Model-based fault diagnosis approaches with application to an industrial gas turbine simulator

In this work, different model-based procedures exploiting the analytical redundancy principle for the detection and isolation of the input-output sensor faults on a gas turbine simulated process are presented and compared. The contribution of the paper consists of exploiting several identification schemes in connection with linear and nonlinear residual generator design procedures for diagnostic purposes. Thus, it will be shown that black-box modelling and output estimation approaches to fault diagnosis are in particular advantageous in terms of solution complexity and performance achieved. The effectiveness and the capabilities of the proposed fault diagnosis strategies are analysed by means of extensive simulation of the industrial gas turbine model, in the presence of measurement and modelling errors.