<?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">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2025-25-3-536-544</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-477</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>МАТЕМАТИЧЕСКОЕ И КОМПЬЮТЕРНОЕ МОДЕЛИРОВАНИЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>MODELING AND SIMULATION</subject></subj-group></article-categories><title-group><article-title>Комбинированный подход к детектированию неисправностей в сложных технических системах на основе модели бонд-графа</article-title><trans-title-group xml:lang="en"><trans-title>Combined approach to fault detection in complex technical systems based on bond-graph model</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0007-5568-498X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Дмитриев</surname><given-names>В. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Dmitriev</surname><given-names>V. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Дмитриев Валентин Алексеевич — руководитель практики</p><p>Санкт-Петербург, 191181;</p><p>Аспирант</p><p>Санкт-Петербург, 197101</p></bio><bio xml:lang="en"><p>Valentin A. Dmitriev — Head of the Practice</p><p>Saint Petersburg, 191181;</p><p>PhD Student</p><p>Saint Petersburg, 197101</p></bio><email xlink:type="simple">valentinswsu@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-5611-8812</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Марусина</surname><given-names>М. Я.</given-names></name><name name-style="western" xml:lang="en"><surname>Marusina</surname><given-names>M. Ya.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Марусина Мария Яковлевна — доктор технических наук, профессор, профессор</p><p>Санкт-Петербург, 197101</p><p>sc 56281574700</p></bio><bio xml:lang="en"><p>Maria Ya. Marusina — D.Sc., Full Professor</p><p>Saint Petersburg, 197101</p><p>sc 56281574700</p></bio><email xlink:type="simple">myamarusina@itmo.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Ассоциация «Цифровые технологии в промышленности»;&#13;
Университет ИТМО</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Association of Digital Technologies in Industry;&#13;
ITMO University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Университет ИТМО</institution><country>Россия</country></aff><aff xml:lang="en"><institution>ITMO University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>03</day><month>07</month><year>2025</year></pub-date><volume>25</volume><issue>3</issue><fpage>536</fpage><lpage>544</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Дмитриев В.А., Марусина М.Я., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Дмитриев В.А., Марусина М.Я.</copyright-holder><copyright-holder xml:lang="en">Dmitriev V.A., Marusina M.Y.</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://ntv.elpub.ru/jour/article/view/477">https://ntv.elpub.ru/jour/article/view/477</self-uri><abstract><p>Введение. Разработан и исследован новый подход к детектированию неисправностей для сложных технических систем, позволяющий определить и классифицировать одиночные и множественные одновременные неисправности. Решена задача надежной и своевременной идентификации как одиночных, так и множественных одновременных неисправностей в условиях ограниченного доступа к размеченным данным. Угроза безопасной работе автономной техники является типичной проблемой для полевых условий эксплуатации, в которых традиционные подходы, основанные на моделях или данных, применяемых по отдельности, оказываются неэффективным.Метод. В работе представлен комбинированный подход к детектированию неисправностей. Предложенное решение сочетает в себе аналитическую модель бонд-графа и сверточную нейронную сеть. Бонд-граф формирует остатки — разницу между значениями, рассчитанными по физическим законам системы, и измерениями с датчиков. Остатки анализируются сверточной нейронной сетью, которая обучается выявлять и классифицировать неисправности по их характерным особенностям. Для учета неопределенности параметров (например, сопротивления или емкости) использовано линейное дробное преобразование. Такой подход позволяет объединить априорные знания о физике системы с возможностями глубокого обучения.