Optimal Input Design for Autoregressive Model Discrimination with Output Amplitude Constraints

Abstract The optimal input design problem is considered for discriminating two autoregressive models when the amplitude of the system output has to be regulated within a certain tolerance limit with high probability. This constraint is more meaningful than power constraint in case where extremely large system output may cause troubles in the system. Methods are presented to construct a Ds-optimal input which maximizes the power of likelihood ratio test discriminating the models. It is exemplified by digital simulation studies the applicability of the proposed Ds-optimal input for discrimination of autoregressive models.