Bearing fault diagnosis method and system based on improved LSSVM transfer learning

Abstract

The invention discloses a bearing fault diagnosis method and system based on improved LSSVM transfer learning, and the method comprises the following steps: processing target data and auxiliary data through employing recurrence quantification analysis, extracting a nonlinear feature and combing the nonlinear feature with a conventional time domain feature, forming a characteristic vector, and forming a training set; constructing a fault classification model through employing an improved LSSVM transfer learning, extracting the nonlinear feature of unmarked fault vibration data of a target bearing under a target work condition through the recurrence quantification analysis, combining the nonlinear feature with the conventional time domain feature, forming a feature vector, forming a test set, inputting the test set into a trained improved LSSVM model, carrying out analysis and outputting a result. Through respectively adding a penalty function and constraint condition of an auxiliary set into the original target function and constraint condition, the method enables the improved LSSVM to be affected by the auxiliary set in an iterative learning process, and improves the classification precision.

Description

technical field [0001] The invention belongs to the field of bearing fault diagnosis, in particular to a bearing fault diagnosis method and system based on transfer learning of an improved LSSVM (Least Squares Support Vector Machine, Least Squares Support Vector Machine). Background technique [0002] As one of the important components of rotating machinery, bearings are widely used in modern industry, and their fault diagnosis has become an effective means to ensure safe production and prevent major accidents. At present, bearing fault diagnosis mainly includes the operation steps of data acquisition, feature extraction and fault classification. Among them, the fault classification can be realized by traditional machine learning algorithm, and its effective classification requires the same distribution of training data and test data, and sufficient amount of target diagnosis data. [0003] However, the complex working conditions common in actual industrial systems often le...

AI Technical Summary

Problems solved by technology

[0003] However, the complex working conditions common in actual industrial systems often lead to the inability to directly obtain target diagnostic data, and there are certain differences in the distribution characteristics of training data and test data, which will reduce the generalization ability of traditional machine learning fault diagnosis models, and even make model no longer applicable

[0004] When the above problems arise, most traditional machine learning algorithms use relabeling of target bearing fault samples to solve them, but it requires a lot of experiments and professional knowledge, and changes in external friction, working conditions and other factors in the industrial environment cannot guarantee collection The distribution of the labeled data and the target bearing fault data is consistent, and re-labeling the target bearing fault samples requires additional time and labor costs

Images