<?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">10.17586/2226-1494-2025-25-5-961-970</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-525</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>Разработка и исследование метода обучения с подкреплением для акустической диагностики промышленного оборудования</article-title><trans-title-group xml:lang="en"><trans-title>Development and research of a reinforcement learning method for acoustic diagnostics of industrial equipment</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-0126-2358</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Верзун</surname><given-names>Н. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Verzun</surname><given-names>N. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Верзун Наталья Аркадьевна — кандидат технических наук, доцент, доцент; доцент</p><p>sc 57208320400</p><p>Санкт-Петербург, 191023</p><p>Санкт-Петербург, 197376</p></bio><bio xml:lang="en"><p>Natalya A. Verzun — PhD, Associate Professor, Associate Professor; Associate Professor</p><p>sc 57208320400</p><p>Saint Petersburg, 191023</p><p>Saint Petersburg, 197376</p></bio><email xlink:type="simple">Verzun.n@unecon.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/0000-0003-4825-6972</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Колбанёв</surname><given-names>М. О.</given-names></name><name name-style="western" xml:lang="en"><surname>Kolbanev</surname><given-names>M. O.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Колбанёв Михаил Олегович — доктор технических наук, профессор, профессор; профессор</p><p>sc 6506189057</p><p>Санкт-Петербург, 191023</p><p>Санкт-Петербург, 197376</p></bio><bio xml:lang="en"><p>Mikhail O. Kolbanev — <ext-link xlink:href="http://D.Sc/" ext-link-type="uri">D.Sc</ext-link>., Full Professor; Professor</p><p>sc 6506189057</p><p>Saint Petersburg, 191023</p><p>Saint Petersburg, 197376</p></bio><email xlink:type="simple">mokolbanev@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/0009-0001-9519-5773</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Салиева</surname><given-names>А. Р.</given-names></name><name name-style="western" xml:lang="en"><surname>Salieva</surname><given-names>A. R.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Салиева Аделина Рустамовна — аспирант, младший аналитик</p><p>Москва, 127015</p></bio><bio xml:lang="en"><p>Adelina R. Salieva — PhD Student, Junior Analyst</p><p>Moscow, 127015</p></bio><email xlink:type="simple">Rustamovna.a3@gmail.com</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный экономический университет; Санкт-Петербургский государственный электротехнический университет «ЛЭТИ» имени В. И. Ульянова (Ленина)</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint Petersburg State University of Economics; Saint Petersburg Electrotechnical University “LETI”</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Лига цифровой экономики</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Digital Economy League</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>27</day><month>10</month><year>2025</year></pub-date><volume>25</volume><issue>5</issue><fpage>961</fpage><lpage>970</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Верзун Н.А., Колбанёв М.О., Салиева А.Р., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Верзун Н.А., Колбанёв М.О., Салиева А.Р.</copyright-holder><copyright-holder xml:lang="en">Verzun N.A., Kolbanev M.O., Salieva A.R.</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/525">https://ntv.elpub.ru/jour/article/view/525</self-uri><abstract><sec><title>Введение</title><p>Введение. Исследована актуальная задача акустической диагностики автономно работающего промышленного оборудования. Обзор существующих подходов к акустической диагностике, включая методы на основе сверточных нейронных сетей и алгоритмы обучения с учителем, показал их ограничения, такие как необходимость использования для обучения больших объемов размеченных данных, слабая адаптация к изменяющимся условиям и отсутствие механизма принятия решений в реальном времени. Предложен новый подход к акустической диагностике на основе методов обучения с подкреплением, отличающийся способностью к адаптации, высокой устойчивостью к шуму и возможностью непрерывного обучения в динамической среде.