Long Short-Term Memory Network-Based Normal Pattern Group for Fault Detection of Three-Shaft Marine Gas Turbine

Bai, Mingliang and Liu, Jinfu and Ma, Yujia and Zhao, Xinyu and Long, Zhenhua and Yu, Daren (2020) Long Short-Term Memory Network-Based Normal Pattern Group for Fault Detection of Three-Shaft Marine Gas Turbine. Energies, 14 (1). p. 13. ISSN 1996-1073

[thumbnail of energies-14-00013-v2.pdf] Text
energies-14-00013-v2.pdf - Published Version

Download (7MB)

Abstract

Fault detection and diagnosis can improve safety and reliability of gas turbines. Current studies on gas turbine fault detection and diagnosis mainly focus on the case of abundant fault samples. However, fault data are rare or even unavailable for gas turbines, especially newly-run gas turbines. Aiming to realize fault detection with only normal data, this paper proposes the concept of normal pattern group. A group of long-short term memory (LSTM) networks are first used for characterizing the mapping relationships among measurable parameters of healthy three-shaft gas turbines. Experiments show that the proposed method can detect all 13 common gas path faults of three-shaft gas turbines sensitively while remaining low false alarm rate. Comparison experiment with single normal pattern model verifies the necessaries and superiorities of using normal pattern group. Meanwhile, comparison between LSTM network and other methods including support vector regression, single-layer feedforward neural network, extreme learning machine and Elman recurrent neural network verifies the superiorities of LSTM network in fault detection. Furthermore, comparison experiment with four common one-class classifiers further verifies the superiorities of the proposed method. This also indicates the superiorities of data-driven methods and gas turbine principle fusion to some extent.

Item Type: Article
Subjects: Science Repository > Energy
Depositing User: Managing Editor
Date Deposited: 24 Mar 2023 05:07
Last Modified: 02 Jun 2024 06:38
URI: http://research.manuscritpub.com/id/eprint/983

Actions (login required)

View Item
View Item