Abstract:In this paper, the problem of identification for passive robust fault detection when parametric modeling uncertainty is considered. In particular, a zonotope is used to bound the model parametric uncertainty. Two identification methods are introduced following, respectively, the worst-case and setmembership approaches. Then, the underlying hypothesis are discussed and performance is compared.These two identification approaches lead to two robust fault detection tests (namely, the direct and inverse tests) that are also discussed. A case study based on a four tanks system is used to exemplify the properties of the two identification and associated fault detection approaches.