<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">caht</journal-id><journal-title-group><journal-title xml:lang="ru">Научный вестник МГТУ ГА</journal-title><trans-title-group xml:lang="en"><trans-title>Civil Aviation High Technologies</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2079-0619</issn><issn pub-type="epub">2542-0119</issn><publisher><publisher-name>Moscow State Technical University of Civil Aviation (MSTU CA)</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.26467/2079-0619-2024-27-6-21-41</article-id><article-id custom-type="elpub" pub-id-type="custom">caht-2465</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ТРАНСПОРТНЫЕ СИСТЕМЫ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>TRANSPORTATION SYSTEMS</subject></subj-group></article-categories><title-group><article-title>Методика диагностирования технического состояния авиационных газотурбинных двигателей с применением рекуррентных нейронных сетей (RNN) и длинно-краткосрочной памяти (LSTM)</article-title><trans-title-group xml:lang="en"><trans-title>Methodology for diagnosing the technical condition of aviation gas turbine engines using recurrent neural networks (RNN) and long short-term memory networks (LSTM)</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Машошин</surname><given-names>О. Ф.</given-names></name><name name-style="western" xml:lang="en"><surname>Mashoshin</surname><given-names>O. F.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Машошин Олег Федорович, доктор технических наук, профессор, заведующий кафедрой двигателей летательных аппаратов</p><p>г. Москва</p></bio><bio xml:lang="en"><p>Oleg F. Mashoshin, Doctor of Technical Sciences, Professor, The Head of the Aircraft Engines Chair</p><p>Moscow</p></bio><email xlink:type="simple">o.mashoshin@mstuca.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гусейнов</surname><given-names>Г.</given-names></name><name name-style="western" xml:lang="en"><surname>Huseynov</surname><given-names>H.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Гусейнов Гусейн, аспирант кафедры двигателей летательных аппаратов</p><p>г. Москва</p></bio><bio xml:lang="en"><p>Huseyn Huseynov, Postgraduate Student, Aircraft Engines Chair</p><p>Moscow</p></bio><email xlink:type="simple">khuseyn.21@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Засухин</surname><given-names>А. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Zasukhin</surname><given-names>A. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Засухин Александр Сергеевич, начальник учебно-тренажерного центра, старший преподаватель кафедры двигателей летательных аппаратов</p><p>г. Москва</p></bio><bio xml:lang="en"><p>Aleksandr S. Zasukhin, The Head of the Training and Simulator Center, Senior Lecturer, Aircraft Engines Chair</p><p>Moscow</p></bio><email xlink:type="simple">a.zasuhin@mstuca.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Московский государственный технический университет гражданской авиации</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Moscow State Technical University of Civil Aviation</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>11</day><month>01</month><year>2025</year></pub-date><volume>27</volume><issue>6</issue><fpage>21</fpage><lpage>41</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Машошин О.Ф., Гусейнов Г., Засухин А.С., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Машошин О.Ф., Гусейнов Г., Засухин А.С.</copyright-holder><copyright-holder xml:lang="en">Mashoshin O.F., Huseynov H., Zasukhin A.S.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://avia.mstuca.ru/jour/article/view/2465">https://avia.mstuca.ru/jour/article/view/2465</self-uri><abstract><p>В данной работе представлена методика диагностирования технического состояния авиационных газотурбинных двигателей (ГТД) с использованием рекуррентных нейронных сетей (RNN) и сетей с длиннократкосрочной памятью (LSTM). Основное внимание уделено сравнению эффективности данных моделей для прогноза ключевых параметров работы ГТД, таких как вибрации, температуры газа перед турбиной и частоты вращения роторов низкого и высокого давления. В процессе исследования проведена тщательная очистка и нормализация данных, включающая обработку пропущенных значений, нормализацию