3 - Way Valve 3 - Way Valve Flow Meter

The complexity of diagnosis tasks in large-scale, heterogeneous dynamic systems has turned the attention in this area toward model-based methods. Most model-based diagnostic systems try to nd a set of failed components that can explain observed discrepancies in system behavior consistently with constraints represented by the models. Observations are usually sensor-based and discrepancies are detected by fault detection algorithms that compare expected and observed system behavior. We have developed and eld tested a real-time robust diagnostic system, which uses hierarchical, multiple-aspect models of plants. The models include the functional structure, timed failure propagation graphs, physical component structure and component failure modes. The diagnostic reasoning applies structural and temporal constraints for the generation and validation of fault hypotheses using the \predictorcorrector" principle. The diagnosis is generated in real-time amid an evolving alarm scenario, and uses progressive deepening control strategy. The robust diagnostic system has been tested and demonstrated using ECLSS models obtained from the Boeing Company.