Bearing state noise diagnosis algorithm facing network variable screening and characteristic entropy fusion

Abstract

The invention discloses a bearing state noise diagnosis algorithm facing network variable screening and characteristic entropy fusion. A sensor collects bearing operation noise signals. The noise signals are segmented according to a time sequence and form a sample set. A time-frequency domain characteristic of a sample is extracted so as to acquire a time-frequency-domain one-dimensional characteristic row vector. An average influence value algorithm is adopted to realize first characteristic variable screening so as to acquire a sensitive characteristic set, and through calculating a characteristic entropy of the sensitive characteristic set, characteristic secondary screening and dimensionality reduction are performed on an average influence value similarity characteristic so as to acquire a final characteristic set. A PSO or GA optimization support vector machine is used to carry out training and establish a fault diagnosis model so as to determine a bearing fault type and output aresult. In the invention, complementarity of a characteristic average influence value and the characteristic entropy based on a network in characteristic selection and characteristic classification isused; and a disadvantage that the characteristic selection and a neural network classification algorithm are mutually isolated in bearing noise diagnosis is overcome so that a time-frequency domain characteristic index well reflects a bearing operation state and a classification network characteristic.

Description

technical field [0001] The invention relates to a bearing noise diagnosis algorithm, in particular to a bearing state noise diagnosis algorithm oriented to network variable screening and feature entropy fusion. Background technique [0002] Rolling bearing is an important component in rotating machinery, and it is also a relatively common and easily damaged part in rotating machinery. It plays a key role in rotating machinery. Whether its working status is normal or not directly affects the performance of the entire unit. Noise is a kind of mechanical wave. Vibration radiates energy to the surrounding medium, which contains rich machine status information. Compared with the vibration diagnosis technology, it has a series of advantages such as non-contact measurement, flexible sensor installation, no influence on the normal operation of the equipment, and online monitoring, and is especially suitable for occasions where the vibration signal is not easy to measure. [0003] B...

AI Technical Summary

Problems solved by technology

However, traditional dimensionality reduction methods such as principal component analysis and linear discriminant analysis are limited to dealing with linear features, and there are often complex nonlinear relationships in the feature sets of rolling bearing vibration signals, so the traditional single dimensionality reduction method faces challenges

[0004] At present, rolling bearing fault diagnosis algorithms generally use data-driven machine learning algorithms, such as neural networks, fuzzy recognition, Bayesian classification, etc., which have the disadvantages of long training time or low classification accuracy.

Images