Diagnosis-Driven Prognosis for Decision Making

In Phase II, the QSI-Vanderbilt team seeks to develop a system-level diagnostics and prognostic process that incorporates a "sense and respond capability," which first uses error codes and discrete sensor values to correctly diagnose the system health including degradations and failures of sensors and components, and then invokes appropriate prognostics routines for the assessment of RUL and performance capability. The QSI-Vanderbilt team plans to emphasize advancement in the following five areas: (a) leverage extensive LADEE telemetry data to further enhance and develop online degradation profiles, performance analysis and remaining useful life (RUL) computation algorithms, (b) develop/implement degradation detection algorithms to compute time-to-alarm (TTA) and time-to-maintenance (TTM) predictions and correlate with alarm/maintenance events, (c) develop reusable library of models and tests, (d) verification and validation of the resulting solution, and (e) demonstrate the proposed solution on LADEE's and other spacecraft subsystems. Once fully developed, outcomes of this effort will lower the cost of developing prognostics and provide maximum critical system availability, smarter scheduling of maintenance, overall logistics support cost, and optimal match of assets to missions. The proposed offering will also provide a cost-effective and pragmatic solution to our commercial customers who want to reduce unscheduled downtime by practicing condition based maintenance, but cannot justify the cost of developing prognostic methods in the conventional way.