Robust Fault Detection of an Industrial Gas Turbine Prototype: A Hybrid Passive Approach Based on Local Linear Neuro-Fuzzy Techniques

This study proposed a model-based robust fault detection (RFD) method using soft computing techniques. Robust detection of the possible realistic incipient faults of an industrial gas turbine engine in steady-state conditions is mainly centered. For residual generation a bank of Multi-Layer perceptron (MLP) models, is used, Moreover, in fault detection phase, a passive approach based on Modelling Error Model (MEM)is employed to achieve robustness and threshold adaptation, and toward this purpose, Local Linear NeuroFuzzy (LLNF) model is exploited to construct error model to generate uncertainty interval upon the system output in order to make decision whether or not a fault occurred. This model is trained using the Locally Linear Model Tree (LOLIMOT) algorithm which is an incremental treestructurealgorithm. Simple thresholding is also exploited along with adaptive thresholding in fault detection phase for comparative purposes. In order to show the effectiveness of proposed RFD method, it was tested on a single-shaft industrial gas turbine prototype and has been evaluated using non-linear simulations based on the gas turbine data. KeywordsRobust fault detection, neural network, industrial gas turbine, local linear neuro-fuzzy local linear model tree (LOLIMOT), system identification.