Gas turbine combustion profile modelling for predictive maintenance using an artificial neural network
FARAH Adlina Md Jafrry, MADIAH Binti Omar, MOCHAMMAD Faqih, ROSDIAZLI Bin Ibrahim
download PDFAbstract. Dry Low Emission (DLE) gas turbine has been developed as a solution to encounter the harmful high NOx emission from conventional gas turbine. However, it is prone to create a Lean Blowout (LBO) error that causes frequent shutdown due to its stringent condition that needs to be operate inside its desired operating condition that can be monitored through the temperature, NOx and CO emission concentration. This paper develops an Artificial Neural Network – Multilayer Perceptron (ANN-MLP) predictive maintenance model using actual DLE gas turbine data that predict trips from the gas exhaust emission and classification of warning stages on the LBO error. 94.12% of R2 for the regression model and 100% accuracy of the classification model using Python is obtained using four months period data. This proposed ANN-MLP model manage to predict the suitable maintenance time of DLE gas turbine using real time data which can help reduce cost lost from unscheduled shutdown.
Keywords
DLE Gas Turbine, Predictive Maintenance, Multi-Layer Perceptron (MLP), Artificial Neural Network (ANN)
Published online 5/20/2023, 8 pages
Copyright © 2023 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: FARAH Adlina Md Jafrry, MADIAH Binti Omar, MOCHAMMAD Faqih, ROSDIAZLI Bin Ibrahim, Gas turbine combustion profile modelling for predictive maintenance using an artificial neural network, Materials Research Proceedings, Vol. 29, pp 218-225, 2023
DOI: https://doi.org/10.21741/9781644902516-25
The article was published as article 25 of the book Sustainable Processes and Clean Energy Transition
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] M. Faqih, M.B. Omar, R. Ibrahim, B.A.A., “Dry-Low Emission Gas Turbine Technology: Recent Trends and Challenges”, Applied Sciences 12 (21), 10922, 2022.
https://doi.org/10.3390/app122110922
[2] A.A. Bahashwan, R.B. Ibrahim, M.B. Omar, M. Faqih, “The Lean Blowout Prediction Techniques in Lean Premixed Gas Turbine: An Overview”, Energies 15 (22), 8343, 2022 https://doi.org/10.3390/en15228343
[3] S. Kwak, J. Choi, M. C. Lee, and Y. Yoon, “Predicting instability frequency and amplitude using artificial neural network in a partially premixed combustor,” Energy (Oxf.), vol. 230, no. 120854, p. 120854, 2021. https://doi.org/10.1016/j.energy.2021.120854
[4] I. Parrella, F. Bardi, G. Salerno, D. Gronchi, M. Cannavò, and E. Sparacino, “Using analytics to assess health status of DLE combustion Gas turbines,” in Day 3 Wed, November 13, 2019, 2019. https://doi.org/10.2118/197679-MS
[5] A. Kaluri, P. Malte, and I. Novosselov, “Real-time prediction of lean blowout using chemical reactor network,” Fuel (Lond.), vol. 234, pp. 797-808, 2018. https://doi.org/10.1016/j.fuel.2018.07.065
[6] T. P. Carvalho, F. A. A. M. N. Soares, R. Vita, R. da P. Francisco, J. P. Basto, and S. G. S. Alcalá, “A systematic literature review of machine learning methods applied to predictive maintenance,” Comput. Ind. Eng., vol. 137, no. 106024, p. 106024, 2019. https://doi.org/10.1016/j.cie.2019.106024
[7] M. H. M. Tarik, M. Omar, M. F. Abdullah, and R. Ibrahim, “Modelling of dry low emission gas turbine using black-box approach,” in TENCON 2017 – 2017 IEEE Region 10 Conference, 2017. https://doi.org/10.1109/TENCON.2017.8228169
[8] P. C. Nassini, D. Pampaloni, R. Meloni, and A. Andreini, “Lean blow-out prediction in an industrial gas turbine combustor through a LES-based CFD analysis,” Combust. Flame, vol. 229, no. 111391, p. 111391, 2021. https://doi.org/10.1016/j.combustflame.2021.02.037
[9] Z. Chen, T. Yang, S. Zhang, S. Li, and Z. Ren, “Efficient emission modelling in lean premixed flames with pre-tabulated formation characteristics,” Fuel (Lond.), vol. 301, no. 121043, p. 121043, 2021. https://doi.org/10.1016/j.fuel.2021.121043
[10] Y. Park, M. Choi, X. Li, C. Jung, S. Ahn, and G. Choi, “Fault detection in fuel distribution characteristics of industrial gas turbine combustor using artificial neural network method,” SSRN Electron. J., 2021. https://doi.org/10.2139/ssrn.3874483
[11] M. B. Omar, R. Ibrahim, M. F. Abdullah, and M. H. M. Tarik, “Modelling of Dry-Low Emission Gas Turbine Fuel System using First Principle Data-Driven Method,” Journal of Power Technologies, vol. 100, no. 1, p. 1, 2020.