Основные результаты. Эффективность подхода оценена на симуляторе гидравлической системы управления поворотным механизмом автономной техники. В симуляцию добавлен гауссовский шум для имитации реальных условий. Эксперименты включали начальные, ступенчатые, одиночные и множественные неисправности. Тесты с разными объемами обучающих данных при выборке менее 128 образцов показали более высокую эффективность предложенного комбинированного подхода по сравнению с классическими методами машинного обучения, такими как Random Forest или K-Nearest Neighbors). Предложено решение для детектирования неисправностей в гидравлических системах управления автономной техникой.Обсуждение. Разработанный подход особенно эффективен при ограниченных данных, что делает его пригодным для полевых условий. Он позволяет своевременно выявлять и классифицировать неисправности (например, утечки в клапанах или сбои электромагнитных задвижек), что снижает риск отказов и обеспечивает безопасность автономной техники. Результаты могут быть адаптированы и внедрены для электрических, механических и прочих сложных технических систем.</p></abstract><trans-abstract xml:lang="en"><p>A new fault detection approach for complex technical systems has been developed and investigated, enabling the identification and classification of single and multiple simultaneous faults. The challenge of reliable and timely identification of both single and multiple simultaneous faults under conditions of limited access to labeled data has been addressed. A threat to the safe operation of autonomous equipment is a common challenge in the field operating conditions where traditional model-based or data-driven approaches, used individually, prove to be ineffective. This work presents a hybrid approach to fault detection. The proposed solution combines an analytical bond-graph model and a Convolutional Neural Network (CNN). The bond-graph generates residuals — the difference between values calculated based on the system physical laws and sensor measurements. The residuals are then analyzed by the CNN which is trained to detect and classify faults based on their characteristic features. Linear Fractional Transformation is employed to account for parameter uncertainties (e.g., resistance or capacitance). This approach allows combining a priori knowledge of the system physics with the capabilities of deep learning. The effectiveness of the approach was evaluated on a simulator of a hydraulic steering control system for autonomous equipment. Gaussian noise was added to the simulation to simulate real-world conditions. The experiments included incipient, abrupt, single, and multiple faults. Tests with varying amounts of training data, using sample sizes less than 128, demonstrated the higher effectiveness of the proposed hybrid approach compared to classical machine learning methods (such as Random Forest or K-Nearest Neighbors). A solution is proposed for fault detection in hydraulic control systems of autonomous equipment. The developed approach is particularly effective with limited data, making it suitable for field conditions. It allows for timely detection and classification of faults (e.g., valve leaks or solenoid valve failures), which reduces the risk of failures and ensures the safety of autonomous equipment. The results can be adapted and implemented for electrical, mechanical, and other complex technical systems.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>детектирование неисправностей</kwd><kwd>бонд-граф</kwd><kwd>сверточная нейронная сеть</kwd><kwd>линейное дробное преобразование</kwd><kwd>технические системы</kwd></kwd-group><kwd-group xml:lang="en"><kwd>fault detection</kwd><kwd>bond-graph</kwd><kwd>convolutional neural network</kwd><kwd>linear fractional transformation</kwd><kwd>technical systems</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">Bouamama B.O., Biswas G., Loureiro R., Merzouki R. Graphical methods for diagnosis of dynamic systems: Review // Annual reviews in control. 2014. V. 38. N 2. P. 199–219. https://doi.org/10.1016/j.arcontrol.2014.09.004</mixed-citation><mixed-citation xml:lang="en">Bouamama B.O., Biswas G., Loureiro R., Merzouki R. Graphical methods for diagnosis of dynamic systems: Review. Annual reviews in control, 2014, vol. 38, no. 2, pp. 199–219. https://doi.org/10.1016/j.arcontrol.2014.09.004</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Isermann R. Fault-Diagnosis Applications: Model-Based Condition Monitoring: Actuators, Drives, Machinery, Plants, Sensors, and Fault-Tolerant Systems. Springer Science &amp; Business Media, 2011. 354 p.