<?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">tatpip</journal-id><journal-title-group><journal-title xml:lang="ru">Техника и технология пищевых производств</journal-title><trans-title-group xml:lang="en"><trans-title>Food Processing: Techniques and Technology</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2074-9414</issn><issn pub-type="epub">2313-1748</issn><publisher><publisher-name>Кемеровский государственный университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21603/2074-9414-2025-4-2613</article-id><article-id custom-type="edn" pub-id-type="custom">KLILNT</article-id><article-id custom-type="elpub" pub-id-type="custom">tatpip-150</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>Статьи</subject></subj-group></article-categories><title-group><article-title>Применение сверточных нейронных сетей для контроля показателей технологического потока производства гранулированных киселей</article-title><trans-title-group xml:lang="en"><trans-title>Convolutional Neural Networks in Granulated Kissel Production</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4512-1933</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Шафрай</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Shafrai</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Шафрай Антон Валерьевич</p><p>Кемерово</p></bio><bio xml:lang="en"><p>Anton V. Shafrai</p><p>Kemerovo</p></bio><email xlink:type="simple">shafraia@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/0000-0003-0728-7211</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Попов</surname><given-names>А. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Popov</surname><given-names>A. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Попов Анатолий Михайлович</p><p>Кемерово</p></bio><bio xml:lang="en"><p>Anatoliy M. Popov</p><p>Kemerovo</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-5852-9809</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Косинов</surname><given-names>В. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Kosinov</surname><given-names>V. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Косинов Виталий Сергеевич</p><p>Кемерово</p></bio><bio xml:lang="en"><p>Vitaly S. Kosinov</p><p>Kemerovo</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-7486-4704</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Резниченко</surname><given-names>И. Ю.</given-names></name><name name-style="western" xml:lang="en"><surname>Reznichenko</surname><given-names>I. Yu.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Резниченко Ирина Юрьевна</p><p>Кемерово</p></bio><bio xml:lang="en"><p>Irina Yu. Reznichenko</p><p>Kemerovo</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0000-0820-5965</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Бондарчук</surname><given-names>О. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Bondarchuk</surname><given-names>O. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Бондарчук Ольга Николаевна</p><p>Кемерово</p></bio><bio xml:lang="en"><p>Olga N. Bondarchuk</p><p>Kemerovo</p></bio><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Кемеровский государственный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Kemerovo State University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Кузбасский государственный аграрный университет имени В. Н. Полецкова</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Kuzbass State Agricultural 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>20</day><month>08</month><year>2026</year></pub-date><volume>55</volume><issue>4</issue><fpage>845</fpage><lpage>855</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Шафрай А.В., Попов А.М., Косинов В.С., Резниченко И.Ю., Бондарчук О.Н., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Шафрай А.В., Попов А.М., Косинов В.С., Резниченко И.Ю., Бондарчук О.Н.</copyright-holder><copyright-holder xml:lang="en">Shafrai A.V., Popov A.M., Kosinov V.S., Reznichenko I.Y., Bondarchuk O.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://www.fptt.ru/jour/article/view/150">https://www.fptt.ru/jour/article/view/150</self-uri><abstract><p>Применение искусственного интеллекта в пищевой промышленности становится актуальным. Существуют разные способы цифровизации контроля показателей технологического потока производства продукции. Например, использование нейронных сетей для определения размеров гранул сухого киселя. Цель исследования – применить сверточные нейронные сети для контроля показателей технологического потока производства гранулированных киселей посредством локализации гранул киселя на изображении.Одним из важнейших параметров готовых гранул сухого киселя является их размер, который должен находится в пределах от 2 до 5 мм. Для разработки модели, определяющей крупные гранулы (более 5 мм), требуется собрать набор данных из изображений гранул разного размера. Выбраны модели локализации объектов из фреймворка Detectron2, которые оптимально справятся с задачей. Описаны принципы работы моделей и качественные показатели для оценки результатов обучения моделей.Для выявления крупных гранул собран и размечен набор данных из изображений гранул разного размера. Наилучших показателей достигала модель R50-FPN. Наибольшее значение принимала метрика AP50, затем шли AP75 и AP. Модели отлично обучились находить объекты на изображении, достаточно хорошо определяли координаты ограничивающей рамки. В собранном наборе данных отсутствовали размеченные объекты для малых (APs) и средних (APm) размеров, т. к. в исследовании сделан акцент на локализации именно больших гранул. Значения метрики APl для всех моделей находились на высоком уровне. Таким образом, выбранный подход к обучению и архитектуре нейронной сети оказался оптимальным для данной задачи.