Prognostic Enhancements to Diagnostic Systems

Impact Technologies in cooperation with the Applied Research Laboratory (ARL) at Penn State University propose the development and implementation of a commercial software program to impartially evaluate the performance and effectiveness of CBMtechnologies. A software product called the CBM Metrics Test Bench will be further developed and implemented as a Web-based application that can be easily accessed and utilized by Navy personnel, system developers, and end-users alike. The Test Benchwill utilize a standardized set of mathematical and business case metrics for evaluating the performance and effectiveness of machinery health monitoring systems. The state-of-the-art evaluation process will be capable of assessing CBM technologies interms of their ability to detect anomalies, and diagnose the root cause of faults. Specific metrics for these abilities include accuracy, reliability, sensitivities, stability, risk, economic cost/benefit, and robustness just to name a few. The evaluationmethodology utilizes the set of metrics in conjunction with a database of clearly documented transitional and seeded fault data from full-scale test-bed tests and Naval in-service data from different applications. The technical performance and accuracy ofthe CBM algorithms at the component or subsystem level will be evaluated with performance metrics, while system level capabilities in terms of achieving the overall operational goals, economic cost/benefit and assessment of the business case will beevaluated with effectiveness measures.