[12] M. Omar, R. Ibrahim, M.F. Abdullah, M.H.M. Tarik, “Modelling and System Identification of Gas Fuel Valves in Rowen’s Model for Dry Low Emission Gas Turbine, in 2018 IEEE Conference on Big Data and Analytics (ICBDA), pp. 33-37, 2018. https://doi.org/10.1109/ICBDAA.2018.8629705
[13] M. Omar, M.H.M. Tarik, R. Ibrahim, M.F. Abdullah, “Suitability study on using rowen’s model for dry-low emission gas turbine operational performance”, in TENCON 2017-2017 IEEE Region 10 Conference, pp. 1925-1930, 2017. https://doi.org/10.1109/TENCON.2017.8228173
[14] M. Faqih, M.B. Omar, R.B. Ibrahim, “Development of Rowen’s Model for Dry-Low Emission Gas Turbine Dynamic Simulation using Scilab”, in 2022 IEEE 5th International Symposium in Robotics and Manufacturing Automation (ROMA), IEEE, pp. 1-5, 2022. https://doi.org/10.1109/ROMA55875.2022.9915695
[15] D. Huang, S. Tang, and D. Zhou, “A Nitrogen Oxides emission prediction model for gas turbines based on interpretable multilayer perceptron neural networks,” in Volume 9: Oil and Gas Applications; Organic Rankine Cycle Power Systems; Steam Turbine, 2020. https://doi.org/10.1115/GT2020-15478
[16] Z. Liu and I. A. Karimi, “Gas turbine performance prediction via machine learning,” Energy (Oxf.), vol. 192, no. 116627, p. 116627, 2020. https://doi.org/10.1016/j.energy.2019.116627
[17] Kirubakaran and N. Shankar, “Prediction of lean blowout performance on variation of combustor inlet area ratio for micro gas turbine combustor,” Aircr. Eng. Aerosp. Technol., vol. 93, no. 5, pp. 915-924, 2021. https://doi.org/10.1108/AEAT-02-2021-0042
[18] M. Salehi, H. Eivazi, M. Tahani, and M. Masdari, “Analysis and prediction of gas turbine performance with evaporative cooling processes by developing a stage stacking algorithm,” J. Clean. Prod., vol. 277, no. 122666, p. 122666, 2020. https://doi.org/10.1016/j.jclepro.2020.122666
[19] O. I. Abiodun et al., “Comprehensive review of artificial neural network applications to pattern recognition,” IEEE Access, vol. 7, pp. 158820-158846, 2019. https://doi.org/10.1109/ACCESS.2019.2945545
[20] B. Akkaya and N. Çolakoğlu, “Comparison of Multi-class Classification Algorithms on Early Diagnosis of Heart Diseases.”
[21] A. Smiti, “A critical overview of outlier detection methods,” Comput. Sci. Rev., vol. 38, no. 100306, p. 100306, 2020. https://doi.org/10.1016/j.cosrev.2020.100306
[22] A. I. Abubakar, H. Chiroma, and S. Abdulkareem, “Comparing performances of neural network models built through transformed and original data,” in 2015 International Conference on Computer, Communications, and Control Technology (I4CT), 2015. https://doi.org/10.1109/I4CT.2015.7219599
[23] M. Chmielewski and M. Gieras, “Small gas turbine gtm-120 bench testing with emission measurements,” J. KONES Powertrain Transp., vol. 22, no. 1, pp. 47-54, 2015. https://doi.org/10.5604/12314005.1161610
[24] M.H.M. Tarik, M. Omar, M.F. Abdullah, R. Ibrahim, “Optimization of neural network hyperparameters for gas turbine modelling using Bayesian optimization”, IET Digital Library, pp. 10-15, 2018. https://doi.org/10.1049/cp.2018.1308
[25] A.A. Bahashwan, R.B. Ibrahim, M.B. Omar, M. Faqih, “Data-driven lean blowout prediction based on industrial dry low emission gas turbine dataset Using decision tree”, 2022 IEEE Industrial Electronics and Applications Conference (IEACon), 90-93, 2022. https://doi.org/10.1109/IEACon55029.2022.9951749
