More Web Proxy on the site http://driver.im/

research-article

Supervised learning-based multi-site lean blowout prediction for dry low emission gas turbine

Authors:

Abdulrahman Abdullah Bahashwan,

Rosdiazli Ibrahim,

Temitope Ibrahim AmosaAuthors Info & Claims

Volume 244, Issue C

https://doi.org/10.1016/j.eswa.2023.123035

Published: 02 July 2024 Publication History

Abstract

Current dry low emission (DLE) gas turbines have extremely low nitrogen oxides (NOx) emissions, allowing them to comply with stringent environmental regulations. The ultra-low temperatures required to achieve such low emissions also increase the risk of a lean blowout (LBO). DLE gas turbines are particularly vulnerable to LBO, which can lead to system instability, higher carbon oxides (CO) emissions, damaged components, substantial financial losses and environmental damages. In this regard, this current study proposes a novel supervised learning-based prediction technique with efficient performance on out-of-distribution data from multiple DLE gas turbine plants (multi-site). The proposed prediction approach exploits the competitive advantages of both adaptive boosting (AdaBoost) and Linear support vector machine (LSVM) to improve the generalization capability as well as prediction accuracy. The proposed algorithm was trained and tested using a real-world DLE gas turbine dataset from six different sites. The result indicates that the proposed model consistently achieving LBO prediction accuracy rates above 99.9% and Mathew’s correlation coefficient (MCC) score above 0.9 across all datasets. All lean-premixed gas turbines could benefit from the developed Ada-LSVM, as it is an accurate model with a high generalization performance that can be used across multiple sites.

Highlights

•

Lean blowout (LBO) is the most critical issue in lean premixed gas turbines.

•

An investigation of the LBO fault based on historical data from real world dry low emission (DLE) gas turbines.

•

A supervised data-driven approach for LBO prediction in multiple lean premixed gas turbines.

•

A high generalization machine learning technique is applied for multisite prediction.

References

[1]

Abubaker H., Ali A., Shamsuddin S.M., Hassan S., Exploring permissions in android applications using ensemble-based extra tree feature selection, Indonesian Journal of Electrical Engineering and Computer Science 19 (1) (2020) 543–552.

[2]

Adekkanattu P., Rasmussen L.V., Pacheco J.A., Kabariti J., Stone D.J., Yu Y., et al., Prediction of left ventricular ejection fraction changes in heart failure patients using machine learning and electronic health records: a multi-site study, Scientific Reports 13 (1) (2023) 294.

[3]

Ahmed E., Yong H., Prediction of lean blowout performance of gas turbine combustor based on flow structures, Aeronautical Journal 122 (1248) (2017) 238–259,.

[4]

Akhtar S., Piffaretti S., Shamim T., Numerical investigation of flame structure and blowout limit for lean premixed turbulent methane-air flames under high pressure conditions, Applied Energy 228 (2018) 21–32,.

[5]

Amiri F., Yousefi M.R., Lucas C., Shakery A., Yazdani N., Mutual information-based feature selection for intrusion detection systems, Journal of Network and Computer Applications 34 (4) (2011) 1184–1199.

[6]

Bahashwan A.A., Ibrahim R.B., Omar M.B., Faqih M., Data-driven lean blowout prediction based on industrial dry low emission gas turbine dataset using decision tree, in: 2022 IEEE industrial electronics and applications conference (IEACon), 2022, pp. 90–93,.

[7]

Bahashwan A.A., Ibrahim R.B., Omar M.B., Faqih M., The lean blowout prediction techniques in lean premixed gas turbine: An overview, Energies 15 (22) (2022) 8343.

[8]

Bhattacharya A., Gupta B., Hansda S., Haque Z., Kumar A., Mishra M.K., et al., Lean blowout phenomena and prior detection of lean blowout in a premixed model annular combustor, in: Gas turbine india conference, Vol. 83532, American Society of Mechanical Engineers, 2019.