методом Min-Max Scaling, удаление выбросов, декорреляцию данных и сглаживание временных рядов. Модели RNN и LSTM были обучены на основе алгоритма обратного распространения ошибки через время (BPTT) для точного прогноза параметров работы ГТД. Результаты показывают, что обе модели демонстрируют высокую точность прогноза, но модели RNN показывают лучшие результаты по большинству параметров. Для вибрационных параметров (VIB_N1FNT1, VIB_N1FNT2, VIB_N2FNT1 и VIB_N2FNT2) модели RNN показали более низкие значения RMSE и MAE, подтверждая их высокую точность. Для температурных параметров (EGT1 и EGT2) модели RNN также продемонстрировали более высокие показатели точности. В то же время модели LSTM показали лучшие результаты для некоторых параметров частоты вращения роторов низкого и высокого давления (N21 и N22). Выводы работы подчеркивают необходимость выбора подходящей модели в зависимости от характера данных и специфики параметров, которые необходимо прогнозировать. Будущие исследования могут быть направлены на разработку гибридных подходов, объединяющих преимущества обеих моделей для достижения наилучших результатов диагностики технического состояния авиационных ГТД.</p></abstract><trans-abstract xml:lang="en"><p>This study presents a method for diagnosing the technical condition of aviation gas turbine engines (GTE) using recurrent neural networks (RNN) and long short-term memory networks (LSTM). The primary focus is on comparing the effectiveness of these models for forecasting key operating parameters of GTEs, such as vibrations, turbine-inlet temperatures, and rotor speeds of low and high pressure. The research involved thorough data cleaning and normalization, including handling missing values, normalization using Min-Max Scaling, outlier removal, data decorrelation, and time series smoothing. The RNN and LSTM models were trained using the backpropagation through time (BPTT) algorithm to accurately forecast GTE operating parameters. The results show that both models demonstrate high forecasting accuracy, but the RNN models perform better in most parameters. For vibration parameters (VIB_N1FNT1, VIB_N1FNT2, VIB_N2FNT1, and VIB_N2FNT2), RNN models achieved lower RMSE and MAE values, confirming their higher accuracy. For temperature parameters (EGT1 and EGT2), RNN models also showed higher accuracy rates. Meanwhile, LSTM models achieved better results for some rotor speed parameters (N21 and N22). The findings emphasize the necessity of choosing the appropriate model based on the nature of data and the specifics of the parameters to be forecast. Future research may focus on developing hybrid approaches that combine the advantages of both models to achieve optimal results in diagnosing the technical condition of GTEs.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>безопасность полетов</kwd><kwd>диагностика авиационных газотурбинных двигателей</kwd><kwd>рекуррентные нейронные сети</kwd><kwd>длинно-краткосрочная память</kwd><kwd>прогноз параметров</kwd><kwd>вибрация</kwd><kwd>компрессор</kwd><kwd>турбина</kwd><kwd>алгоритм BPTT</kwd></kwd-group><kwd-group xml:lang="en"><kwd>flight safety</kwd><kwd>gas turbine engine diagnostics</kwd><kwd>recurrent neural networks</kwd><kwd>long short-term memory</kwd><kwd>parameter forecasting</kwd><kwd>vibration</kwd><kwd>compressor</kwd><kwd>turbine</kwd><kwd>BPTT algorithm</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Fentaye A.D., Zaccaria V., Kyprianidis K. Aircraft engine performance monitoring and diagnostics based on deep convolutional neural networks [Электронный ресурс] // Machines. 2021. Vol. 9, iss. 12. ID: 337. DOI: 10.3390/machines9120337 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Fentaye, A.D., Zaccaria, V., Kyprianidis, K. (2021). Aircraft engine performance monitoring and diagnostics based on deep convolutional neural networks. Machines, vol. 9, issue 12, ID: 337. DOI: 10.3390/machines9120337 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Al-Tekreeti W.K.F., Kashyzadeh K.R., Ghorbani S. Advancements in gas turbine fault detection: a machine learning approach based on the temporal convolutional network-autoencoder model [Электронный ресурс] // Applied Sciences. 