Bearing Crack Diagnosis Using a Smooth Sliding Digital Twin to Overcome Fluctuations Arising in Unknown Conditions

Bearings cause the most breakdowns in induction motors, which can result significant economic losses. If faults bearings are not detected time, they whole system to fail. System failures lead unexpected breakdowns, threats worker safety, and huge In this investigation, a new approach is proposed for fault diagnosis of under variable low-speed conditions using smooth sliding digital twin analysis indirect acoustic emission (AE) signals. The designed based on combination autoregressive fuzzy Gauss–Laguerre bearing modeling observer. has four steps. AE signals resampled root mean square (RMS) feature extracted from signal first step. To estimate RMS signal, second After that, residual generated difference between original estimated Next, support vector machine (SVM) crack detection size identification. effectiveness evaluated by provided our lab’s dataset, where benchmark dataset consists one normal seven abnormal conditions: ball, outer, inner, outer-ball, inner-ball, inner-outer, inner-outer-ball. results demonstrated that average accuracies anomaly identification used 97.75% 97.78%, respectively.