[9]

Boughorbel S., Jarray F., El-Anbari M., Optimal classifier for imbalanced data using matthews correlation coefficient metric, PLoS One 12 (6) (2017).

[10]

Cartocci N., Napolitano M.R., Costante G., Valigi P., Fravolini M.L., Aircraft robust data-driven multiple sensor fault diagnosis based on optimality criteria, Mechanical Systems and Signal Processing 170 (2022).

[11]

Cervantes J., Garcia-Lamont F., Rodríguez-Mazahua L., Lopez A., A comprehensive survey on support vector machine classification: Applications, challenges and trends, Neurocomputing 408 (2020) 189–215.

[12]

Chang L., Cao Z., Fu B., Lin Y., Xu L., Lean blowout detection for bluff-body stabilized flame, Fuel 266 (2020).

[13]

Chaudhari R.R., Sahu R.P., Ghosh S., Mukhopadhyay A., Sen S., Flame color as a lean blowout predictor, International Journal of Spray and Combustion Dynamics 5 (1) (2013) 49–66,.

[14]

Chen Y., Fan Y., Han Q., Shan X., Bi Y., Deng Y., The influence of cooling air jets on the premixed flame structure and stability of air-cooled bluff-body flameholder, Fuel 310 (2022).

[15]

Chicco D., Jurman G., The advantages of the matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation, BMC Genomics 21 (2020) 1–13.

[16]

De S., Bhattacharya A., Mondal S., Mukhopadhyay A., Sen S., Application of recurrence quantification analysis for early detection of lean blowout in a swirl-stabilized dump combustor, Chaos 30 (4) (2020).

[17]

De S., Bhattacharya A., Mukhopadhyay A., Sen S., Early detection of lean blowout in a combustor using symbolic analysis of colour images, Measurement 186 (2021),.

[18]

Edwards, J. T. (2017). Reference jet fuels for combustion testing. In 55th AIAA aerospace sciences meeting (p. 0146).

[19]

Elangovan M., Sugumaran V., Ramachandran K., Ravikumar S., Effect of SVM kernel functions on classification of vibration signals of a single point cutting tool, Expert Systems with Applications 38 (12) (2011) 15202–15207.

[20]

Elbaz A.M., Wang S., Guiberti T.F., Roberts W.L., Review on the recent advances on ammonia combustion from the fundamentals to the applications, Fuel Communications 10 (2022).

[21]

Faqih M., Omar M.B., Ibrahim R., Prediction of dry-low emission gas turbine operating range from emission concentration using semi-supervised learning, Sensors 23 (8) (2023) 3863.

[22]

Faqih M., Omar M.B., Ibrahim R., Omar B.A.A., Dry-low emission gas turbine technology: Recent trends and challenges, Applied Sciences 12 (21) (2022).

[23]

Guo L., Ge P.-S., Zhang M.-H., Li L.-H., Zhao Y.-B., Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine, Expert Systems with Applications 39 (4) (2012) 4274–4286.

Digital Library

[24]

Hasti V.R., Navarkar A., Gore J.P., A data-driven approach using machine learning for early detection of the lean blowout, Energy and AI 5 (2021).

[25]

Hoque N., Bhattacharyya D.K., Kalita J.K., MIFS-ND: A mutual information-based feature selection method, Expert Systems with Applications 41 (14) (2014) 6371–6385.

[26]

Hu B., Huang Y., Wang F., FIA method for LBO limit predictions of aero-engine combustors based on FV model, Aerospace Science and Technology 28 (1) (2013) 435–446.

[27]

Hu B., Huang Y., Xu J., A hybrid semi-empirical model for lean blow-out limit predictions of aero-engine combustors, Journal of Engineering for Gas Turbines and Power 137 (3) (2015).

[28]

Hu B., Xu Q.J., Predicting lean blowout limit of combustors based on semi-empirical correlation and simulation, Journal of Propulsion and Power 32 (1) (2016) 108–120,.

[29]

Huang X., Li Z., Jin Y., Zhang W., Fair-AdaBoost: Extending AdaBoost method to achieve fair classification, Expert Systems with Applications 202 (2022).