2024. Vol. 14, iss. 11. ID: 4551. DOI: 10.3390/app14114551 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Al-Tekreeti, W.K.F., Kashyzadeh, K.R., Ghorbani, S. (2024). Advancements in gas turbine fault detection: a machine learning approach based on the temporal convolutional network-autoencoder model. Applied Sciences, vol. 14, issue 11, ID: 4551. DOI: 10.3390/app14114551 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Berghout T. ProgNet: A transferable deep network for aircraft engine damage propagation prognosis under real flight conditions / T. Berghout, M.-D. Mouss, L.-H. Mouss, M. Benbouzid [Электронный ресурс] // Aerospace. 2023. Vol. 10, iss. 1. ID: 10. DOI: 10.3390/aerospace10010010 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Berghout, T., Mouss, M.-D., Mouss, L.-H., Benbouzid, M. (2023). ProgNet: A transferable deep network for aircraft engine damage propagation prognosis under real flight conditions. Aerospace, vol. 10, issue 1, ID: 10. DOI: 10.3390/aerospace10010010 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Hochreiter S., Schmidhuber J. Long short-term memory // Neural computation. 1997. Vol. 9, iss. 8. Pp. 1735–1780. DOI: 10.1162/neco.1997.9.8.1735</mixed-citation><mixed-citation xml:lang="en">Hochreiter, S., Schmidhuber, J. (1997). Long short-term memory. Neural computation, vol. 9, issue 8, pp. 1735–1780. DOI: 10.1162/neco.1997.9.8.1735</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Zhao J., Li Y.-G., Sampath S. Convolutional neural network denoising autoencoders for intelligent aircraft engine gas path health signal noise filtering [Электронный ресурс] // Journal of Engineering for Gas Turbines and Power. 2023. Vol. 145, iss. 6. ID: 061013. DOI: 10.1115/1.4056128 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Zhao, J., Li, Y.-G., Sampath, S. (2023). Convolutional neural network denoising autoencoders for intelligent aircraft engine gas path health signal noise filtering. Journal of Engineering for Gas Turbines and Power, vol. 145, issue 6, ID: 061013. DOI: 10.1115/1.4056128 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Garg S., Simon D. Challenges in aircraft engine gas path health management [Электронный ресурс] // Proceedings of the Tutorial on Aircraft Engine Control and Gas Path Health Management, Cleveland, OH, USA, 2012. 64 p. URL: https://ntrs.nasa.gov/api/citations/20150009565/downloads/20150009565.pdf (дата обращения: 15.02.2024).</mixed-citation><mixed-citation xml:lang="en">Garg, S., Simon, D. (2012). Challenges in aircraft engine gas path health management. In: Proceedings of the Tutorial on Aircraft Engine Control and Gas Path Health Management, Cleveland, OH, USA, 64 p. Available at: https:// ntrs.nasa.gov/api/citations/20150009565/downloads/20150009565.pdf (accessed: 15.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Mohammadi R. Fault diagnosis of gas turbine engines by using dynamic neural networks / R. Mohammadi, E. Naderi, K. Khorasani, S. Hashtrudi-Zad // 2011 IEEE International Conference on Quality and Reliability. Bangkok, Thailand, 2011. Pp. 25–30. DOI: 10.1109/ICQR.2011.6031675</mixed-citation><mixed-citation xml:lang="en">Mohammadi, R., Naderi, E., Khorasani, K., Hashtrudi-Zad, S. (2011). Fault diagnosis of gas turbine engines by using dynamic neural networks. 2011 IEEE International Conference on Quality and Reliability. Bangkok, Thailand, pp. 25–30. DOI: 10.1109/ICQR.2011.6031675</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Goodfellow I., Bengio Y. Courville A. Deep learning. The MIT Press, 2016. 800 p.</mixed-citation><mixed-citation xml:lang="en">Goodfellow, I., Bengio, Y. Courville, A. (2016). Deep learning. The MIT Press, 800 p.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Clifton D. Condition monitoring of gasturbine engines [Электронный ресурс] // Transfer Report. Department of Engineering Science, University of Oxford, 2006. 60 p. URL: https://www.robots.ox.ac.uk/~davidc/pubs/transfer.pdf (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Clifton, D. (2006). Condition monitoring of gas-turbine engines. Transfer Report, Department of Engineering Science, University of Oxford, 60 p. Available at: https://www.robots.ox.ac.uk/~davidc/pubs/transfer.pdf (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Upadhyay A. A deep-learning-based approach for aircraft engine defect detection / A. Upadhyay, J. Li, S. King, S. Addepalli [Электронный ресурс] // Machines. 