<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article 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" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">RUDN Journal of Engineering Research</journal-id><journal-title-group><journal-title xml:lang="en">RUDN Journal of Engineering Research</journal-title><trans-title-group xml:lang="ru"><trans-title>Вестник Российского университета дружбы народов. Серия: Инженерные исследования</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2312-8143</issn><issn publication-format="electronic">2312-8151</issn><publisher><publisher-name xml:lang="en">Peoples’ Friendship University of Russia named after Patrice Lumumba (RUDN University)</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">51213</article-id><article-id pub-id-type="doi">10.22363/2312-8143-2026-27-2-203-214</article-id><article-id pub-id-type="edn">KZRMZX</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Articles</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Статьи</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">A Method for Predicting the Lifetime of Power Modules of Power Converters Based on the Analysis of Operational Data</article-title><trans-title-group xml:lang="ru"><trans-title>Методика прогнозирования ресурса силовых модулей преобразователей частоты на основе анализа эксплуатационных данных</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0008-5290-2045</contrib-id><contrib-id contrib-id-type="spin">7020-2664</contrib-id><name-alternatives><name xml:lang="en"><surname>Bunin</surname><given-names>Nikita V.</given-names></name><name xml:lang="ru"><surname>Бунин</surname><given-names>Никита Вячеславович</given-names></name></name-alternatives><bio xml:lang="en"><p>PhD Student of the Department of Systems Analysis and Informatics, Institute of Economics, Mathematics and Information Technology</p></bio><bio xml:lang="ru"><p>аспирант кафедры системного анализа и информатики Института экономики, математики и информационных технологий</p></bio><email>cool.buninnikita@yandex.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-1733-2778</contrib-id><contrib-id contrib-id-type="spin">1822-7840</contrib-id><name-alternatives><name xml:lang="en"><surname>Salnikov</surname><given-names>Aleksandr Yu.</given-names></name><name xml:lang="ru"><surname>Сальников</surname><given-names>Александр Юрьевич</given-names></name></name-alternatives><bio xml:lang="en"><p>PhD in Technical Sciences, Associate Professor of the Department of Systems Analysis and Informatics, Institute of Economics, Mathematics and Information Technology</p></bio><bio xml:lang="ru"><p>кандидат технических наук, доцент кафедры системного анализа и информатики, Институт экономики, математики и информационных технологий</p></bio><email>salnikov-ay@ranepa.ru</email><xref ref-type="aff" rid="aff1"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Russian Presidential Academy of National Economy and Public Administration</institution></aff><aff><institution xml:lang="ru">Российская академия народного хозяйства и государственной службы при Президенте Российской Федерации</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2026-07-08" publication-format="electronic"><day>08</day><month>07</month><year>2026</year></pub-date><volume>27</volume><issue>2</issue><issue-title xml:lang="en"/><issue-title xml:lang="ru"/><fpage>203</fpage><lpage>214</lpage><history><date date-type="received" iso-8601-date="2026-07-10"><day>10</day><month>07</month><year>2026</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2026, Bunin N.V., Salnikov A.Y.</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2026, Бунин Н.В., Сальников А.Ю.</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="en">Bunin N.V., Salnikov A.Y.</copyright-holder><copyright-holder xml:lang="ru">Бунин Н.В., Сальников А.Ю.</copyright-holder><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/"/><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://creativecommons.org/licenses/by-nc/4.0</ali:license_ref></license></permissions><self-uri xlink:href="https://journals.rudn.ru/engineering-researches/article/view/51213">https://journals.rudn.ru/engineering-researches/article/view/51213</self-uri><abstract xml:lang="en"><p>In the context of industrial digital transformation, the transition from scheduled preventive maintenance to condition-based maintenance is a key factor in increasing the reliability of electric drives. Industrial frequency converters (FCs) are critical components of process chains; however, existing maintenance procedures are often economically inefficient and do not prevent sudden failures of power electronics. The aim of this study is to develop a methodology for assessing the remaining useful life (RUL) of critical components of industrial frequency converters, namely IGBT modules and DC-link capacitors, based on a hybrid analysis of real-time operational data. The authors combine physical failure models with deep learning algorithms (CNN-LSTM). To overcome the limitations of the closed architecture of industrial controllers, a two-tier data collection system based on edge computing principles is proposed. Diagnostics are performed by indirectly assessing the saturation voltage drift (VCE(ON)) and equivalent series resistance (ESR) through an analysis of spectral distortions in the output current and DC link voltage ripple. A converter technical condition classification matrix with quantitative degradation thresholds has been developed . A numerical experiment based on a historical dataset from a chemical industry plant showed that the proposed hybrid model reduces the RUL prediction error to 12-15% compared to traditional extrapolation methods, enabling the identification of pre-failure conditions conditions 160-200 hours before failure. The implementation of the developed model will enable a full transition to condition-based maintenance, thereby improving the efficiency of maintenance and repair activities.