НОВЫЙ МЕТОД ПРОГНОЗИРОВАНИЯ ОСТАТОЧНОГО РЕСУРСА ОБОРУДОВАНИЯ ДЛЯ ВЫСОКОЧАСТОТНЫХ ДАННЫХ С НЕОДНОРОДНОЙ ДЛИТЕЛЬНОСТЬЮ РАБОЧИХ ЦИКЛОВ
Ключевые слова:
Турбинные двигатели, управление жизненным циклом промышленного оборудования, остаточный ресурс оборудования, машинное обучение
Аннотация
Достижения в машиностроении позволяют создавать более совершенное и эффек-
тивное оборудование, однако при этом повышается его сложность и требования к управ-
лению его жизненным циклом, техническим обслуживанием. К этому прибавляются тре-
бования по надежности и доступности, которые также создают дополнительные испы-
тания при управлении жизненным циклом. Существуют различные стратегии планирова-
ния технического обслуживания. Среди них наиболее перспективной является предиктив-
ная стратегия, основанная на прогнозировании остаточного ресурса оборудования. Суще-
ствующие методы прогнозирования остаточного ресурса оборудования фокусируются на применении исторических данных, агрегированных по рабочим циклам, при этом отсутст-
вуют широко распространенные методы для прогнозирования по непрерывным данным, в
том числе высокочастотным, получаемым с оборудования и содержащим рабочие циклы
различной длительности и данные, записанные во время простоя оборудования. Для реше-
ния этой проблемы предлагается метод прогнозирования остаточного ресурса с выделе-
нием в исходных данных рабочих циклов и агрегированием их значений в одномерные векто-
ры с целью дальнейшего использования для обучения модели прогнозирования. Результаты
демонстрируют успешную применимость предложенного метода – в комбинации с моде-
лью прогнозирования XGBoost удается достичь точности на данных, полученных с газо-
турбинного двигателя, со значением средней квадратической ошибки 14.02 и средней
ошибкой 10.71.
Литература
1. Kupriyanovskiy V.P., Namiot D.E., Drozhzhinov V.I., Kupriyanovskaya Yu.V., Ivanov M.O.
Internet veshchey na promyshlennykh predpriyatiyakh [Internet of things in industrial enterprises],
International Journal of Open Information Technologies, 2016, No. 12, pp. 156-161.
2. Gunina I.A., SHkarupeta E.V., Reshetov V.V. Proryvnoe tekhnologicheskoe razvitie
promyshlennykh kompleksov v usloviyakh tsifrovoy transformatsii [Breakthrough technological
development of industrial complexes in the context of digital transformation],
Innovatsionnye klastery tsifrovoy ekonomiki: teoriya i praktika [Innovative clusters of the digital
economy: theory and practice], 2018, pp. 535-554.
3. Lysenko S.V., Ten E.V. Ob otsenke ostatochnogo resursa bashennykh kranov [On assessing the
residual life of tower cranes], Problemy sovremennoy nauki i obrazovaniya [Problems of modern
science and education], 2016, No. 1, pp. 98-102.
4. Manasis C., Assimakis N., Vikias V., Ktena A., Stamatelos T. Power Generation Prediction of
an Open Cycle Gas Turbine Using Kalman Filter, Energies, 2020, No. 13, pp. 6692.
5. Antonenko I.N., Kryukov I.E. Informatsionnye sistemy i praktiki TOiR: etapy razvitiya [Information
systems and maintenance and repair practices: stages of development], Avtomatizatsiya
[Automation], 2011, No. 1, pp. 37-44.
6. Chen X., Yan R., Liu Y. Wind turbine condition monitoring and fault diagnosis in China, IEEE
Instrumentation & Measurement Magazine, 2016, No. 19, pp. 22-28.
7. Susto G.A., Schirru A., Pampuri S., McLoone S., Beghi A. Machine learning for predictive
maintenance: A multiple classifier approach, IEEE Transactions on Industrial Informatics,
2014, No. 11, pp. 812-820.