</p></sec><sec><title>Метод</title><p>Метод. Представленный метод определения состояния работоспособности оборудования использует подход, основанный на исследовании акустических сигналов, издаваемых работающим оборудованием. Метод включает построение нейронной сети, выбор аудиозаписей из открытых библиотек аудиофайлов и обучение сети при помощи алгоритма с подкреплением. Процесс акустической диагностики состояния исправности/ неисправности промышленного оборудования предполагает четыре этапа: фиксацию в режиме реального времени акустических данных работающего оборудования, извлечение признаков состояния оборудования, обучение с подкреплением нейронной сети и принятие решения о исправности/неисправности оборудования.</p></sec><sec><title>Основные результаты</title><p>Основные результаты. На основе размеченных аудиофайлов из открытых баз данных проведен эксперимент по идентификации различных состояний оборудования: нормальное состояние, начальная стадия дефекта, критическая неисправность. Результаты показали точность классификации от 89,7 % до 98,5 % и среднее время отклика от 0,5 до 0,7 с при низкой вычислительной нагрузке (в среднем загрузка центрального процессора 36,5 % и объем потребляемой оперативной памяти 509 МБ).</p></sec><sec><title>Обсуждение</title><p>Обсуждение. В отличие от известных систем акустической диагностики, основанных на алгоритмах обучения с учителем нейронных и сверточных нейронных сетей на предварительно размеченных базах данных, содержащих акустические сигналы, издаваемые работающим оборудованием, в предлагаемом подходе реализуется декомпозиция исходных акустических сигналов на спектральные составляющие. Каждая из этих составляющих анализируется и снабжается признаками, отражающими состояние исправности/неисправности оборудования. Такой подход позволяет: использовать алгоритмы обучения с подкреплением для принятия решений на основе стратегии; сократить время обучения модели за счет предварительного выделения значимых признаков; повысить точность диагностики; снизить вычислительную нагрузку и требования к аппаратным ресурсам. Разработанный алгоритм может применяться для непрерывного мониторинга состояния оборудования и предиктивного обслуживания в автономно функционирующих промышленных системах. Его использование позволит надежно и своевременно выявлять, и классифицировать неисправности промышленного оборудования. Алгоритм возможно доработать с учетом требований к интеграции с инфраструктурой интернета вещей, повышения устойчивости к внешним шумам и внедрения более продвинутых алгоритмов обучения с подкреплением, таких как Proximal Policy Optimization или Asynchronous Advantage Actor-Critic.</p></sec></abstract><trans-abstract xml:lang="en"><p>The actual problem of acoustic diagnostics of autonomously operating industrial equipment is investigated. An overview of existing approaches to acoustic diagnostics, including methods based on convolutional neural networks and learning algorithms with a teacher, is provided. Their limitations have been identified, such as the need to use large amounts of labeled data for training, poor adaptation to changing conditions, and the lack of a real-time decision-making mechanism. A new approach to acoustic diagnostics based on reinforcement learning methods is proposed, characterized by adaptability, high resistance to noise and the possibility of continuous learning in a dynamic environment. The proposed method for determining the state of equipment operability uses an approach based on the study of acoustic signals emitted by operating equipment. The method includes building a neural network, selecting audio recordings from open audio file libraries, and training the network using a reinforcement learning algorithm. The process of acoustic diagnostics of the state of serviceability/ malfunction of industrial equipment involves four stages: real-time recording of acoustic data of working equipment, extraction of signs of equipment condition, training with reinforcement of a neural network and making a decision on the serviceability / malfunction of the equipment. Based on tagged WAV audio files from open databases, an experiment was