Imbalance learning for fault diagnosis gearbox in wind turbine

Liu Tianyu

Abstract

Defect is one of the important factors resulting in gearbox of wind turbine, so it is significant to study the technology of defect diagnosis for gearbox. 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 gearbox. In imbalanced problems, some features are redundant and even irrelevant. These features will hurt the generalization performance of learning machines. Here we propose PSO (Particle Swarm Optimization based feature selection for Easy Ensemble) to solve the class imbalanced problem in the fault diagnosis of gear. Experimental results on UCI data sets and gearbox data set show that PSOEE improves the classification performance and prediction ability on the imbalanced dataset.