Bearing degradation state identification and predication method based on variation modal decomposition-transfer entropy

Abstract

The invention relates to a bearing degradation state identification and predication method based on variation modal decomposition-transfer entropy, and belongs to the technical field of gear fault analysis. According to the technical scheme, the severity degree of a rotating machinery fault can be effectively reflected through parameters of system nonlinearity and the complexity degree; variationmodal decomposition and a transfer entropy theory based on signal complexity of the nonlinearity kinetic parameters are combined to achieve rolling bearing degradation state identification; and the rolling bearing state evaluation index based on variation modal decomposition-transfer entropy is built, and full-life experimental data of a rolling bearing are predicted through a model. The bearing degradation state identification and predication method provides new and effective means for fault diagnosis, performance degradation state identification and trend prediction of rotating machinery; and the variation modal decomposition-transfer entropy and SVR rolling bearing fault evolutionary trend prediction model is built, the full-life experimental data of the rolling bearing are predicted through the model, and accuracy and effectiveness are improved.

Description

technical field [0001] The invention relates to a method for identifying and predicting a bearing degradation state based on variational mode decomposition-transfer entropy, and belongs to the technical field of gear failure analysis. Background technique [0002] Rotating machinery such as gears and rolling bearings are important components commonly used in mechanical systems, and their operating status is directly related to the smooth and safe operation of the system. Therefore, it is of great significance to monitor and predict the operating state of rotating machinery. If quantitative degradation information can be extracted during the process of its performance evolution, it is possible to organize and formulate effective maintenance plans in a targeted manner, ensure the safe operation of mechanical equipment, and greatly improve the service performance of key components. Fault prediction methods require the ability to detect early faults, determine the severity of c...

AI Technical Summary

Problems solved by technology

In recent years, EMD and LMD have been used as adaptive decomposition methods for nonlinear and non-stationary signals. Although EMD has been widely used in the field of fault diagnosis of rotating machinery, EMD is still an empirical algorithm without a solid mathematical fou

Images