conducted to identify various states of the equipment: normal condition, initial stage of the defect, critical malfunction. The results showed classification accuracy from 89.7 % to 98.5 % and average response time from 0.5 to 0.7 seconds with low computing load (on average 36.5 % CPU and 509 MB RAM). Unlike the wellknown acoustic diagnostic systems based on teacher-learning algorithms for neural and convolutional neural networks on pre-marked datasets containing acoustic signals emitted by running equipment, the proposed approach implements the decomposition of the initial acoustic signals into spectral components. Each of these components is analyzed and provided with signs reflecting the state of serviceability or malfunction of the equipment. This approach allows you to: use reinforcement learning algorithms for strategic decision-making; reduce model training time by pre-selecting significant features; improve diagnostic accuracy; reduce computational load and hardware resource requirements. The developed algorithm can be used for continuous monitoring of equipment condition and predictive maintenance in autonomously functioning industrial systems. Its use will allow reliable and timely detection and classification of industrial equipment malfunctions. It is possible to refine the algorithm to meet the requirements for integration with the IoT infrastructure, increase resistance to external noise, and implement more advanced RL algorithms such as PPO. </p></trans-abstract><kwd-group xml:lang="ru"><kwd>акустическая диагностика</kwd><kwd>промышленное оборудование</kwd><kwd>обучение с подкреплением</kwd><kwd>классификация состояний</kwd><kwd>RL-агент</kwd><kwd>спектральный анализ</kwd></kwd-group><kwd-group xml:lang="en"><kwd>acoustic diagnostics</kwd><kwd>industrial equipment</kwd><kwd>reinforcement learning</kwd><kwd>classification of states</kwd><kwd>RL agent</kwd><kwd>spectral analysis</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">Винограденко А.М., Будко Н.П. Адаптивный контроль технического состояния автономных сложных технических объектов на основе интеллектуальных технологий // T-Comm: Телекоммуникации и Транспорт. 2020. Т. 14. № 1. С. 25–35. https://doi.org/10.36724/2072-8735-2020-14-1-25-35</mixed-citation><mixed-citation xml:lang="en">Vinogradenko A.M., Budko N.P. Adaptive control of technical condition of autonomous complex technical objects on the basis of intelligent technologies. Electrostatic gyroscope in spacecraft attitude reference systems. T-Comm, 2020, vol. 14, no. 1, pp. 25–35. (in Russian). https://doi.org/10.36724/2072-8735-2020-14-1-25-35</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Богатырев В.А., Богатырев С.В., Богатырев А.В. Оценка готовности компьютерной системы к своевременному обслуживанию запросов при его совмещении с информационным восстановлением памяти после отказов // Научно-технический вестник информационных технологий, механики и оптики. 2023. Т. 23. № 3. С. 608–617. https://doi.org/10.17586/2226-1494-2023-23-3-608-617</mixed-citation><mixed-citation xml:lang="en">Bogatyrev V.A., Bogatyrev S.V., Bogatyrev A.V. Assessment of the readiness of a computer system for timely servicing of requests when combined with information recovery of memory after failures. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2023, vol. 23, no. 3, pp. 608–617. (in Russian). https://doi.org/10.17586/2226-1494-2023-23-3-608-617</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Bogatyrev V., Vinokurova M. Control and safety of operation of duplicated computer systems // Communications in Computer and Information Science. 2017. V. 700. P. 331–342. https://doi.org/10.1007/978-3-319-66836-9_28</mixed-citation><mixed-citation xml:lang="en">Bogatyrev V., Vinokurova M. Control and safety of operation of duplicated computer systems. Communications in Computer and Information Science, 2017, vol. 700, pp. 331–342. https://doi.org/10.1007/978-3-319-66836-9_28</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Bogatyrev V.A. Exchange of duplicated computing complexes in fault-tolerant systems // Automatic Control and Computer Sciences. 