<?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">gumrf</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник Государственного университета морского и речного флота имени адмирала С. О. Макарова</journal-title><trans-title-group xml:lang="en"><trans-title>Vestnik Gosudarstvennogo universiteta morskogo i rechnogo flota imeni admirala S. O. Makarova</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2309-5180</issn><issn pub-type="epub">2500-0551</issn><publisher><publisher-name>ФГБОУ ВО «Государственный университет морского и речного флота имени адмирала С.О. Макарова»</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21821/2309-5180-2025-17-5-768-778</article-id><article-id custom-type="edn" pub-id-type="custom">WDIPTC</article-id><article-id custom-type="elpub" pub-id-type="custom">gumrf-628</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>АВТОМАТИЗАЦИЯ И УПРАВЛЕНИЕ ТЕХНОЛОГИЧЕСКИМИ ПРОЦЕССАМИ И ПРОИЗВОДСТВАМИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>AUTOMATION AND CONTROL OF TECHNOLOGICAL PROCESSES AND PRODUCTIONS</subject></subj-group></article-categories><title-group><article-title>Модель обнаружения аномалий на основе обучения без учителя для многомерных временных рядов технологических параметров промышленных объектов</article-title><trans-title-group xml:lang="en"><trans-title>Anomaly detection model based on unsupervised learning for multivariate industrial time series</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>Лиманский</surname><given-names>Н. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Limansky</surname><given-names>N. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Лиманский Николай Николаевич — ассистент.</p><p>191023, Санкт-Петербург, наб. канала Грибоедова, 30–32</p></bio><bio xml:lang="en"><p>Nikolay N. Limanskiy — Assistant lecturer Saint Petersburg State University of Economics.</p><p>30–32 Griboedov Canal Emb., St. Petersburg, 191023</p></bio><email xlink:type="simple">info@sohoware.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ФГБОУ ВО «Санкт-Петербургский государственный экономический университет»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint Petersburg State University of Economics</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>06</day><month>12</month><year>2025</year></pub-date><volume>17</volume><issue>5</issue><fpage>768</fpage><lpage>778</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Лиманский Н.Н., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Лиманский Н.Н.</copyright-holder><copyright-holder xml:lang="en">Limansky N.N.</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://journal.gumrf.ru/jour/article/view/628">https://journal.gumrf.ru/jour/article/view/628</self-uri><abstract><p>Темой работы является исследование процесса роста сложности киберфизических производственных систем (Cyber-Physical Systems) на судостроительных и судоремонтных заводах, который приводит к генерации многомерных временных рядов с сильными межканальными связями и «дрейфом» режимов, когда традиционные методы статистического контроля процессов (Statistical Process Control) теряют чувствительность. Целью исследования является разработка математически определенной модели обнаружения аномалий на основе обучения без учителя (Unsupervised Learning). Задачами исследования являются формализация представления состояния через сигнатурные матрицы, фиксирующие попарные зависимости между параметрами; реконструкция нормального поведения с помощью нейронной сети Long Short-Term Memory (сеть с долгой краткосрочной памятью) и ее сверточной модификации Convolutional Long Short-Term Memory; использование адаптивных порогов на основе квантильного правила и метода Exponentially Weighted Moving Average (экспоненциально взвешенное скользящее среднее) для учета дрейфа; локализация источников аномалий по остаточным картам и сопряжение с контуром управления. Модель обеспечивает масштабную инвариантность, чувствительность к межканальным зависимостям и устойчивость к режимным смещениям. Практическая значимость выполненного исследования заключается в мониторинге технологических процессов на этапах судостроительного производства, таких как сварка корпусов, сборка секций, испытания энергетических и вспомогательных систем, что снижает количество ложных тревог и обеспечивает оператору интерпретируемые причины срабатывания.