Fault Recognition in the Presence of Error With NURBS-Based Metamodels

Condition-based maintenance (CBM) offers the possibility of replacing the predominant maintenance-as-scheduled paradigm with a maintenance-on-demand paradigm. In all CBM algorithms, faults must first be recognized, then characterized and finally reconciled. Multiple CBM methods have been proposed, including model-free, model-based and metamodel-based methods. However, the signals from real systems are obscured by sources of error. This research examines the impact of error upon a metamodel-based CBM approach using a simulated system to reveal the significance of error in the all-important step of fault recognition. The use of a simulated system allows control of the type and magnitude of both the error and of the fault signals allowing their significance to be evaluated. As a result of this research, a stronger theoretical foundation metamodel-based CBM techniques is established and several promising behaviors are identified.