2011. V. 45. N 5. P. 268–276. https://doi.org/10.3103/s014641161105004x</mixed-citation><mixed-citation xml:lang="en">Bogatyrev V.A. Exchange of duplicated computing complexes in fault-tolerant systems. Automatic Control and Computer Sciences, 2011, vol. 45, no. 5, pp. 268–276. https://doi.org/10.3103/s014641161105004x</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Мартюгов А.С., Ершов Е.В., Виноградова Л.Н., Варфоломеев И.А. Диагностика промышленного оборудования методом акустического контроля // Оптико- электронные приборы и устройства в системах распознавания образов и обработки изображений: Материалы XVI Международной научно-технической конференции. Курск: Юго-Западный государственный университет, 2021. С. 172–174.</mixed-citation><mixed-citation xml:lang="en">Martiugov A.S., Ershov E.V., Vinogradova L.N., Varfolomeev I.A. Diagnostics of industrial equipment using acoustic testing. Proc. of the Optical-Electronic Devices and Instruments in Image Recognition and Processing Systems, 2021, pp. 172–174. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Верзун Н.А., Колбанёв М.О., Салиева А.Р. Многоагентный ансамблевый алгоритм акустического распознавания нарушений работоспособности автономного технологического оборудования // Информационно-управляющие системы. 2025. № 3 (136). C. 14–24. https://doi.org/10.31799/1684-8853-2025-3-14-24</mixed-citation><mixed-citation xml:lang="en">Verzun N.A., Kolbanev M.O., Salieva A.R. Multi-agent ensemble algorithm for acoustic recognition of malfunctions of autonomous technological equipment. Information and Control Systems, 2025, no. 3, pp. 14–24. (in Russian). https://doi.org/10.31799/1684-8853-2025-3-14-24</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Щегольков М.В., Зинкин С.А. Обзор основных подходов обучения с подкреплением на основе обучения без знания модели // Энергетика и автоматизация в современном обществе: Материалы VII Всероссийской научно-практической конференции обучающихся и преподавателей. СПб: Санкт-Петербургский государственный университете промышленных технологий и дизайна, 2024. С. 91–95.</mixed-citation><mixed-citation xml:lang="en">Shchegolkov M.V., Zinkin S.A. Overview of the main model-free reinforcement learning approaches. Proc. of the Energy and Automation in Modern Society, 2024, pp. 91–95. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Ye L., Ma X., Wen C. Rotating machinery fault diagnosis method by combining time-frequency domain features and CNN knowledge transfer // Sensors. 2021. V. 21. N 24. P. 8168. https://doi.org/10.3390/s21248168</mixed-citation><mixed-citation xml:lang="en">Ye L., Ma X., Wen C. Rotating machinery fault diagnosis method by combining time-frequency domain features and CNN knowledge transfer. Sensors, 2021, vol. 21, no. 24, pp. 8168. https://doi.org/10.3390/s21248168</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Shao S., McAleer S., Yan R., Baldi P. Highly accurate machine fault diagnosis using deep transfer learning // IEEE Transactions on Industrial Informatics. 2019. V. 15. N 4. P. 2446–2455. https://doi.org/10.1109/tii.2018.2864759</mixed-citation><mixed-citation xml:lang="en">Shao S., McAleer S., Yan R., Baldi P. Highly accurate machine fault diagnosis using deep transfer learning. IEEE Transactions on Industrial Informatics, 2019, vol. 15, no. 4, pp. 2446–2455. https://doi.org/10.1109/tii.2018.2864759</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Souza R.M., Nascimento E.G.S., Miranda U.A., Silva W.J.D., Lepikson H.A.. Deep learning for diagnosis and classification of faults in industrial rotating machinery // Computers and Industrial Engineering. 2021. V. 153. P. 107060. https://doi.org/10.1016/j.cie.2020.107060</mixed-citation><mixed-citation xml:lang="en">Souza R.M., Nascimento E.G.S., Miranda U.A., Silva W.J.D., Lepikson H.A.. Deep learning for diagnosis and classification of faults in industrial rotating machinery. Computers and Industrial Engineering, 2021, vol. 153, pp. 107060. https://doi.org/10.1016/j.cie.2020.107060</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Lyu P., Zhang K., Yu W., Wang B., Liu C. A novel RSG-based intelligent bearing fault diagnosis method for motors in high-noise industrial environment // Advanced Engineering Informatics. 