Generative Oversampling Method for Imbalanced Data on Bearing Fault Detection and Diagnosis

Applied Sciences

Paul Lukowicz¹  Haebom Lee²  Jun Jo²  Sungho Suh²  YongOh Lee² 

[1] Department of Computer Science, TU Kaiserslautern, 67663 Kaiserslautern, Germany;Smart Convergence Group, Korea Institute of Science and Technology Europe Forschungsgesellschaft mbH, 66123 Saarbrücken, Germany;

关键词: generative adversarial networks;    oversampling;    data imbalance problem;    bearing fault;    convolutional neural networks;   

DOI  :  10.3390/app9040746

来源: DOAJ

【 摘 要 】

In this study, we developed a novel data-driven fault detection and diagnosis (FDD) method for bearing faults in induction motors where the fault condition data are imbalanced. First, we propose a bearing fault detector based on convolutional neural networks (CNN), in which the vibration signals from a test bench are used as inputs after an image transformation procedure. Experimental results demonstrate that the proposed classifier for FDD performs well (accuracy of 88% to 99%) even when the volume of normal and fault condition data is imbalanced (imbalance ratio varies from 20:1 to 200:1). Additionally, our generative model reduces the level of data imbalance by oversampling. The results improve the accuracy of FDD (by up to 99%) when a severe imbalance ratio (200:1) is assumed.

【 授权许可】

Unknown