Digital Library

[30]

Huang Y., Sun L., On the quick prediction of lean blowout limits for gas turbine combustors, DEStech Transactions on Environment, Energy and Earth Sciences (2018).

[31]

Hui F., Liping J., Song Q., Zhanqiang L., Jiawei T., Cheng C., Grinding surface roughness prediction for silicon nitride ceramics: A dynamic grinding force and frequency domain approach, Ceramics International (2023).

[32]

Iannitelli M., Allegorico C., Garau F., Capanni M., A hybrid model for on-line detection of gas turbine lean blowout events, in: PHM society European conference, Vol. 4, 2018.

[33]

Ibrahim O., Bakare M.S., Amosa T.I., Otuoze A.O., Owonikoko W.O., Ali E.M., et al., Development of fuzzy logic-based demand-side energy management system for hybrid energy sources, Energy Conversion and Management: X 18 (2023).

[34]

Jang H.S., Bae K.Y., Park H.-S., Sung D.K., Solar power prediction based on satellite images and support vector machine, IEEE Transactions on Sustainable Energy 7 (3) (2016) 1255–1263.

[35]

Jaw, L. C., & Lee, Y.-J. (2014). Engine diagnostics in the eyes of machine learning. In Proceedings of the ASME turbo expo, Vol. 6.

[36]

Kang Z., Catal C., Tekinerdogan B., Product failure detection for production lines using a data-driven model, Expert Systems with Applications 202 (2022).

[37]

Kong C., Wang Y., Wu X., Zhang Z., Rotating gliding arc discharge induced flame oscillation near the lean blowout limit, Combustion and Flame 254 (2023).

[38]

Koutsouleris N., Worthington M., Dwyer D.B., Kambeitz-Ilankovic L., Sanfelici R., Fusar-Poli P., et al., Toward generalizable and transdiagnostic tools for psychosis prediction: an independent validation and improvement of the NAPLS-2 risk calculator in the multisite PRONIA cohort, Biological Psychiatry 90 (9) (2021) 632–642.

[39]

Krüger J.G.C., de Souza Britto A. Jr., Barddal J.P., An explainable machine learning approach for student dropout prediction, Expert Systems with Applications 233 (2023).

[40]

Lefebvre A.H., Fuel Effects on Gas Turbine Combustion—Ignition, Stability, and Combustion Efficiency, Journal of Engineering for Gas Turbines and Power 107 (1) (1985) 24–37,.

[41]

Lei S., Yong H., An overview of methodologies to predict lean blowout limits for gas turbine combustors, in: 2019 16th international bhurban conference on applied sciences and technology (IBCAST), IEEE, 2019, pp. 709–718.

[42]

Li F., Xu L., Du M., Yang L., Cao Z., Ion current sensing-based lean blowout detection for a pulse combustor, Combustion and Flame 176 (2017) 263–271,.

[43]

Li D., Zhang C., Cao J., Short-term passenger flow prediction of a passageway in a subway station using time space correlations between multi sites, IEEE Access 8 (2020) 72471–72484.

[44]

Liao M., Wen H., Yang L., Wang G., Xiang X., Liang X., Improving the model robustness of flood hazard mapping based on hyperparameter optimization of random forest, Expert Systems with Applications (2023).

[45]

Liu J., Gas path fault diagnosis of aircraft engine using HELM and transfer learning, Engineering Applications of Artificial Intelligence 114 (2022).

[46]

Liu S., Wang H., Tang J., Zhang X., Research on fault diagnosis of gas turbine rotor based on adversarial discriminative domain adaption transfer learning, Measurement 196 (2022).

[47]

Longwell J.P., Frost E.E., Weiss M.A., Flame stability in bluff body recirculation zones, Industrial & Engineering Chemistry 45 (8) (1953) 1629–1633. doi: 10.1021/ie50524a019.