2022. V. 52. P. 101564. https://doi.org/10.1016/j.aei.2022.101564</mixed-citation><mixed-citation xml:lang="en">Lyu P., Zhang K., Yu W., Wang B., Liu C. A novel RSG-based intelligent bearing fault diagnosis method for motors in high-noise industrial environment. Advanced Engineering Informatics, 2022, vol. 52, pp. 101564. https://doi.org/10.1016/j.aei.2022.101564</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang J., Koppel A., Bedi A.S., Szepesvari C., Wang M., Variational policy gradient method for reinforcement learning with general utilities // arXiv. 2020. arXiv:2007.02151. https://doi.org/10.48550/arXiv.2007.02151</mixed-citation><mixed-citation xml:lang="en">Zhang J., Koppel A., Bedi A.S., Szepesvari C., Wang M., Variational policy gradient method for reinforcement learning with general utilities. arXiv, 2020, arXiv:2007.02151. https://doi.org/10.48550/arXiv.2007.02151</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Chen D., Peng P., Huang T., Tian Y. Deep reinforcement learning with spiking Q-learning // arXiv. 2022. arXiv:2201.09754.</mixed-citation><mixed-citation xml:lang="en">Chen D., Peng P., Huang T., Tian Y. Deep reinforcement learning with spiking Q-learning. arXiv, 2022, arXiv:2201.09754. https://doi.org/10.48550/arXiv.2201.09754</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Верзун Н.А., Колбанёв М.О., Салиева А.Р. Анализ перспектив обучения умных автономных логистических систем на основе оптимизации функции ценности // Известия СПбГЭТУ ЛЭТИ. 2024. Т. 17. № 10. C. 28–39. https://doi.org/10.32603/2071-8985-2024-17-10-28-39</mixed-citation><mixed-citation xml:lang="en">Verzun N.A., Kolbanev M.O., Salieva A.R. Analysis learning prospects of smart autonomous logistics systems based on value function optimization. LETI Transactions on Electrical Engineering &amp; Computer Science, 2024, vol. 17, no. 10, pp. 28–39. (in Russian). https://doi.org/10.32603/2071-8985-2024-17-10-28-39</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Tama B.A., Vania M., Lee S., Lim S. Recent advances in the application of deep learning for fault diagnosis of rotating machinery using vibration signals // Artificial Intelligence Review. 2023. V. 56. N 5. P. 4667–4709. https://doi.org/10.1007/s10462-022-10293-3</mixed-citation><mixed-citation xml:lang="en">Tama B.A., Vania M., Lee S., Lim S. Recent advances in the application of deep learning for fault diagnosis of rotating machinery using vibration signals. Artificial Intelligence Review, 2023, vol. 56, no. 5, pp. 4667–4709. https://doi.org/10.1007/s10462-022-10293-3</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Wang R., Zhan X., Bai H., Dong E., Cheng Z., Jia X. A review of fault diagnosis methods for rotating machinery using infrared thermography // Micromachines. 2022. V. 13. N 10. P. 1644. https://doi.org/10.3390/mi13101644</mixed-citation><mixed-citation xml:lang="en">Wang R., Zhan X., Bai H., Dong E., Cheng Z., Jia X. A review of fault diagnosis methods for rotating machinery using infrared thermography. Micromachines, 2022, vol. 13, no. 10, pp. 1644. https://doi.org/10.3390/mi13101644</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Ramaswamy A., Hüllermeier E. Deep Q-Learning: theoretical insights from an asymptotic analysis // arXiv. 2020. arXiv:2008.10870. https://doi.org/10.48550/arXiv.2008.10870</mixed-citation><mixed-citation xml:lang="en">Ramaswamy A., Hüllermeier E. Deep Q-Learning: theoretical insights from an asymptotic analysis. arXiv, 2020, arXiv:2008.10870. https://doi.org/10.48550/arXiv.2008.10870</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Hansen N., Su H., Wang X. Stabilizing Deep Q-Learning with ConvNets and vision transformers under data augmentation // Proc. of the 35th International Conference on Neural Information Processing Systems. 2021. P. 3680–3693.</mixed-citation><mixed-citation xml:lang="en">Hansen N., Su H., Wang X. Stabilizing Deep Q-Learning with ConvNets and vision transformers under data augmentation. Proc. of the 35th International Conference on Neural Information Processing Systems, 2021, pp. 3680–3693.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Haq A.S., Nasrun M., Setianingsih C., Murti M.A. Speech recognition implementation using MFCC and DTW algorithm for home automation // Proc. of the International Conference on Electrical Engineering Computer Science and Informatics. 