Field data evaluation and continuous health assessment of critical avionics subsystem degradation

Effectively utilizing existing on-board and at-wing data that encompasses environmental, built-in-test (BIT), vibration, and maintenance test results, can realize improved maintenance, survivability and critical failure rates via the identification of degrading components prior to critical failure. The authors have developed software to show the feasibility of onboard and at-wing prognostics using field data from an army aircraft platform as a multi-faceted case study for predicting and diagnosing the health of a mission-critical targeting subsystem. The two use cases presented, complimentary embedded and at-wing paradigms, illustrate the mining of data from multiple sources, trending and ranking of anomalous indicators, development of a relational model for on-board BIT data, automated advanced reasoning for reduced ambiguity, and valuable avionics system prognostics. The application of these techniques to the systems engineering process, allow for the ground truth feedback of valuable engineering test results for validation of the prognostic health management (PHM) process