Department of Electrical Engineering, Islamic Azad University, South Tehran Branch Tehran, Iran
Faculty of Electrical Engineering, K. N. Toosi University of Technology Tehran, Iran
In this study, detection and identification of common faults in industrial gas turbines is investigated. We propose a model-based robust fault detection(FD) method based on multiple models. For residual generation a bank of Local Linear Neuro-Fuzzy (LLNF) models is used. Moreover, in fault detection step, a passive approach based on adaptive threshold is employed. To achieve this purpose, the adaptive threshold band is made by a sliding window technique to make decision whether a fault occurred or not. In order to show the effectiveness of proposed FD method, it is used to identify a simulated single-shaft industrial gas turbine prototype model, which works in various operation points. This model is a reference simulation which is used in many similar researches with the aim of fault detection in gas turbines.