Anomaly Detection on Gas Turbine Fuel System Using a Sequential Symbolic Method

Li, Fēi; Wang, Hongzhi; Zhou, Guowen; Yu, Dan; Li, Jianzhong; Gao, Hong

doi:10.20944/preprints201704.0071.v1

2017

DOI: 10.20944/preprints201704.0071.v1

|View full text |Cite

Preprint

Anomaly Detection on Gas Turbine Fuel System Using a Sequential Symbolic Method

Fēi Li¹,

Hongzhi Wang²,

Guowen Zhou³

et al.

Abstract: Anomaly detection plays a significant role in helping gas turbines run reliably and economically. Considering collective anomalous data and both sensitivity and robustness of the anomaly detection model, a sequential symbolic anomaly detection method is proposed and applied to the gas turbine fuel system. A structural Finite State Machine is to evaluate posterior probabilities of observing symbolic sequences and most probable state sequences they may locate.Hence an estimating based model and a decoding based … Show more

Help me understand this report

View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2018

2024

Publication Types

Select...

Article4

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Symbolic Analysis of the Cycle-to-Cycle Variability of a Gasoline–Hydrogen Fueled Spark Engine Model

et al. 2018

View full text Add to dashboard Cite

An study of temporal organization of the cycle-to-cycle variability (CCV) in spark ignition engines fueled with gasoline-hydrogen blends is presented. First, long time series are generated by means of a quasi-dimensional model incorporating the key chemical and physical components, leading to variability in the time evolution of energetic functions. The alterations in the combustion process, for instance the composition of reactants, may lead to quantitative changes in the time evolution of the main engine variables. It has been observed that the presence of hydrogen in the fuel mixture leads to an increased laminar flame speed, with a corresponding decrease in CCV dispersion. Here, the effects of different hydrogen concentrations in the fuel are considered. First, it is observed that return maps of heat release sequences exhibit different patterns for different hydrogen concentrations and fuel-air ratios. Second, a symbolic analysis is used to characterize time series. The symbolic method is based on the probability of occurrence of consecutive states (a word) in a symbolic sequence histogram (SSH). Modified Shannon entropy is computed in order to determine the adequate word length. Results reveal the presence of non-random patterns in the sequences and soft transitions between states. Moreover, the general behavior of CCV simulations results and three types of synthetic noises: white, log-normal, and a noisy logistic map, are compared. This analysis reveals that the non-random features observed in heat release sequences are quite different from synthetic noises.

show abstract

Symbolic Analysis of the Cycle-to-Cycle Variability of a Gasoline–Hydrogen Fueled Spark Engine Model

et al. 2018

View full text Add to dashboard Cite

show abstract

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

Bai

Liu

et al. 2020

Energies

View full text Add to dashboard Cite

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.

show abstract

Anomaly Detection in Gas Turbines Using Outlet Energy Analysis with Cluster-Based Matrix Profile

Ghazvini,

Sànchez-Marrè,

Naderi

et al. 2024

Energies

View full text Add to dashboard Cite

Gas turbines play a key role in generating power. It is really important that they work efficiently, safely, and reliably. However, their performance can be adversely affected by factors such as component wear, vibrations, and temperature fluctuations, often leading to abnormal patterns indicative of potential failures. As a result, anomaly detection has become an area of active research. Matrix Profile (MP) methods have emerged as a promising solution for identifying significant deviations in time series data from normal operational patterns. While most existing MP methods focus on vibration analysis of gas turbines, this paper introduces a novel approach using the outlet power signal. This modified approach, termed Cluster-based Matrix Profile (CMP) analysis, facilitates the identification of abnormal patterns and subsequent anomaly detection within the gas turbine engine system. Significantly, CMP analysis not only accelerates processing speed, but also provides user-friendly support information for operators. The experimental results on real-world gas turbines demonstrate the effectiveness of our approach in the early detection of anomalies and potential system failures.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Anomaly Detection on Gas Turbine Fuel System Using a Sequential Symbolic Method

Cited by 4 publications

References 29 publications

Symbolic Analysis of the Cycle-to-Cycle Variability of a Gasoline–Hydrogen Fueled Spark Engine Model

Symbolic Analysis of the Cycle-to-Cycle Variability of a Gasoline–Hydrogen Fueled Spark Engine Model

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

Anomaly Detection in Gas Turbines Using Outlet Energy Analysis with Cluster-Based Matrix Profile

Contact Info

Product

Resources

About