On the observation of the transient behavior of gas turbine combustion instability using the entropy analysis of dynamic pressure

Choi, Jongwun; Choi, Ouk; Lee, Min Chul; Kim, Nam Keun

doi:10.1016/j.expthermflusci.2020.110099

Cited by 9 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the RMS is the most standard method of CI diagnostics and is widely applied to commercial engines, RMS is firstly selected as a comparison tool [31][32][33][34] . TK is chosen secondly, because it is one of the recent methods that can judge the onset of CI, based not on the magnitude of DP but on the periodicity 14,35,36 . That is, since the TK contains information on the statistical quantity of "peakedness" and "tailedness, " the distribution and shape of DP can be used when determining the CI driving or decaying.…”

Section: Parameter or Methods Description Referencesmentioning

confidence: 99%

“…There are other approaches similar to TK. For example, entropy of energy 36 and permutation entropy 51,52 are recent approaches for CI diagnostics based on the signal distribution. In these methods, TK is widely used in the acoustics and CI detection; thus, it has also been selected as a parameter for comparison.…”

Section: Parameter or Methods Description Referencesmentioning

confidence: 99%

See 1 more Smart Citation

A novel diagnostic method based on filter bank theory for fast and accurate detection of thermoacoustic instability

Joo

Choi

Kim

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

This study proposes and analyzes a novel methodology that can effectively detect multi-mode combustion instability (CI) in a gas turbine combustor. The experiment is conducted in a model gas turbine combustor, and dynamic pressure (DP) and flame images are examined during the transition from stable to unstable flame, which is driven by changing fuel compositions. As a powerful technique for early detection of CI in multi-mode as well as in single mode, a new filter bank (FB) method based on spectral analysis of DP is proposed. Sequential processing using a triangular filter with Mel-scaling and a Hamming window is applied to increase the accuracy of the FB method, and the instability criterion is determined by calculating the magnitude of FB components. The performance of the FB method is compared with that of two conventional methods that are based on the root-mean-squared DP and temporal kurtosis. From the results, the FB method shows comparable performance in detection speed, sensitivity, and accuracy with other parameters. In addition, the FB components enable the analysis of various frequencies and multi-mode frequencies. Therefore, the FB method can be considered as an additional prognosis tool to determine the multi-mode CI in a monitoring system for gas turbine combustors.

show abstract

Section: Parameter or Methods Description Referencesmentioning

confidence: 99%

Section: Parameter or Methods Description Referencesmentioning

confidence: 99%

A novel diagnostic method based on filter bank theory for fast and accurate detection of thermoacoustic instability

Joo

Choi

Kim

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…To implement the block capable of extracting the power spectral density, we first apply two 1 × 1 convolutions with T filters to J (τ) . Denoting the two resulting feature maps by Re and Im, the power spectral density map PS is calculated as in Equation (11). J, Re, Im, and PS are then concatenated into a 4T-channel feature map, which is used as input to a ResNet.…”

Section: Early Fusionmentioning

confidence: 99%

“…Thus, CI has been one of the main issues for many combustion engines including gas turbines and internal engines. Although tremendous efforts have been exerted to notify and characterize the CI mechanisms [1][2][3][4][5] and to monitor and control the CI [6][7][8][9][10][11], the remorseless reinforcement of NOx emission regulation has made gas turbines to operate in ultra-lean premixed condition. This premixed combustion near the blowout limit makes safe operation of gas turbines uneasy by leading flame to oscillate, and, thus, amplifying CI [12,13].…”

Section: Introductionmentioning

confidence: 99%

Combustion Instability Monitoring through Deep-Learning-Based Classification of Sequential High-Speed Flame Images

Choi

Kim

et al. 2020

Electronics

Self Cite

View full text Add to dashboard Cite

In this study, novel deep learning models based on high-speed flame images are proposed to diagnose the combustion instability of a gas turbine. Two different network layers that can be combined with any existing backbone network are established—(1) An early-fusion layer that can learn to extract the power spectral density of subsequent image frames, which is time-invariant under certain conditions. (2) A late-fusion layer which combines the outputs of a backbone network at different time steps to predict the current combustion state. The performance of the proposed models is validated by the dataset of high speed flame images, which have been obtained in a gas turbine combustor during the transient process from stable condition to unstable condition and vice versa. Excellent performance is achieved for all test cases with high accuracy of 95.1–98.6% and a short processing time of 5.2–12.2 ms. Interestingly, simply increasing the number of input images is as competitive as combining the proposed early-fusion layer to a backbone network. In addition, using handcrafted weights for the late-fusion layer is shown to be more effective than using learned weights. From the results, the best combination is selected as the ResNet-18 model combined with our proposed fusion layers over 16 time-steps. The proposed deep learning method is proven as a potential tool for combustion instability identification and expected to be a promising tool for combustion instability prediction as well.

show abstract

Introduction of self-sustained thermoacoustic instability

Zhao¹

2023

Thermoacoustic Combustion Instability Control

View full text Add to dashboard Cite

On the observation of the transient behavior of gas turbine combustion instability using the entropy analysis of dynamic pressure

Cited by 9 publications

References 44 publications

A novel diagnostic method based on filter bank theory for fast and accurate detection of thermoacoustic instability

A novel diagnostic method based on filter bank theory for fast and accurate detection of thermoacoustic instability

Combustion Instability Monitoring through Deep-Learning-Based Classification of Sequential High-Speed Flame Images

Introduction of self-sustained thermoacoustic instability

Contact Info

Product

Resources

About