Multiple-model-based diagnosis and fault tolerant control
Résumé
Process diagnosis is still considered a challenging engineering problem. Technological systems, and also environmental systems, have complex behaviours often involving non linear relationships. When confronted to such systems, there is a need to build systems which can operate over a wide range of operating conditions. For that, it is very attractive to appeal to a decomposition of the model of the system into a number of simpler linear models. This appeal has been a factor in the development of the so-called multiple model approaches. This communication mainly focuses on the use of multiple models for process supervision including diagnosis and control. In both cases, it is shown how the traditional tools of the linear automatic can be wide and applied to the structures based on multiple models.