</p></abstract><trans-abstract xml:lang="en"><p>This study focuses on developing an unsupervised anomaly detection model for multivariate time series generated by complex Cyber-Physical Systems (CPS) in shipbuilding and manufacturing enterprises, where strong inter-channel dependencies and regime drifts reduce the sensitivity of traditional Statistical Process Control (SPC) methods. The objective is to design a mathematically grounded model capable of detecting abnormal system behavior under varying operational conditions. The proposed approach includes: (1) representing system states through signature matrices that capture pairwise dependencies among process parameters; (2) reconstructing normal operational patterns using a Long Short-Term Memory (LSTM) neural network and its convolutional variant, Convolutional LSTM (ConvLSTM); (3) applying adaptive thresholds derived from the quantile rule and the Exponentially Weighted Moving Average (EWMA) method to account for process drift; and (4) localizing anomaly sources using residual maps and linking them to the control loop for interpretability. The model ensures scale invariance, sensitivity to cross-channel correlations, and robustness to regime shifts. Its practical application lies in real-time monitoring and early detection of deviations in ship power plants, cooling and fuel systems, and various stages of shipbuilding production, thereby reducing false alarms and providing interpretable diagnostics for operators.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>аномалия</kwd><kwd>управление процессом</kwd><kwd>временной ряд</kwd><kwd>матрица признаков</kwd><kwd>нейронная модель</kwd><kwd>кодировщик-декодировщик</kwd><kwd>адаптивный порог</kwd><kwd>остаточная ошибка</kwd><kwd>контроль качества</kwd><kwd>обратная связь</kwd><kwd>киберфизическая система</kwd><kwd>обучение без учителя</kwd></kwd-group><kwd-group xml:lang="en"><kwd>anomaly detection</kwd><kwd>process control</kwd><kwd>multivariate time series</kwd><kwd>feature matrix</kwd><kwd>neural model</kwd><kwd>encoder–decoder</kwd><kwd>adaptive threshold</kwd><kwd>residual error</kwd><kwd>quality control</kwd><kwd>feedback loop</kwd><kwd>cyber-physical system</kwd><kwd>unsupervised learning</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">Lee J. A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems / J. Lee, B. Bagheri, H-A. Kao // Manufacturing Letters. — 2015. — Vol. 3. — Pp. 18–23. DOI: 10.1016/j.mfglet.2014.12.001.</mixed-citation><mixed-citation xml:lang="en">Lee, J., B. Bagheri and H-A. Kao. “A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems.” Manufacturing Letters 3 (2015): 18–23. DOI: 10.1016/j.mfglet.2014.12.001.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Куприяновский В. П. Кибер-физические системы как основа цифровой экономики / В. П. Куприяновский, Д. Е. Намиот, С. А. Синягов // International Journal of Open Information Technologies. — 2016. — Т. 4. — № 2. — С. 18–25. — EDN VKCXLH.</mixed-citation><mixed-citation xml:lang="en">Kupriyanovskiy, V. P., D. E. Namiot and S. A. Sinyagov. “Cyber-physical systems as a base for digital economy.” International Journal of Open Information Technologies 4.2 (2016): 18–25.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Ozbayoglu A. M. Deep learning for financial applications: A survey / A. M. Ozbayoglu, M. U. Gudelek, O. B. Sezer // Applied Soft Computing. — 2020. — Vol. 93. — Pp. 106384. DOI: 10.1016/j.asoc.2020.106384.</mixed-citation><mixed-citation xml:lang="en">Ozbayoglu, A. M., M. U. Gudelek and O. B. Sezer. “Deep learning for financial applications: A survey.” Applied Soft Computing 93 (2020): 106384. DOI: 10.1016/j.asoc.2020.106384.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Адлер Ю. П. Контрольные карты Шухарта в России и за рубежом. Часть 1 / Ю. П. Адлер, О. В. Максимова, В. Л. Шпер // Стандарты и качество. — 2011. — № 7. — С. 82–87. — EDN NXZTNV.</mixed-citation><mixed-citation xml:lang="en">Adler, Yu. P., O. V. Maksimova and V. L. Shper. “Kontrol’nye karty Shukharta v Rossii i za rubezhom. Chast’ 1.” Standards and Quality 7 (2011): 82–87.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Åström K. J. Feedback Systems: An Introduction for Scientists and Engineers. / K. J. Åström, R. M. Murray. — Princeton: Princeton Univ. Press, 2008. — 408 p.</mixed-citation><mixed-citation xml:lang="en">Åström K. J. and R. M. Murray. Feedback Systems: An Introduction for Scientists and Engineers. Princeton: Princeton Univ. Press, 2008: 408 p.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Журилова О. Е. Современные методы и задачи спектрального анализа сигналов: краткий обзор и сравнение / О. Е. Журилова, А. В. Башкиров, С. Ю. Белецкая [и др.] // Вестник Воронежского государственного технического университета. — 2019. — Т. 15. — № 2. — С. 128–131. DOI: 10.25987/VSTU.2019.15.2.016. — EDN HAUOVJ.</mixed-citation><mixed-citation xml:lang="en">Zhurilova, O. E., A. V. Bashkirov et al. “Modern methods and problems of spectral analysis of signals: brief discussion and comparison.” Bulletin of Voronezh State Technical University 15.2 (2019): 128–131. DOI: 10.25987/VSTU.2019.15.2.016.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Hochreiter S. Long Short-Term Memory / S. Hochreiter, J. Schmidhuber // Neural Computation. — 1997. — Vol. 9. — Is. 8. — Pp. 1735–1780. DOI: 10.1162/neco.1997.9.8.1735.</mixed-citation><mixed-citation xml:lang="en">Hochreiter, S. and J. Schmidhuber. “Long Short-Term Memory.” Neural Computation 9.8 (1997): 1735–1780. DOI: 10.1162/neco.1997.9.8.1735.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">SHI X. