In this article, different methodologies in the area of system identification, parametric fault isolation, robustness in fault diagnosis have been surveyed and applied to a pedagogical HydroStatic Transmission (HST) system. A Bond Graph (BG) model for the system has been developed and then nonlinear regression analysis was done on the state equations, obtained from that model, to estimate the unknown parameters as a part of system identification. The test bench was designed to introduce faults in different components for the purpose of experimental validation of Fault Detection and Isolation (FDI). The model based single fault isolation was done by using structural analysis of some constraint relations, called Analytical Redundancy Relations (ARR), the numerical evaluation of which are called residuals. The robustness in fault isolation was addressed through Linear Fractional Transformation (LFT) approach to make residuals insensitive to uncertainty of system parameters, but sensitive to fault.