Rolling bearing fault diagnosis method based on envelope permutation entropy

Abstract

The invention provides a rolling bearing fault diagnosis method based on envelope permutation entropy. The method comprises the following steps: collecting vibration signals of a rolling bearing in different states; solving an upper envelope curve, a lower envelope curve and a mean envelope curve of the collected vibration signals by referring to an envelope extremum thought, and calculating permutation entropy of each envelope curve; taking permutation entropies of the upper envelope curve, the lower envelope curve and the mean value curve as feature vectors of vibration signals of the rolling bearing; dividing the collected rolling bearing signals in different states into a training set and a test set, and using a support vector machine as a pattern recognition tool; and completing identification of different state signals of the rolling bearing according to a prediction result. Aiming at the limitation of a conventional permutation entropy algorithm and other multi-scale analysis algorithms, an envelope curve thought is introduced to perform rolling bearing fault feature extraction and calculate the envelope permutation entropy, and the scheme can extract more complete feature information from different types of vibration signals, and has better classification performance in rolling bearing fault recognition.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis method of a rolling bearing based on envelope arrangement entropy. Background technique [0002] With the continuous improvement of the composite and integration of modern mechanical equipment, rolling bearings have gradually become an indispensable key component in the mechanical system, and the quality of its working performance is directly related to the performance of the entire mechanical system. Therefore, it is necessary to accurately and effectively identify the working state of rolling bearings. [0003] In the field of rolling bearing fault diagnosis, analyzing the vibration signal and extracting its characteristic information is one of the most effective and common methods. However, with the influence of the complexity of the mechanical system and the interference of the working environment, the vibration signal of the rolling bearing exhibit...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that the conventional multi-scale decomposition algorithm cannot adaptively select components when describing the characteristic information of vibration signals, and the number of selected components is too large, the present invention proposes a rolling bearing fault diagnosis method based on envelope permutation entropy, which is different from conventional permutation entropy Compared with the method, the envelopment permutation entropy summarizes the characteristic information of the vibration signal through the entropy values ​​of the multi-scale components at three scales, and the obtained characteristic information is more complete, so that the classification and identification of the bearing working state are more accurate and effective; compared with the conventional multi-scale Compared with the scale decomposition method, the envelope permutation entropy does not need to select from multiple components obtained by decomposition and calculate its feature information, which improves the adaptability of the algorithm and the speed of the calculation process

Images