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting / X. SHI, Z. Chen, H. Wang, D-Y. Yeung, W-.Wong, W-.WOO // Advances in Neural Information Processing Systems. — 28 — Curran Associates, Inc., 2015.</mixed-citation><mixed-citation xml:lang="en">SHI, X., W-. WOO, et al. “Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting.” Advances in Neural Information Processing Systems — 28Curran Associates, Inc., 2015.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang C. A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data / C. Zhang, D. Song, Y. Chen, X. Feng, C. Lumezanu, W. Cheng, J. Ni, B. Zong, H. Chen, N. V. Chawla // Proceedings of the AAAI Conference on Artificial Intelligence. — 2019. — Vol. 33. — Is. 01. — Pp. 1409–1416. DOI: 10.1609/aaai.v33i01.33011409.</mixed-citation><mixed-citation xml:lang="en">Zhang, C., N. V. Chawla, et al. “A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data.” Proceedings of the AAAI Conference on Artificial Intelligence 33.01 (2019): 1409–1416. DOI: 10.1609/aaai.v33i01.33011409.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Qingning L. Multi-Scale Anomaly Detection for Time Series with Attention-based Recurrent Autoencoders / L. Qingning, L. Wenzhong, Z. Chuanze [и др.] // Proceedings of Machine Learning Research — 189 — PMLR, 2023. — С. 674–689.</mixed-citation><mixed-citation xml:lang="en">Qingning, L., L. Sanglu, et al. “Multi-Scale Anomaly Detection for Time Series with Attention-based Recurrent Autoencoders.” Proceedings of Machine Learning Research — 189PMLR, 2023: 674–689.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Jolliffe I. T. Principal component analysis: a review and recent developments / I. T. Jolliffe, J. . Cadima // Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. — 2016. — Vol. 374. — Is. 2065. — Pp. 20150202. DOI: 10.1098/rsta.2015.0202.</mixed-citation><mixed-citation xml:lang="en">Jolliffe, I. T. and J. . Cadima. “Principal component analysis: a review and recent developments.” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 374.2065 (2016): 20150202. DOI: 10.1098/rsta.2015.0202.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Намиот Д. Е. Мониторинг сдвига данных в моделях машинного обучения / Д. Е. Намиот, Е. А. Ильюшин // International Journal of Open Information Technologies. — 2022. — Т. 10. — № 12. — С. 84–93. — EDN NDOMRK.</mixed-citation><mixed-citation xml:lang="en">Namiot, D. E. and E. A. Il’yushin. “Data shift monitoring in machine learning models.” International Journal of Open Information Technologies 10.12 (2022): 84–93.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Марчук В. И. Анализ методов адаптации порогового значения при обнаружении аномальных измерений / В. И. Марчук, К. Е. Румянцев // Известия высших учебных заведений России. Радиоэлектроника. — 2006. — № 1. — С. 29–34. — EDN THUIIR.</mixed-citation><mixed-citation xml:lang="en">Marchuk, V. I. and K. E. Rumyantsev. “Analysis of the adaptation methods of threshold value at detection of abnormal measurements.” Journal of The Russian Universities. Radioelectronics 1 (2006): 29–34.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Hundman K. Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding / K. Hundman, V. Constantinou, C. Laporte, I. Colwell, T. Soderstrom // KDD ‘18 — Association for Computing Machinery, 2018. — С. 387–395. DOI: 10.1145/3219819.3219845.</mixed-citation><mixed-citation xml:lang="en">Hundman, K., T. Soderstrom, et al. “Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding.” KDD ‘18Association for Computing Machinery, 2018: 387–395. DOI: 10.1145/3219819.3219845.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Lucas J. M. Exponentially Weighted Moving Average Control Schemes: Properties and Enhancements / J. M. Lucas, M. S. Saccucci // Technometrics. — 1990. — Vol. 32. — Is. 1. — Pp. 1–12. DOI: 10.1080/00401706.1990.10484583.</mixed-citation><mixed-citation xml:lang="en">Lucas, J. M. and M. S. Saccucci. “Exponentially Weighted Moving Average Control Schemes: Properties and Enhancements.” Technometrics 32.1 (1990): 1–12. DOI: 10.1080/00401706.1990.10484583.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">NIST/SEMATECH e-Handbook of Statistical Methods [Электронный ресурс]. — Режим доступа: https://www.itl.nist.gov/div898/handbook/ (дата обращения: 09.08.2025).</mixed-citation><mixed-citation xml:lang="en">NIST/SEMATECH e-Handbook of Statistical Methods. Web. 09 Aug. 2025 https://www.itl.nist.gov/div898/handbook/.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Wang F. A Survey of Deep Anomaly Detection in Multivariate Time Series: Taxonomy, Applications, and Directions / F. Wang, Y. Jiang, R. Zhang, A. Wei, J. Xie, X. Pang // Sensors. — 2025. — Vol. 25. — Is. 1. DOI: 10.3390/s25010190.</mixed-citation><mixed-citation xml:lang="en">Wang, F., X. Pang, et al. “A Survey of Deep Anomaly Detection in Multivariate Time Series: Taxonomy, Applications, and Directions.” Sensors 25.1 (2025). DOI: 10.3390/s25010190.</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>
