Detecting faults in dynamic and bounded stochastic distributions: an observer based technique

Presents an approach to detect and diagnose faults in the dynamic part of a class of stochastic systems. Such a group of systems are subjected to a set of crisp inputs but the outputs considered are the measurable probability density functions of the system output, rather than the system output alone. A new approximation model is developed for the output probability density functions so that the dynamic part of the system is decoupled from the output probability density function. A nonlinear adaptive observer is constructed to detect and diagnose the fault in the dynamic part of the system. Convergency analysis is performed for the error dynamics,raised from the fault detection and diagnosis phase and an applicability study on the detection of the unexpected changes in the 2D grammage distributions in the paper forming process is included.