Dynamic system identification and model-based fault diagnosis of an industrial gas turbine prototype

Abstract

In this paper, a model-based procedure exploiting analytical redundancy for the detection and isolation of faults on a gas turbine process is presented. The main point of the present work consists of exploiting system identification schemes in connection with observer and filter design procedures for diagnostic purpose. Linear model identification (black-box modelling) and output estimation (dynamic observers and Kalman filters) integrated approaches to fault diagnosis are in particular advantageous in terms of solution complexity and performance. This scheme is especially useful when robust solutions are considered for minimise the effects of modelling errors and noise, while maximising fault sensitivity. A model of the process under investigation is obtained by identification procedures, whilst the residual generation task is achieved by means of output observers and Kalman filters designed in both noise-free and noisy assumptions. The proposed tools have been tested on a single-shaft industrial gas turbine prototype model and they have been evaluated using non-linear simulations, based on the gas turbine data.