission path of the sensor will also interfere with the fault information of the signal, especially ...

AI Technical Summary

Problems solved by technology

[0004] As one of the commonly used parts in rotating machinery, rolling bearings are also one of the most easily damaged parts due to their small structure and large load capacity. They are often used as the main monitoring object for mechanical fault diagnosis. Due to the advantages of rich information and convenient collection, signal processing and analysis of vibration signals is one of the important means of bearing fault diagnosis commonly used at present. However, the working environment is complex during mechanical operation, and the measured signals collected by vibration sensors are usually many The result of the mutual coupling of two source signals, and the transmission path of the sensor will also interfere with the fault information of the signal, especially in the early stage of the bearing fault, the fault information is weak, which increases the difficulty of bearing signal feature extraction, and the extracted feature parameters will appear virtual. Disadvantages such as high alert rate

[0005] In general, the more complex the machine, the more the number of source signals, and considering the cost control in practical applications, the number of sensors used to collect vibration signals of rolling bearings is often smaller than the actual number of source signals, or even single-channel measured For the underdetermined problem of the signal, the current blind source separation technology mostly assumes that the number of sensors is greater than the number of source signals. However, in actual engineering, due to limited conditions, the above conditions are often not met, resulting in inaccurate or even distorted source signals. Although the above problems can be solved by EMD decomposition, due to interpolation errors and boundary effects in the EMD decomposition process, the IMF components will be mixed with pseudo components, which do not contain the effective information of the original single-channel measured signal, and eventually lead to the construction of virtual channels. The signal is distorted and the extracted source signal is inaccurate

[0006] Signal feature extraction is an important link in mechanical fault diagnosis. The selection method of feature extraction directly affects the reliability of fault pattern recognition results. Different feature parameters reflect the motion state of bearing faults from different angles. Fault diagnosis of bearings has limitations, and it is impossible to accurately predict the fault result. Too many feature indicators can easily cause "information disaster"

Images