Model selection via worts-case criterion for nonlinear bounded-error estimation

Tech. Conf.International audienceIn this paper the problem of model selection for measurement purpose is studied. A new selcetion procedure in a deterministic framework is proposed. The problem of nonlinear bounded-error estimation is viewed as a set inversion procedure. As each candidate model structure leads to a specific set of admissible values of the measurement vector, the worts-case criterion is used to select the optimal model. The selection procedure is applied to a real measurement problem, grooves dimensioning using Remote Field Eddy Current (RFEC) inspection