Physical Modeling for Anomaly Diagnostics and Prognostics

Ridgetop developed an innovative, model-driven anomaly diagnostic and fault characterization system for electromechanical actuator (EMA) systems to mitigate catastrophic failures.Ridgetop developed a MIL-STD-1553 bus monitor and a MIL-STD-1553 bus controller that simulates the aircraft data bus, reads the environmental (i.e., altitude) and operational (i.e., response of system) data of a system and determines if a fault is manifesting; and if true determines the root cause and symptoms of the fault. Once an anomaly is detected, the Model-based Avionic Prognostic Reasoner (MAPR) solves a user-outlined state-space model, symbolically, using a Gauss-Newton optimization method and the information from the MIL-STD-1553 bus. This algorithm outputs a list of best fitting parameters to match the command to the actual performance. Rules are programmed in, based on results from principal component analysis . The rules determine both fault mode and the severity of that fault. The rules can distinguish between two failure modes: Mechanical jam and MOSFET failure, and healthy.The real-time processing will allow for critical evolutions in flight safety and provides a game-changing approach to condition-based maintenance. Once deployed, flight safety can be improved by allowing the on-board flight computers to read from the MAPR and update their control envelope based on its evaluations, reducing damage propagation and increasing operational safety.In Phase 2, we will develop a functioning ground-based prototype of the technology to show the efficacy of the method. A ground-based version of the tool is the best candidate for development to ease adoption by testing in a low-risk environment; this tool will be demonstrated at the end of Phase 2. The MAPR concept is also applicable to any system with a state-space representation but at this point it has been developed with EMAs in mind.The MAPR prototype is at TRL 5 and will reach a TRL 7 by the end of Phase 2.