8. Azhmukhamedov I.M., Gostyunin Yu.A. Vybor strategii tekhnicheskogo obsluzhivaniya i remonta
oborudovaniya setey svyazi na predpriyatiyakh neftegazovogo kompleksa [Choice of strategy for
maintenance and repair of communication network equipment at oil and gas enterprises],
Inzhenernyy vestnik Dona [Engineering Bulletin of the Don], 2017, No. 2 (45), pp. 1-10.
9. Say Van Kvong, Shcherbakov M.V. Metod prognozirovaniya ostatochnogo resursa na osnove
obrabotki dannykh mnogoob"ektnykh slozhnykh sistem [A method for forecasting residual life based
on data processing of multi-object complex systems], Prikaspiyskiy zhurnal: upravlenie i vysokie
tekhnologii [Caspian Journal: management and high technologies], 2019, No. 1 (45), pp. 33-44.
10. Zadiran K., Shcherbakov M. New Method of Degradation Process Identification for Reliability-
Centered Maintenance of Energy Equipment, Energies, 2023, No. 16, pp. 575.
11. Cheng J.C., Chen W., Chen K., Wang Q. Data-driven predictive maintenance planning framework
for MEP components based on BIM and IoT using machine learning algorithms, Automation
in Construction, 2020, No. 112, pp. 1-21.
12. Xiongzi C., Jinsong Y., Diyin T. Yingxun W. Remaining useful life prognostic estimation for
aircraft subsystems or components: A review, 10th IEEE International Conference on Electronic
Measurement & Instruments (ICEMI), 2011, pp. 92-94.
13. Zhao J., Gao C., Tang T., Xiao X., Luo M., Yuan B. Overview of Equipment Health State Estimation
and Remaining Life Prediction Methods, Machines, 2022, No. 10, pp. 422.
14. Yan M., Wang X., Wang B., Chang M., Muhammad I. Bearing remaining useful life prediction
using support vector machine and hybrid degradation tracking model, ISA transactions, 2020,
No. 98, pp. 471-482.
15. Nieto P.G., Garcia-Gonzalo E., Lasheras F.S., De Cos Juez F.J. Hybrid PSO–SVM-based
method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability,
Reliability Engineering & System Safety, 2015, No. 138, pp. 219-231.
16. Patil S., Patil A., Handikherkar V., Desai S., Phalle V.M., Kazi F.S. Remaining Useful Life
(RUL) Prediction of Rolling Element Bearing Using Random Forest and Gradient Boosting
Technique, ASME 2018 International Mechanical Engineering Congress and Exposition,
2018, pp. 1-7.
17. Ng S.S., Xing Y., Tsui K.L. A naive Bayes model for robust remaining useful life prediction of
lithium-ion battery, Applied Energy, 2014, No. 118, pp. 114-123.
18. Babu G.S., Zhao P., Li X.L. Deep convolutional neural network based regression approach for
estimation of remaining useful life, In Proceedings of the International Conference on Database
Systems for Advanced Applications (Dallas, TX, USA, 16–19 April 2016), 2016, pp. 214-228.
19. Li X., Ding Q., Sun J. Remaining useful life estimation in prognostics using deep convolution
neural networks, Reliability Engineering & System Safety, 2018, No. 172, pp. 1-11.
20. Che-Sheng H., Jehn-Ruey J. Remaining useful life estimation using long short-term memory
deep, In 2018 IEEE InternationalConference on Applied System Invention (ICASI) (Chiba, Japan).
IEEE, 2018, pp. 58-61.
21. Sagheer A., Kotb M. Unsupervised pre-training of a Deep LSTM-based Stacked Autoencoder
for Multivariate time Series forecasting problems, Scientific Reports, 2019, No. 9, pp. 1-16.
22. Zhang Y., Xin Y., Liu Z.W., Chi M., Ma G. Health status assessment and remaining useful life
prediction of aero-engine based on BiGRU and MMoE, Reliability Engineering & System
Safety, 2022, No. 220, pp. 108-123.