[48]

Lotfipoor A., Patidar S., Jenkins D.P., Deep neural network with empirical mode decomposition and Bayesian optimisation for residential load forecasting, Expert Systems with Applications 237 (2024).

[49]

Ma H., Peng T., Zhang C., Ji C., Li Y., Nazir M.S., Developing an evolutionary deep learning framework with random forest feature selection and improved flow direction algorithm for NOx concentration prediction, Engineering Applications of Artificial Intelligence 123 (2023).

[50]

Mondal S., De S., Mukhopadhyay A., Sen S., Ray A., Early prediction of lean blowout from chemiluminescence time series data, Combustion Science and Technology 194 (6) (2020) 1108–1135,.

[51]

Mumtaz W., Xia L., Ali S.S.A., Yasin M.A.M., Hussain M., Malik A.S., Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD), Biomedical Signal Processing and Control 31 (2017) 108–115.

[52]

Naderi E., Khorasani K., Data-driven fault detection, isolation and estimation of aircraft gas turbine engine actuator and sensors, Mechanical Systems and Signal Processing 100 (2018) 415–438.

[53]

Nassini P.C., Pampaloni D., Meloni R., Andreini A., Lean blow-out prediction in an industrial gas turbine combustor through a LES-based CFD analysis, Combustion and Flame 229 (2021).

[54]

Olsson T., Ramentol E., Rahman M., Oostveen M., Kyprianidis K., A data-driven approach for predicting long-term degradation of a fleet of micro gas turbines, Energy and AI 4 (2021).

[55]

OMAR M., Lean blowout fault prediction for dry low emission gas turbine using hybrid of support vector machine and bayesian belief network, (Ph.D. thesis) Universiti Teknologi PETRONAS, 2021.

[56]

Panchal A., Menon S., Large eddy simulation of fuel sensitivity in a realistic spray combustor II. Lean blowout analysis, Combustion and Flame 240 (2022).

[57]

Plee S., Mellor A., Review of flashback reported in prevaporizing/premixing combustors, Combustion and Flame 32 (1978) 193–203.

[58]

Pourbabaee B., Meskin N., Khorasani K., Robust sensor fault detection and isolation of gas turbine engines subjected to time-varying parameter uncertainties, Mechanical Systems and Signal Processing 76 (2016) 136–156.

[59]

Sahu S.K., Pandey M., An optimal hybrid multiclass SVM for plant leaf disease detection using spatial fuzzy C-means model, Expert Systems with Applications 214 (2023).

[60]

Sanaye S., Hosseini S., Prediction of blade life cycle for an industrial gas turbine at off-design conditions by applying thermodynamics, turbo-machinery and artificial neural network models, Energy Reports 6 (2020) 1268–1285.

[61]

Schwagerus A., Habisreuther P., Zarzalis N., Lean-blow-out simulation of natural gas fueled, premixed turbulent jet flame arrays with LES and FGM-modeling, in: Turbo expo: power for land, sea, and air, Vol. 84942, American Society of Mechanical Engineers, 2021.

[62]

Sethuraman R., Sellappan S., Shunmugiah J., Subbiah N., Govindarajan V., Neelagandan S., An optimized AdaBoost multi-class support vector machine for driver behavior monitoring in the advanced driver assistance systems, Expert Systems with Applications 212 (2023).

[63]

Sowkarthika B., Gyanchandani M., Wadhvani R., Shukla S., Data complexity-based dynamic ensembling of SVMs in classification, Expert Systems with Applications 216 (2023).

[64]

Sun L., Huang Y., Wang R., Feng X., Liu Z., Wu J., FV-MP model to predict lean blowout limits for multi-point lean direct injection combustors, Aerospace Science and Technology 88 (2019) 185–192.

[65]

Sun L., Huang Y., Wang X., Zheng Z., Wang R., Feng X., Hybrid method based on flame volume concept for lean blowout limits prediction of aero engine combustors, Chinese Journal of Aeronautics 34 (5) (2021) 425–437,.

