Remaining Useful Life Estimation Based on Detection of Explosive Changes: Analysis of Bearing Vibration

The monitoring of condition variables for maintenance purposes is a growing trend amongst researchers and practitioners where decisions are based on degradation levels. two approaches in Condition-Based Maintenance (CBM) diagnosing the level (diagnostics) or predicting when certain will be reached (prognostics). Using diagnostics determines it necessary to perform maintenance, but rarely allows estimation future degradation. In second case, prognostics does allow failure prediction, however, its major drawback lies analysis, exactly what information should used predictions. This encumbrance due previous studies that have shown variable could undergo change misleads these calculations. paper addresses issue identifying explosive changes variables, using Control Charts, determine new model fitting order obtain more accurate Remaining Useful Life (RUL) estimations. diagnostic-prognostic methodology discarding pre-change observations avoid contamination prediction. addition performance integration compared against adaptive autoregressive (AR) models. Results show only acquired after out-of-control signal produces RUL