23. Deutsch J., He D. Using deep learning-based approach to predict remaining useful life of rotating
components, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017,
No. 48, pp. 11-20.
24. Wang H.K., Cheng Y., Song K. Remaining Useful Life Estimation of Aircraft Engines Using a
Joint Deep Learning Model Based on TCNN and Transformer, Computational Intelligence and
Neuroscience, 2021, No. 2021, pp. 1-14.
25. NASA Turbofan Jet Engine Data Set. Available at: https://www.kaggle.com/datasets/
behrad3d/nasa-cmaps (accessed 01 April 2023).
26. Zadiran K.S., Shcherbakov M.V., Say Van Kvong. Prognozirovanie ostatochnogo resursa
oborudovaniya v usloviyakh maloy vyborki dannykh [Forecasting the residual life of equipment
in conditions of a small data sample], Upravlenie bol'shimi sistemami [Management of
large systems], 2023, No. 102, pp. 99-113.
27. Shcherbakov M.V. A Survey of Forecast Error Measures, World Applied Sciences Journal
(WASJ), 2013, No. 24, pp. 171-176.
Internet veshchey na promyshlennykh predpriyatiyakh [Internet of things in industrial enterprises],
International Journal of Open Information Technologies, 2016, No. 12, pp. 156-161.
2. Gunina I.A., SHkarupeta E.V., Reshetov V.V. Proryvnoe tekhnologicheskoe razvitie
promyshlennykh kompleksov v usloviyakh tsifrovoy transformatsii [Breakthrough technological
development of industrial complexes in the context of digital transformation],
Innovatsionnye klastery tsifrovoy ekonomiki: teoriya i praktika [Innovative clusters of the digital
economy: theory and practice], 2018, pp. 535-554.
3. Lysenko S.V., Ten E.V. Ob otsenke ostatochnogo resursa bashennykh kranov [On assessing the
residual life of tower cranes], Problemy sovremennoy nauki i obrazovaniya [Problems of modern
science and education], 2016, No. 1, pp. 98-102.
4. Manasis C., Assimakis N., Vikias V., Ktena A., Stamatelos T. Power Generation Prediction of
an Open Cycle Gas Turbine Using Kalman Filter, Energies, 2020, No. 13, pp. 6692.
5. Antonenko I.N., Kryukov I.E. Informatsionnye sistemy i praktiki TOiR: etapy razvitiya [Information
systems and maintenance and repair practices: stages of development], Avtomatizatsiya
[Automation], 2011, No. 1, pp. 37-44.
6. Chen X., Yan R., Liu Y. Wind turbine condition monitoring and fault diagnosis in China, IEEE
Instrumentation & Measurement Magazine, 2016, No. 19, pp. 22-28.
7. Susto G.A., Schirru A., Pampuri S., McLoone S., Beghi A. Machine learning for predictive
maintenance: A multiple classifier approach, IEEE Transactions on Industrial Informatics,
2014, No. 11, pp. 812-820.
8. Azhmukhamedov I.M., Gostyunin Yu.A. Vybor strategii tekhnicheskogo obsluzhivaniya i remonta
oborudovaniya setey svyazi na predpriyatiyakh neftegazovogo kompleksa [Choice of strategy for
maintenance and repair of communication network equipment at oil and gas enterprises],
Inzhenernyy vestnik Dona [Engineering Bulletin of the Don], 2017, No. 2 (45), pp. 1-10.
9. Say Van Kvong, Shcherbakov M.V. Metod prognozirovaniya ostatochnogo resursa na osnove
obrabotki dannykh mnogoob"ektnykh slozhnykh sistem [A method for forecasting residual life based
on data processing of multi-object complex systems], Prikaspiyskiy zhurnal: upravlenie i vysokie
tekhnologii [Caspian Journal: management and high technologies], 2019, No. 1 (45), pp. 33-44.
10. Zadiran K., Shcherbakov M. New Method of Degradation Process Identification for Reliability-
Centered Maintenance of Energy Equipment, Energies, 2023, No. 16, pp. 575.
