Byeong-Keun Choi

TL;DR: In this paper, two methods of multi-class classification techniques for fault diagnosis through RVM and SVM are presented and the effectiveness of using acoustic emission (AE) and vibration signals due to low impact rate for low speed diagnosis.

TL;DR: In this paper, a genetic algorithm (GA)-based kernel discriminative feature analysis is proposed for low-speed bearing defect detection. And the most useful fault features for diagnosis are then selected by utilizing a GA-based Kernel Discriminative Feature Analysis (KDA) cooperating with one-against-all multicategory support vector machines (OAA MCSVMs).

TL;DR: In this article, a technique for accurate assessment of the remnant life of bearings based on health state probability estimation and historical knowledge embedded in the closed loop diagnostics and prognostics system is described.

TL;DR: In this article, the authors proposed a fault diagnosis scheme for incipient low-speed rolling element bearing failures, which consists of fault feature calculation, discriminative fault feature analysis, and fault classification.

TL;DR: The start-up transient current signal is selected as features source for fault diagnosis and SVM multi-class classification using one against all strategy is selected for classification tool due to good generalization properties.