</mixed-citation><mixed-citation xml:lang="en">Isermann R. Fault-Diagnosis Applications: Model-Based Condition Monitoring: Actuators, Drives, Machinery, Plants, Sensors, and FaultTolerant Systems. Springer Science &amp; Business Media, 2011, 354 p.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Chen J., Patton R.J. Robust Model-Based Fault Diagnosis for Dynamic Systems. Springer Science &amp; Business Media, 2012. V. 3. 356 p.</mixed-citation><mixed-citation xml:lang="en">Chen J., Patton R.J. Robust Model-Based Fault Diagnosis for Dynamic Systems. Springer Science &amp; Business Media, 2012, vol. 3, 356 p.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Ding S.X. Model-Based Fault Diagnosis Techniques: Design Schemes, Algorithms and Tools. Springer Science &amp; Business Media, 2012. 504 p.</mixed-citation><mixed-citation xml:lang="en">Ding S.X. Model-Based Fault Diagnosis Techniques: Design Schemes, Algorithms and Tools. Springer Science &amp; Business Media, 2012. 504 p.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Akhenak A., Duviella E., Bako L., Lecoeuche S. Online fault diagnosis using recursive subspace identification: application to a dam-gallery open channel system // Control Engineering Practice. 2013. V. 21. N 6. P. 797–806. https://doi.org/10.1016/j.conengprac.2013.02.013</mixed-citation><mixed-citation xml:lang="en">Akhenak A., Duviella E., Bako L., Lecoeuche S. Online fault diagnosis using recursive subspace identification: application to a dam-gallery open channel system. Control Engineering Practice, 2013, vol. 21, no. 6, pp. 797–806. https://doi.org/10.1016/j.conengprac.2013.02.013</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Lei Y., Yang B., Jiang X., Jia F., Li N., Nandi A.K. Applications of machine learning to machine fault diagnosis: a review and roadmap // Mechanical Systems and Signal Processing. 2020. V. 138. P. 106587. https://doi.org/10.1016/j.ymssp.2019.106587</mixed-citation><mixed-citation xml:lang="en">Lei Y., Yang B., Jiang X., Jia F., Li N., Nandi A.K. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mechanical Systems and Signal Processing, 2020, vol. 138, pp. 106587. https://doi.org/10.1016/j.ymssp.2019.106587</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Xu G., Yu Z., Lu N., Lv G. High-gain observer-based sliding mode control for hydraulic excavators // Journal of Harbin Engineering University. 2021. V. 42. N 6. P. 885–892.</mixed-citation><mixed-citation xml:lang="en">Xu G., Yu Z., Lu N., Lv G. High-gain observer-based sliding mode control for hydraulic excavators. Journal of Harbin Engineering University, 2021, vol. 42, no. 6, pp. 885–892.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Shen W., Yuan X., Liu M. Event-triggered control for hydraulic position tracking system with extended state observer // Journal of Mechanical Engineering. 2022. V. 58. N 8. P. 274–284. https://doi.org/10.3901/JME.2022.08.274</mixed-citation><mixed-citation xml:lang="en">Shen W., Yuan X., Liu M. Event-triggered control for hydraulic position tracking system with extended state observer. Journal of Mechanical Engineering. 2022, vol. 58, no. 8, pp. 274–284. (in Chinese). https://doi.org/10.3901/JME.2022.08.274</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Nasiri S., Khosravani M.R., Weinberg K. Fracture mechanics and mechanical fault detection by artificial intelligence methods: a review // Engineering Failure Analysis. 2017. V. 81. P. 270–293. https://doi.org/10.1016/j.engfailanal.2017.07.011</mixed-citation><mixed-citation xml:lang="en">Nasiri S., Khosravani M.R., Weinberg K. Fracture mechanics and mechanical fault detection by artificial intelligence methods: a review. Engineering Failure Analysis, 2017, vol. 81, pp. 270–293. https://doi.org/10.1016/j.engfailanal.2017.07.011</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Hu Z., Zhao G., Li F., Zhou D. Fault diagnosis for nonlinear dynamical system based on adaptive unknown input observer // Control and Decisions. 2016. V. 31. N 5. P. 901–906.</mixed-citation><mixed-citation xml:lang="en">Hu Z., Zhao G., Li F., Zhou D. Fault diagnosis for nonlinear dynamical system based on adaptive unknown input observer. Control and Decisions, 2016, vol. 31, no. 5, pp. 901–906.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Liu Y., Sun C., Chen Y., Lin G. Design and application on sliding mode controller for roller microporous system based on disturbance observer // Forging and Stamping Technology. 2022. V. 47. N 3. P. 116–120.