Gas turbine system identification using a bilayer equilibrium manifold expansion model
Aircraft Engineering and Aerospace Technology
ISSN: 0002-2667
Article publication date: 7 April 2022
Issue publication date: 4 August 2022
Abstract
Purpose
This paper aims to establish a multi-input equilibrium manifold expansion (EME) model for gas turbine (GT). It proposes that the extension of model input dimension is realized based on similarity theory and affine structure in the framework of single-input EME model. The study aims to expand the scope of application of the EME model so that it can be used for the control or fault diagnosis of GTs.
Design/methodology/approach
In this paper, the concepts of corrected equilibrium manifold expansion (CEME) model and multi-cell equilibrium manifold expansion (MEME) model are first proposed. This paper uses theoretical analysis and simulation experiments to demonstrate the effectiveness of the bilayer equilibrium manifold expansion (BEME) model, which is a combination of the CEME and the MEME models. Simulation experiments include confirmatory experiments and comparative experiments.
Findings
The paper provides a new sight into building a multiple-input EME (MI-EME) model for GTs. The proposed method can build an accurate and robust MI-EME model that has superior performance compared with widely used nonlinear models including Wiener model (WM), Hammerstein model (HM), Hammerstein–Wiener model (HWM) and nonlinear autoregressive with exogenous inputs (NARX) network model. In terms of accuracy, the maximum error percentage of the proposed model is just 1.309%, far less than WM, HM and HWM. In terms of the stability of model calculation, the range of the mean error percentage of the proposed model is just a quarter of that of NARX network model.
Originality/value
The paper fulfills the construction of a novel multi-input nonlinear model, which has laid a foundation for the follow-up research of model-based GT fault detection and isolation or GT control.
Keywords
Acknowledgements
This work is supported by National Natural Science Foundation of China under Grant No. 51976042 and National Science and Technology Major Project of China under Grant No. 2017-I-0007–0008.
Citation
Zhu, L., Jinfu, L., Ma, Y., Bai, M., Zhou, W. and Yu, D. (2022), "Gas turbine system identification using a bilayer equilibrium manifold expansion model", Aircraft Engineering and Aerospace Technology, Vol. 94 No. 8, pp. 1263-1274. https://doi.org/10.1108/AEAT-01-2020-0016
Publisher
:Emerald Publishing Limited
Copyright © 2022, Emerald Publishing Limited