The monitoring of condition variables for maintenance purposes is a growing trend amongst researchers and practition-ers where decisions are based on degradation levels. The two approaches in Condition-Based Maintenance (CBM) are di-agnosing the level of degradation (diagnostics) or predicting when a certain level of degradation will be reached (prognos-tics). Using diagnostics determines when it is necessary to perform maintenance, but it rarely allows for estimation of future degradation. In the second case, prognostics does al-low for degradation and failure prediction, however, its major drawback lies in when to perform the analysis, and exactly what information should be used for predictions. This en-cumbrance is due to previous studies that have shown that degradation variable could undergo a change that misleads these calculations. This paper addresses the issue of identifying explosive changes in condition variables, using Control Charts, to determine when to perform a new model fitting in order to obtain more accurate Remaining Useful Life (RUL) estimations. The diagnostic-prognostic methodology allows for discarding pre-change observations to avoid contamina-tion in condition prediction. In addition the performance of the integration methodology is compared against adaptive au-toregressive (AR) models. Results show that using only the observations acquired after the out-of-control signal produces more accurate RUL estimations.
|Number of pages||16|
|Journal||International Journal of Prognostics and Health Management|
|State||Published - 2020|