Integrating model-based diagnostics with simulation for real time health monitoring

In systems that contain continuous-valued variables, such as aerospace systems, faults can be sensitively detected and diagnosed by combining a real time simulation with a conventional model-based diagnostic engine. We present a unified approach in which the user builds a single model that contains a sufficiently detailed description of the system to support both simulation and automatic diagnosis. This approach is implemented in a modeling environment called CNModeler/spl trade/.