2023. Vol. 11, iss. 2. ID: 192. DOI: 10.3390/machines11020192 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Upadhyay, A., Li, J., King, S., Addepalli, S. (2023). A deep-learning-based approach for aircraft engine defect detection. Machines, vol. 11, issue 2, ID: 192. DOI: 10.3390/machines11020192 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Zhou D. Fault diagnosis of gas turbine based on partly interpretable convolutional neural networks / D. Zhou, Q. Yao, H. Wu, S. Ma, H. Zhang [Электронный ресурс] // Energy. 2020. Vol. 200. ID: 117467. DOI: 10.1016/j.energy.2020.117467 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Zhou, D., Yao, Q., Wu, H., Ma, S., Zhang, H. (2020). Fault diagnosis of gas turbine based on partly interpretable convolutional neural networks. Energy, vol. 200, ID: 117467. DOI: 10.1016/j.energy.2020.117467 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Falsetti C., Sisti M., Beard P.F. Infrared thermography and calibration techniques for gas turbine applications: A review [Электронный ресурс] // Infrared Physics &amp; Technology. 2021. Vol. 113. ID: 103574. DOI: 10.1016/j.infra red.2020.103574 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Falsetti, C., Sisti, M., Beard, P.F. (2021). Infrared thermography and calibration techniques for gas turbine applications: A review. Infrared Physics &amp; Technology, vol. 113, ID: 103574. DOI: 10.1016/j.infrared.2020.103574 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Zhao F. Gas turbine exhaust system health management based on recurrent neural networks / F. Zhao, L. Chen, T. Xia, Z. Ye, Y. Zheng // Procedia CIRP. 2019. Vol. 83, no. 12. Pp. 630–635. DOI: 10.1016/j.procir.2019.04.122</mixed-citation><mixed-citation xml:lang="en">Zhao, F., Chen, L., Xia, T., Ye, Z., Zheng, Y. (2019). Gas turbine exhaust system health management based on recurrent neural networks. Procedia CIRP, vol. 83, no. 12, pp. 630–635. DOI: 10.1016/j.procir.2019.04.122</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Pitkänen J. NDT methods for revealing anomalies and defects in gas turbine blades / J. Pitkänen, T. Hakkarainen, H. Jeskanen, P. Kuusinen, K. Lahdenperä, P. Särkiniemi [Электронный ресурс] // 15th World Conference on Nondestructive Testing. Italy, Roma, 15–21 October 2000. URL: https://www.ndt.net/article/wcndt00/papers/idn629/idn629.htm (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Pitkänen, J., Hakkarainen, T., Jeskanen, H., Kuusinen, P., Lahdenperä, K., Särkiniemi, P. (2000). NDT methods for revealing anomalies and defects in gas turbine blades. In: 15th World Conference on Nondestructive Testing, Italy, Roma, 15–21 October. Available at: https://www.ndt.net/article/wcndt00/papers/idn629/idn629.htm (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Loboda I. Neural networks for gas turbine diagnosis [Электронный ресурс] // Artificial Neural Networks-Models and Applications, 2016. DOI: 10.5772/63107 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Loboda, I. (2016). Neural networks for gas turbine diagnosis. In book: Artificial Neural Networks-Models and Applications. DOI: 10.5772/63107 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Pineda F.J. Generalization of backpropagation to recurrent neural networks [Электронный ресурс] // Physical Review Letters. 1987. Vol. 59, iss. 19. ID: 2229. DOI: 10.1103/PhysRevLett.59.2229 (дата обращения: 27.02.2024).</mixed-citation><mixed-citation xml:lang="en">Pineda, F.J. (1987). Generalization of back-propagation to recurrent neural networks. Physical Review Letters, vol. 59, issue 19, ID: 2229. DOI: 10.1103/PhysRevLett.59.2229 (accessed: 27.02.2024).</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Панков Е.А., Чайка Н.Ф. Возможности спектральных методов для диагностики авиационных двигателей // Интерэкспо Гео-Сибирь. 2016. № 9. С. 8–13.</mixed-citation><mixed-citation xml:lang="en">Pankov, E.A., Chayka, N.F. (2016). The possibilities of spectral methodes for aircraft engines diagnosis. Interexpo Geo-Siberia, no. 9, pp. 8–13. (in Russian)</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