</mixed-citation><mixed-citation xml:lang="en">Liu Y., Sun C., Chen Y., Lin G. Design and application on sliding mode controller for roller microporous system based on disturbance observer. Forging and Stamping Technology, 2022, vol. 47, no. 3, pp. 116–120. (in Chinese)</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Bohagen B., Gravdahl J.T. Active surge control of compression system using drive torque // Automatica. 2008. V. 44. N 4. P. 1135–1140. https://doi.org/10.1016/j.automatica.2007.11.002</mixed-citation><mixed-citation xml:lang="en">Bohagen B., Gravdahl J.T. Active surge control of compression system using drive torque. Automatica, 2008, vol. 44, no. 4, pp. 1135–1140. https://doi.org/10.1016/j.automatica.2007.11.002</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Дмитриев В.А., Марусина М.Я. Особенности построения бонд-графа шагающих роботов // Известия высших учебных заведений. Приборостроение. 2024. Т. 67. № 2. С. 195–199. https://doi.org/10.17586/0021-3454-2024-67-2-195-199</mixed-citation><mixed-citation xml:lang="en">Dmitriev V.A., Marusina M.Ya. Features of constructing a bond graph of walking robots. Journal of Instrument Engineering, 2024, vol. 67, no. 2, pp. 195–199. (in Russian). https://doi.org/10.17586/0021-3454-2024-67-2-195-199</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Rahman A., Hasan N., Zaki M. Modelling and validation of electric vehicle drive line architectureusing Bond Graph // Test Engineering and Management. 2020. V. 82. P. 15154–15167.</mixed-citation><mixed-citation xml:lang="en">Rahman A., Hasan N., Zaki M. Modelling and validation of electric vehicle drive line architectureusing Bond Graph. Test Engineering and Management, 2020, vol. 82, pp. 15154–15167.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Gonzalez-Avalos G., Gallegos N.B., Ayala-Jaimes G., Garcia A.P. Modeling and simulation in Multibond Graphs applied to three-phase electrical systems // Applied Sciences. 2023. V. 13. N 10. P. 5880. https://doi.org/10.3390/app13105880</mixed-citation><mixed-citation xml:lang="en">Gonzalez-Avalos G., Gallegos N.B., Ayala-Jaimes G., Garcia A.P. Modeling and simulation in Multibond Graphs applied to three-phase electrical systems. Applied Sciences, 2023, vol. 13, no. 10, pp. 5880. https://doi.org/10.3390/app13105880</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Li F., Wu Z., Li J., Lai Z., Zhao B., Min C. A multi-step CNN-based estimation of aircraft landing gear angles // Sensors. 2021. V. 21. N 24. P. 8440. https://doi.org/10.3390/s21248440</mixed-citation><mixed-citation xml:lang="en">Li F., Wu Z., Li J., Lai Z., Zhao B., Min C. A multi-step CNN-based estimation of aircraft landing gear angles. Sensors, 2021, vol. 21, no. 24, pp. 8440. https://doi.org/10.3390/s21248440</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Chen J., Xu Q., Guo Y., Chen R. Aircraft landing gear retraction/extension system fault diagnosis with 1-D dilated convolutional neural network // Sensors. 2022. V. 22. N 4. P. 1367. https://doi.org/10.3390/s22041367</mixed-citation><mixed-citation xml:lang="en">Chen J., Xu Q., Guo Y., Chen R. Aircraft landing gear retraction/extension system fault diagnosis with 1-D dilated convolutional neural network. Sensors, 2022, vol. 22, no. 4, pp. 1367. https://doi.org/10.3390/s22041367</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Saucedo-Dorantes J.J., Delgado-Prieto M., Osornio-Rios R.A., Romero-Troncoso R.J. Industrial data-driven monitoring based on incremental learning applied to the detection of novel faults // IEEE Transactions on Industrial Informatics. 2020. V. 16. N 9. P. 5985–5995. https://doi.org/10.1109/TII.2020.2973731</mixed-citation><mixed-citation xml:lang="en">Saucedo-Dorantes J.J., Delgado-Prieto M., Osornio-Rios R.A., Romero-Troncoso R.J. Industrial data-driven monitoring based on incremental learning applied to the detection of novel faults. IEEE Transactions on Industrial Informatics, 2020, vol. 16, no. 9, pp. 5985–5995. https://doi.org/10.1109/TII.2020.2973731</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Mo H., Li Y. Fault diagnosis based on interval analytic redundancy relation // Journal of Nanjing University of Aeronautics and Astronautics. 2021. V. 53. N 6. P. 972–980.</mixed-citation><mixed-citation xml:lang="en">Mo H., Li Y. Fault diagnosis based on interval analytic redundancy relation. Journal of Nanjing University of Aeronautics and Astronautics, 2021, vol. 53, no. 6, pp. 972–980.</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>
