Bearing residual service life prediction method and system based on multi-source domain field generalization

• Main Authors: DING XU, FAN YUQI, HEO JIN, XU JUAN, LV ZENGWEI
• Format: Patent
• Language: Chinese; English
• Published: 18.04.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention relates to the field of bearing life prediction, in particular to a bearing residual service life prediction method and system based on multi-source domain field generalization. Sampling signals of a target bearing at the latest t times are input into a bearing prediction model to predict the end of life of the target bearing, and the remaining service life of the bearing is calculated in combination with the end of life of the target bearing; the bearing prediction model comprises a data preprocessing module and a health prediction module. In the training process of the health prediction module, intra-domain and inter-domain normalization and mean variance cross exchange are combined. According to intra-domain normalization, different time points of the same bearing are subjected to normalization processing, and intra-domain differences are learned; inter-domain normalization: performing normalization processing on the same time point of different bearings, and learning inter-domain difference