Ensemble-Based Fault Detection and Isolation of an Industrial Gas Turbine

Document Type

Conference Proceeding

Publication Date

10-11-2020

Publication Title

Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

Volume

2020-October

First Page

2351

Keywords

decision tree, ensemble-based learning, fault detection and isolation (FDI), gas turbine

Last Page

2358

Abstract

In this study, an efficient strategy for fault detection and isolation (FDI) of an Industrial Gas Turbine is introduced based on ensemble learning methods. Four independent Wiener models are identified by employing plant input/output data to determine system behavior. Following that, an ensemble-based method is established, which utilizes all the Wiener models and relevant residuals to detect the faults. A fault isolation structure is then developed based on ensemble bagged tree procedure such that it is capable of isolating faults in a steady-state runtime. As a crucial goal, increasing accuracy and robustness simultaneously are mainly centered. The proposed FDI method is tested on nonlinear gas turbine simulation using real data from a combined cycle power plant. The obtained results illustrate the correctness and accuracy of the presented FDI scheme.

DOI

10.1109/SMC42975.2020.9282904

ISSN

1062922X

ISBN

9781728185262

Share

COinS