Abstract: Defect is one of the important factors resulting in the bearing fault, so it is significant to study the technology of defect diagnosis for rolling bearing. The class imbalance problem is encountered in the fault diagnosis, which causes seriously negative effect on the performance of classifiers that assume a balanced distribution of classes. Though it is critical, few previous works paid attention to this class imbalance problem in the fault diagnosis of bearing. In the imbalanced data problems, some features are redundant and even irrelevant. These features will hurt the generalization performance of learning machines. Here we propose FEE (Fisher criterion feature selection for EasyEnsemble) to solve the class imbalanced problem in the fault diagnosis of bearing. The experimental results on the UCI data set and the bearing data set show that FEE improves the classification performance and prediction ability on the imbalanced dataset.

Key words: rolling bearing；fault diagnosis;imbalanced data set;ensemble learning