In this work, a model-based procedure exploiting analytical redundancy for the FDI of faults on a multivariable dynamic process is presented. The main point of the paper consists of exploiting a disturbance decoupling scheme in connection with a dynamic filter design procedure for diagnostic purpose. It is shown that the suggested approach to fault diagnosis is in particular advantageous in terms of solution complexity and performance. Moreover, the presented method is especially useful when robust solutions are considered for minimising the effects of modelling errors and noise, while maximising fault sensitivity. In order to verify the robustness of the solution achieved, the proposed design has been experimented with the data of a simulated aircraft model in the presence of both measurement and modelling errors. Finally, extensive simulations of the test-bed process and Monte Carlo analysis are the tools used for assessing the overall capabilities of the developed FDI scheme, when compared also with different data-driven diagnosis methods.