11. Cheng J.C., Chen W., Chen K., Wang Q. Data-driven predictive maintenance planning framework
for MEP components based on BIM and IoT using machine learning algorithms, Automation
in Construction, 2020, No. 112, pp. 1-21.
12. Xiongzi C., Jinsong Y., Diyin T. Yingxun W. Remaining useful life prognostic estimation for
aircraft subsystems or components: A review, 10th IEEE International Conference on Electronic
Measurement & Instruments (ICEMI), 2011, pp. 92-94.
13. Zhao J., Gao C., Tang T., Xiao X., Luo M., Yuan B. Overview of Equipment Health State Estimation
and Remaining Life Prediction Methods, Machines, 2022, No. 10, pp. 422.
14. Yan M., Wang X., Wang B., Chang M., Muhammad I. Bearing remaining useful life prediction
using support vector machine and hybrid degradation tracking model, ISA transactions, 2020,
No. 98, pp. 471-482.
15. Nieto P.G., Garcia-Gonzalo E., Lasheras F.S., De Cos Juez F.J. Hybrid PSO–SVM-based
method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability,
Reliability Engineering & System Safety, 2015, No. 138, pp. 219-231.
16. Patil S., Patil A., Handikherkar V., Desai S., Phalle V.M., Kazi F.S. Remaining Useful Life
(RUL) Prediction of Rolling Element Bearing Using Random Forest and Gradient Boosting
Technique, ASME 2018 International Mechanical Engineering Congress and Exposition,
2018, pp. 1-7.
17. Ng S.S., Xing Y., Tsui K.L. A naive Bayes model for robust remaining useful life prediction of
lithium-ion battery, Applied Energy, 2014, No. 118, pp. 114-123.
18. Babu G.S., Zhao P., Li X.L. Deep convolutional neural network based regression approach for
estimation of remaining useful life, In Proceedings of the International Conference on Database
Systems for Advanced Applications (Dallas, TX, USA, 16–19 April 2016), 2016, pp. 214-228.
19. Li X., Ding Q., Sun J. Remaining useful life estimation in prognostics using deep convolution
neural networks, Reliability Engineering & System Safety, 2018, No. 172, pp. 1-11.
20. Che-Sheng H., Jehn-Ruey J. Remaining useful life estimation using long short-term memory
deep, In 2018 IEEE InternationalConference on Applied System Invention (ICASI) (Chiba, Japan).
IEEE, 2018, pp. 58-61.
21. Sagheer A., Kotb M. Unsupervised pre-training of a Deep LSTM-based Stacked Autoencoder
for Multivariate time Series forecasting problems, Scientific Reports, 2019, No. 9, pp. 1-16.
22. Zhang Y., Xin Y., Liu Z.W., Chi M., Ma G. Health status assessment and remaining useful life
prediction of aero-engine based on BiGRU and MMoE, Reliability Engineering & System
Safety, 2022, No. 220, pp. 108-123.
23. Deutsch J., He D. Using deep learning-based approach to predict remaining useful life of rotating
components, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017,
No. 48, pp. 11-20.
24. Wang H.K., Cheng Y., Song K. Remaining Useful Life Estimation of Aircraft Engines Using a
Joint Deep Learning Model Based on TCNN and Transformer, Computational Intelligence and
Neuroscience, 2021, No. 2021, pp. 1-14.
25. NASA Turbofan Jet Engine Data Set. Available at: https://www.kaggle.com/datasets/
behrad3d/nasa-cmaps (accessed 01 April 2023).
26. Zadiran K.S., Shcherbakov M.V., Say Van Kvong. Prognozirovanie ostatochnogo resursa
oborudovaniya v usloviyakh maloy vyborki dannykh [Forecasting the residual life of equipment
in conditions of a small data sample], Upravlenie bol'shimi sistemami [Management of
large systems], 2023, No. 102, pp. 99-113.
27. Shcherbakov M.V. A Survey of Forecast Error Measures, World Applied Sciences Journal
(WASJ), 2013, No. 24, pp. 171-176.
