For the fault detection of technical processes different methods can be applied based on the information extracted from direct measured signals, from signal models and process models. Examples for signal model based fault detection methods are spectral analysis or parameter estimation of ARMA models, examples for process model based methods are parameter estimation, state estimation or parity equation approaches. A comparison of these methods shows that they have different properties with regard to the detection of faults in the process, the actuators and the sensors.
After a brief review of model based fault detection methods the various advantages and disadvantages of the different methods are summarized. The importance of realistic fault modeling is outlined and the suitability of model-based fault detection methods in dependence on the type of faults is discussed. By a proper integration of different fault detection methods mainly their advantages can be used and their disadvantages avoided. It will be shown which integrations of fault detection methods are appropriate to generate analytical symptoms which are then treated by methods of change detection and classification.
For fault diagnosis a knowledge based procedure is required, because in addition to analytical symptoms also qualitative information in form of heuristic symptoms have to be taken into account. It will be shown how based on heuristic process knowledge as fault-symptom causalities and a unified representation of all symptoms an integrated fault diagnosis can be performed. This comprises the treatment of the symptom as uncertain facts and approximate diagnostic reasoning via if-then rules either in a probabilistic or a fuzzy-logic (possibilistic) frame.
As examples for integrated fault detection and diagnosis experimental results are shown which were obtained with machine tools.
In summary, the contribution shows how through proper integration of different fault detection methods and integration of fault diagnosis methods a comprehensive fault diagnosis of the components of technical processes can be performed.
Танкадо мертв. Партнер Танкадо обнаружен. Сьюзан замолчала. Танкадо мертв. Как это удобно.