2020. V. 7. P. 78–85. https://doi.org/10.11591/eecsi.v7.2041</mixed-citation><mixed-citation xml:lang="en">Haq A.S., Nasrun M., Setianingsih C., Murti M.A. Speech recognition implementation using MFCC and DTW algorithm for home automation. Proc. of the International Conference on Electrical Engineering Computer Science and Informatics, 2020, vol. 7, pp. 78–85. https://doi.org/10.11591/eecsi.v7.2041</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Sutton R.S., Barto A.G. Reinforcement Learning: An Introduction. Bradford Books, 2018. 552 p.</mixed-citation><mixed-citation xml:lang="en">Sutton R.S., Barto A.G. Reinforcement Learning: An Introduction. Bradford Books, 2018, 552 p.</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Das O., Das D.B., Birant D. Machine learning for fault analysis in rotating machinery: A comprehensive review // Heliyon. 2023. V. 9. N 6. P. e17584. https://doi.org/10.1016/j.heliyon.2023.e17584</mixed-citation><mixed-citation xml:lang="en">Das O., Das D.B., Birant D. Machine learning for fault analysis in rotating machinery: A comprehensive review. Heliyon, 2023, vol. 9, no. 6, pp. e17584. https://doi.org/10.1016/j.heliyon.2023.e17584</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Свидетельство о государственной регистрации программы для ЭВМ № 2025619237. Акустическая система диагностики неисправностей промышленного оборудования на основе обучения с подкреплением (АСД-ОП). Номер и дата поступления заявки: 2025617991 10.04.2025. Опубликовано 14.04.2025 Бюл. № 4 / Бердникова А.А., Колбанёв М.О, Верзун Н.А., Салиева А.Р. Правообладатель: Государственное бюджетное образовательное учреждение высшего образования «Нижегородский государственный инженерно-экономический университет».</mixed-citation><mixed-citation xml:lang="en">Berdnikova A.A., Kolbanev M.O, Verzun N.A., Salieva A.R. Acoustic system for diagnostics of industrial equipment faults based on reinforcement learning (ASD-OP). Certificate of state registration of the computer program RU 2025619237. 2025. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Moharam M.H., Hany O., Hany A., Mahmoud A., Mohamed M., Saeed S. Anomaly detection using machine learning and adopted digital twin concepts in radio environments // Scientific Reports. 2025. V. 15. P. 18352. https://doi.org/10.1038/s41598-025-02759-5</mixed-citation><mixed-citation xml:lang="en">Moharam M.H., Hany O., Hany A., Mahmoud A., Mohamed M., Saeed S. Anomaly detection using machine learning and adopted digital twin concepts in radio environments. Scientific Reports, 2025, vol. 15, pp. 18352. https://doi.org/10.1038/s41598-025-02759-5</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Purohit H.P., Tanabe R., Ichige K., Endo T., Nikaido Y., Suefusa K., Kawaguchi Y. MIMII Dataset: sound dataset for malfunctioning industrial machine investigation and inspection // Proc. of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019). 2019. P. 209–213. https://doi.org/10.33682/m76f-d618</mixed-citation><mixed-citation xml:lang="en">Purohit H.P., Tanabe R., Ichige K., Endo T., Nikaido Y., Suefusa K., Kawaguchi Y. MIMII Dataset: sound dataset for malfunctioning industrial machine investigation and inspection. Proc. of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), 2019, pp. 209–213. https://doi.org/10.33682/m76f-d618</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Koizumi Y., Kawaguchi Y., Imoto K., Nakamura T., Nikaido Y., Tanabe R., Purohit H., Suefusa K., Endo T., Yasuda M., Harada N. Description and discussion on DCASE2020 challenge Task2: unsupervised anomalous sound detection for machine condition monitoring // arXiv. 2020. arXiv:2006.05822. https://doi.org/10.48550/arXiv.2006.05822</mixed-citation><mixed-citation xml:lang="en">Koizumi Y., Kawaguchi Y., Imoto K., Nakamura T., Nikaido Y., Tanabe R., Purohit H., Suefusa K., Endo T., Yasuda M., Harada N. Description and discussion on DCASE2020 challenge Task2: unsupervised anomalous sound detection for machine condition monitoring. arXiv, 2020, arXiv:2006.05822. https://doi.org/10.48550/arXiv.2006.05822</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>