</p></abstract><trans-abstract xml:lang="ru"><p>В условиях цифровой трансформации промышленности переход от планово-предупредительных ремонтов к обслуживанию по фактическому состоянию выступает ключевым фактором повышения надежности электроприводов. Промышленные преобразователи частоты (ПЧ) являются критически важными узлами технологических цепочек, однако существующие регламенты их обслуживания часто экономически неэффективны и не предотвращают внезапные отказы силовой электроники. Цель исследования - разработка методики оценки остаточного полезного ресурса (RUL) критически важных компонентов промышленных преобразователей частоты (IGBT-модулей и конденсаторов звена постоянного тока) на основе гибридного анализа эксплуатационных данных (реального времени). Применено комплексирование физических моделей отказов и алгоритмов глубокого обучения (CNN-LSTM). Для преодоления ограничений закрытой архитектуры промышленных контроллеров предложена двухуровневая система сбора данных на принципах граничных вычислений (Edge Computing). Диагностика выполнена путем косвенной оценки дрейфа напряжения насыщения ( VCE( ON )) и эквивалентного последовательного сопротивления (ESR) через анализ спектральных искажений выходного тока и пульсаций напряжения DC-звена . Сформирована матрица классификации технических состояний преобразователя с количественными пороговыми значениями деградации. Численный эксперимент на массиве исторических данных с предприятия химической промышленности показал, что предложенная гибридная модель снижает ошибку прогнозирования RUL до 12-15 % по сравнению с традиционными методами экстраполяции, позволяя выявлять предаварийные состояния за 160-200 часов до отказа. Внедрение разработанной модели даст возможность полноценного перехода к стратегии обслуживания по фактическому состоянию, повышая эффективность мероприятий, связанных с техническим обслуживанием и ремонтом.</p></trans-abstract><kwd-group xml:lang="en"><kwd>maintenance and repair (MRO)</kwd><kwd>failure prediction</kwd><kwd>predictive maintenance</kwd><kwd>automation</kwd><kwd>diagnostic</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>техническое обслуживание и ремонт</kwd><kwd>ТОиР</kwd><kwd>прогнозирование отказов</kwd><kwd>предиктивное обслуживание</kwd><kwd>автоматизация</kwd><kwd>диагностика</kwd></kwd-group><funding-group><award-group><funding-source><institution-wrap><institution xml:lang="ru">Исследование частично финансировалось предприятиями крупного химического холдинга, компании предоставили данные технологических карт, выгрузки из АСУТП, перечень и паспорта преобразовательной техники, технические регламенты и прочее; в связи с конфиденциальностью данной информации название предприятий не раскрывается.</institution></institution-wrap><institution-wrap><institution xml:lang="en">The study was partially funded by enterprises belonging to a large chemical holding. The participating companies provided process flow sheet data, data exports from automated process control systems (APCS), lists and technical data sheets for converter equipment, technical regulations, and other materials. Due to the confidentiality of this information, the names of the enterprises are not disclosed.</institution></institution-wrap></funding-source></award-group></funding-group></article-meta><fn-group/></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Nagy M, Figura M, Valaskova K, Lăzăroiu G. Predictive maintenance algorithms, artificial intelligence digital twin technologies, and internet of robotic things in big data-driven industry 4.0 manufacturing systems. Mathematics. 2025;13(6):981. https://doi.org/10.3390/math13060981 EDN: NBUSQZ</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>Ramesh K, Raju P, Sasank MVSS. AI-driven pre-dictive maintenance for electric motors: A case study of electric motor scan technology. Grenze International Journal of Engineering and Technology. 2025;11(1):1664-1669. Available from: https://thegrenze.com/index.php?display=page&amp;view=journalabstract&amp;absid=3804&amp;id=8 (accessed: 27.09.2025).</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Constantino-Robles CD, Castillo Leonardo FA, Galván JH, Alvarez YC, Carrera LAI, Rodríguez-Reséndiz J. Vibration-based predictive maintenance for wind turbines: A Prisma-Guided systematic review on methods, applications, and remaining useful life prediction. Applied Mechanics. 2026;7(1):11. https://doi.org/10.3390/applmech7010011</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Tolbert CL. Leveraging variable frequency drive data for nondestructive testing and predictive maintenance in industrial systems. NDT. 2025;3(2):7. https://doi.org/10.3390/NDT3020007</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Ma K, Yang Y, Wang H, Blaabjerg F. Design for reliability of power electronics in renewable energy systems. Use, Operation and Maintenance of Renewable Energy Systems. Springer International Publ.; 2014. p. 295-338. ISBN 978-1-4471-6482-1</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Peyghami S, Wang Z, Blaabjerg F. A guideline for reliability prediction in power electronic converters. IEEE Transactions on Power Electronics. 