State monitoring method for rolling bearing and state monitoring device for rolling bearing

摘要

Problem to be solved: to provide a state monitoring method and a state monitoring apparatus capable of accurately estimating the size of the damaged portion of the rolling bearing.A method of generating a feature vector of a first rolling bearing comprising a characteristic quantity of vibration data of a first rolling bearing andBy performing machine learning of the feature vector of the first rolling bearing and the damage size of the first rolling bearingGenerating regression models to estimate damage size from feature vectors andGenerating a feature vector of a second rolling bearing comprising features of the vibration data of the second rolling bearing andUsing regression modelsFrom the feature vector of the second rolling bearingIncluding the step of estimating the damage size of the second rolling bearing.Diagram