Causal strategy for set-membership fault diagnosis

Set-membership fault detection seems to be a promising approach because it takes into account a priori knowledge on modelling uncertainties and measurement errors. It consists in coherency tests with measurements and models. Nevertheless, a careful diagnostic strategy has to be designed in order to achieve fault diagnosis of complex processes. To achieve the diagnostic procedure, a causal analysis allows focusing the coherency tests on simple models, resulting in a decrease of the amount of computations. This paper will present an application to a nuclear waste treatment plant. The proposed causal strategy for diagnosis will be explained first. The set-membership coherency tests will be justified. Finally, a fault scenario will be presented in order to enlighten the method.