[66]

Tian D., Xin H., Xin-chen Z., Numerical simulation research on the lean blowout boundary of the multi-point LDI combustor, Journal of Aeronautics, Astronautics and Aviation 52 (3) (2020) 293–310.

[67]

Virani N., Jha D.K., Ray A., Phoha S., Sequential hypothesis tests for streaming data via symbolic time-series analysis, Engineering Applications of Artificial Intelligence 81 (2019) 234–246.

[68]

Wang Q., Li M., He X., Effect of a passive control strategy on lean ignition and blowout performance of a gas turbine combustor, Applied Thermal Engineering 219 (2023).

[69]

Wang C., Liu W., Bi Z., Li G., Zeng W., Experimental and numerical prediction of LBO performance in a centrally staged combustor, Applied Thermal Engineering 227 (2023).

[70]

Wang N., Yao D., Ma L., Liu M., Multi-site clustering and nested feature extraction for identifying autism spectrum disorder with resting-state fMRI, Medical Image Analysis 75 (2022).

[71]

Wollgarten J.C., Zarzalis N., Turrini F., Peschiulli A., Experimental investigations of ion current in liquid-fuelled gas turbine combustors, International Journal of Spray and Combustion Dynamics 9 (3) (2017) 172–185.

[72]

Wu C.-T., Huang H.-C., Huang S., Chen I.-M., Liao S.-C., Chen C.-K., et al., Resting-state EEG signal for major depressive disorder detection: a systematic validation on a large and diverse dataset, Biosensors 11 (12) (2021) 499.

[73]

Xie J., Sage M., Zhao Y.F., Feature selection and feature learning in machine learning applications for gas turbines: A review, Engineering Applications of Artificial Intelligence 117 (2023).

[74]

Xu H., Fan W., Feng J., Yan P., Qi S., Zhang R., Parameter determination and ion current improvement of the ion current sensor used for flame monitoring, Sensors 21 (3) (2021) 697.

[75]

Zhou H., Zhao J.P., Zheng L.G., Wang C.L., Cen K.F., Modeling NOx emissions from coal-fired utility boilers using support vector regression with ant colony optimization, Engineering Applications of Artificial Intelligence 25 (1) (2012) 147–158.

[76]

Zouhri W., Homri L., Dantan J.-Y., Handling the impact of feature uncertainties on SVM: A robust approach based on sobol sensitivity analysis, Expert Systems with Applications 189 (2022).

[77]

Zukoski E.E., Marble F.E., Experiments concerning the mechanism of flame blowoff from bluff bodies, 1983.

Recommendations

Investigation on Characteristics of an Innovative Lean Burn Catalytic Combustion Gas Turbine
ICEET '09: Proceedings of the 2009 International Conference on Energy and Environment Technology - Volume 01

Fugitive methane, emitted from coal mines, landfill and animal waste etc. into atmosphere, is not only a greenhouse gas, but also a waste energy source if not utilized. This paper investigates a novel lean burn catalytic combustion gas turbine, which ...
Aeroengine Turbine Exhaust Gas Temperature Prediction Using Support Vector Machines
ISNN 2009: Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II

The turbine exhaust gas temperature (EGT) is an important parameter of the aeroengine and it represents the thermal health condition of the aeroengine. By predicting the EGT, the performance deterioration of the aeroengine can be deduced in advance. ...
Coal Face Gas Emission Prediction Based on Support Vector Machine
AICI '09: Proceedings of the 2009 International Conference on Artificial Intelligence and Computational Intelligence - Volume 01

Mine work face gas emission quantity is an important mine design basis, which also has important practical significance for guide mine design, ventilation and safety production. Mine gas emission quantity and work face multi factors have complex non-...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Expert Systems with Applications: An International Journal

Expert Systems with Applications: An International Journal Volume 244, Issue C

Jun 2024

1583 pages

Issue’s Table of Contents

Elsevier Ltd.

Publisher

Pergamon Press, Inc.

United States

Publication History

Published: 02 July 2024

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 24 Dec 2024

Other Metrics

View Author Metrics

Citations

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents