Development of Novel and Emerging Technology for the Enhancement of Fault Diagnostics

The critical navigational precision of the nuclear-powered ballistic missile submarine fleet is based on the aging Electrostatically Supported Gyroscope Navigator (ESGN). The increasing frequency of repairs and increasing Mean Time To Repair (MTTR) for ESGN systems have potential to affect mission readiness. Ridgetop Group proposes an Expert Troubleshooting Action System (ETAS) to reduce mean time to repair (MTTR) and increase mean time between failures (MTBF). The novel machine learning system combines accelerated diagnostics with prognostics to detect signatures of incipient failure. This optimized approach enables simultaneous preventive and corrective maintenance within prescribed time-constraints. The diagnostic element builds on Ridgetop"s experience in prioritized analytical troubleshooting, anchored in historical repair actions and outcomes from existing best practices for the ESGN. Difficult-to-diagnose faults (e.g., intermittent connections and marginal stability) will receive particular focus. The prognostic element will integrate diagnostic data with"what-if"analyses and physics-of-failure models to identify likely next failures and corresponding time horizons. The prognostic element leverages Ridgetop"s core strengths in prognostic health management (PHM) and condition-based maintenance (CBM) for complex electronic and electromechanical equipment. Ridgetop will formulate metrics in Phase I to drive maturation of the approach in Phase II.