2020;35(10):10958-10968. https://doi.org/10.1109/TPEL.2020.2981933 EDN: DBTDTN</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>Konkimalla S. AI-based predictive maintenance for electric vehicles: Enhancing reliability and performance.International Journal of Engineering and Computer Science. 2022;11(12):25647-25661. http://doi.org/10.18535/ijecs/v11i12.4713 EDN: KRGEVM</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Jian Y, Chen Z, Peng S, Liu L, Zeng W, Liu J, Liu J, Huang Q. Capacitor aging state evaluation and a remaining-useful-life prediction method based on a CNN-LSTM network considering the impact of parameter dispersion. Electronics. 2025;14(22):4452. https://doi.org/10.3390/electronics14224452 EDN: YZCFEO</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Zhang Z, Chen X. A knowledge-driven method for IGBT remaining useful life prediction using bidirectional learning and physics-enhanced pathformer networks. Journal of Computational Design and Engineering. 2025;12(1):327-344. https://doi.org/10.1093/jcde/qwaf082</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Taoufyq H, El Guemmat K, Mansouri K, Akef F. Predictive maintenance approaches: a systematic literature review. Journal of Industrial Engineering and Management. 2025;18(3):427-458. https://doi.org/10.3926/jiem.8537 EDN: TJXGUY</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Muniandi B, Kulkarni SV, Garg S, Howard E. Real-Time Predictive Maintenance of Power Electronics Systems using Machine Learning and IoT Integration. Naturalista Campano. 2024;28(1):1876-1887. Available from: https://museonaturalistico.it/index.php/journal/article/view/353/276 (accessed: 20.01.2026).</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation>Fassi Y, Heiries V, Boutet J, Boisseau S. Towards physics-informed machine learning based predictive main-tenance for power converters-A review. IEEE Transactions on Power Electronics. 2024;39(2):2692-2720. https://doi.org/10.1109/TPEL.2023.3328438 EDN: PTWZEZ</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation>Ozdagli AI, Koutsoukos X. Model-based damage detection through physics guided learning. Annual Conference of the PHM Society. 2021;13(1). https://doi.org/10.36001/phmconf.2021.v13i1.3012 EDN: YHRKFA</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation>Otuyemi F. Condition monitoring and fault diagnosis of motor-driven systems using electrical signals. [PhD Thesis]. [Huddersfield]: University of Huddersfield; 2018. P. 1-285. Available from: https://pure.hud.ac.uk/ws/portalfiles/portal/67175424/Final_Thesis.pdf (accessed: 13.02.2026).</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation>Butler R, Cui Y, Liu Z, Jaremko T, Hinds S. The Future for Variable Frequency Drive Predictive Maintenance. IEEE IAS Pulp and Paper Industry Conference (PPIC); 2024 09-13 Jun; Charleston, WV, USA. IEEE; 2024. p. 127-132. https://doi.org/10.1109/PPIC57149.2024.10902345</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation>Foube F. Power devices health condition monitoring: A review of recent papers. PHM Society European Conference. 2021;6(1):136-150. https://doi.org/10.36001/phme.2021.v6i1.2808 EDN: ZFUMZA</mixed-citation></ref><ref id="B17"><label>17.</label><mixed-citation>Balakrishna P, Akilezkrishnamurthy A, Mitalkumar K. Enhanced electrical signature analysis for fault detection: Pat.11,639,966 B2 US: G01R 31/34. No. 17/123,456; filed 15.12.2020; publ. 02.05.2023. Available from: https://patents.google.com/patent/US11639966B2/en (accessed: 21.08.2025)</mixed-citation></ref><ref id="B18"><label>18.</label><mixed-citation>Vogl GW, Weiss BA, Donmez MA. Standards for prognostics and health management (PHM) techniques within manufacturing operations. Annual Conference of the PHM Society. 2014;6(1). https://doi.org/10.36001/phmconf.2014.v6i1.2503</mixed-citation></ref><ref id="B19"><label>19.</label><mixed-citation>Baumann T, Garcia R, Papastergiou K, Peftitsis D. Discharge-based condition monitoring for electrolytic DC-link capacitors. IEEE Transactions on Power Electronics. 2024;39(12):16622-16637. https://doi.org/10.1109/tpel.2024.3442077 EDN: LTWSWV</mixed-citation></ref><ref id="B20"><label>20.</label><mixed-citation>Wang H, Blaabjerg F. Power electronics reliability: State of the art and outlook. IEEE Journal of Emerging and Selected Topics in Power Electronics. 2021;9(6):6476-6493. https://doi.org/10.1109/JESTPE.2020.3037161 EDN: PMRQXF</mixed-citation></ref><ref id="B21"><label>21.</label><mixed-citation>Habeeb A. Reducing Downtime in Production Lines Through Proactive Maintenance Strategies. ResearchGate. 2025. Art. 389891476. Available from: https://www.researchgate.net/publication/389891476_Reducing_Downtime_in_Production_Lines_Through_Proactive_Maintenance_Strategies (accessed: 20.12.2025).</mixed-citation></ref><ref id="B22"><label>22.</label><mixed-citation>Smartening up with Artificial Intelligence (AI) : What’s in it for Germany and its Industrial Sector? McKinsey &amp; Company. 2017. Available from: https://www.mckinsey.com/industries/semiconductors/our-insights/smartening-up-with-artificial-intelligence (accessed: 14.02.2026).</mixed-citation></ref></ref-list></back></article>