На основе обученной модели разработана программа ЭВМ, которая использует сверточные нейронные сети для детекции больших гранул на снимке с продукцией. В дальнейшем она может быть использована на непрерывных производствах для контроля размера готового продукта и его соответствия технологическим параметрам.</p></abstract><trans-abstract xml:lang="en"><p>Artificial intelligence can be used to monitor production parameters in the food industry. Kissel is a jelly-like fruit or berry starch drink. Instant kissel usually consists of granules. Neural networks may help to control the size of kissel granules. In this research, convolutional neural networks monitored the production parameters of granulated kissel powder by localizing granules in an image.Size is the most important parameter of kissel granules: it should remain between 2 and 5 mm. To detects larger granules (≥ 5 mm), the network was provided with a visual dataset of granules of varying sizes. The localization models were developed using Detectron2.The research yielded a set of optimal operating principles and quality metrics. The R50-FPN model achieved the best results. The AP50 metric had the highest value, followed by AP75 and AP. The models performed well in visual detection and successfully determined the coordinates of the bounding rectangle. The resulting dataset did not label objects for small (APs) and medium (APm) sizes because the study focused on localizing large granules. The APl metric values for all models were high. The approach to AI training and neural network architecture proved optimal for food production control.The trained model made it possible to develop a computer program based on convolutional neural networks that demonstrated good results in detecting large granules in instant kissel powder. The new program can be used in continuous production to monitor the size of finished products and their compliance with process parameters.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>Искусственный интеллект</kwd><kwd>нейронные сети</kwd><kwd>локализация</kwd><kwd>гранулированные продукты</kwd><kwd>гранулированные кисели</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Artificial intelligence</kwd><kwd>neural networks</kwd><kwd>localization</kwd><kwd>granulated products</kwd><kwd>granulated kissel</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено за счет гранта Российского научного фонда № 25-26-00136, https://rscf.ru/project/25-26-00136/</funding-statement><funding-statement xml:lang="en">The study was supported by the Russian Science Foundation, grant No. 25-26-00136, https://rscf.ru/en/project/25-26-00136/</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Shafrai AV, Permyakova LV, Borodulin DM, Sergeeva IY. Modeling the physiological parameters of brewer’s yeast during storage with natural zeolite-containing tuffs using artificial neural networks. Information. 2022;13(11):529. https://doi.org/10.3390/info13110529</mixed-citation><mixed-citation xml:lang="en">Shafrai AV, Permyakova LV, Borodulin DM, Sergeeva IY. Modeling the physiological parameters of brewer’s yeast during storage with natural zeolite-containing tuffs using artificial neural networks. Information. 2022;13(11):529. https://doi.org/10.3390/info13110529</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Королев И. А. Автоматизированное определение дисперсности воздушной фазы в мороженом с применением методов машинного обучения. Техника и технология пищевых производств. 2023. Т. 53. № 3. С. 455–464. https://doi.org/10.21603/2074-9414-2023-3-2448</mixed-citation><mixed-citation xml:lang="en">Korolev IA. automated measurement of air bubbles dispersion in ice cream using machine learning methods. Food Processing: Techniques and Technology. 2023;53(3):455–464. (In Russ.) https://doi.org/10.21603/2074-9414-2023-3-2448</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Jo DM, Han S-J, Ko S-C, Kim KW, Yang D, et al. Application of artificial intelligence in the advancement of sensory evaluation of food products. Trends in Food Science &amp; Technology. 2025;165:105283. https://doi.org/10.1016/j.tifs.2025.105283</mixed-citation><mixed-citation xml:lang="en">Jo DM, Han S-J, Ko S-C, Kim KW, Yang D, et al. Application of artificial intelligence in the advancement of sensory evaluation of food products. Trends in Food Science &amp; Technology. 2025;165:105283. https://doi.org/10.1016/j.tifs.2025.105283</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Михеев П. Н. Технологии искусственного интеллекта в пищевой промышленности. Инновации и инвестиции. 2023. № 4. С. 536–539. https://elibrary.ru/DYOHTS</mixed-citation><mixed-citation xml:lang="en">Mikheev PN. Artificial intelligence technologies in the food industry. Innovation &amp; Investment. 2023;(4):536–539. (In Russ.) https://elibrary.ru/DYOHTS</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Лындина М. И. Пути совершенствования пищеконцентрантной отрасли. Инновационные технологии производства и хранения материальных ценностей для государственных нужд. 2020. № 13. С. 157–163. https://elibrary.ru/DHQPUP</mixed-citation><mixed-citation xml:lang="en">Lyndina MI. Ways to improve the food industry. Material assets for government needs: Innovative production and storage. 2020;(13):157–163. (In Russ.) https://elibrary.ru/DHQPUP</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Попов А. М. Анализ и синтез технологий гранулированных концентратов напитков. Кемерово: КемТИПП; 2003. С. 133–148.</mixed-citation><mixed-citation xml:lang="en">Popov AM. Granulated beverage concentrates: Technological analysis and synthesis. Kemerovo: KemTIPP; 2003. pp. 133–148. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Ксенофонтов В. В. Нейронные сети. Проблемы науки. 2020. № 11. С. 28–29. https://elibrary.ru/DTVJNS</mixed-citation><mixed-citation xml:lang="en">Ksenofontov VV. Neural networks. Problems of science. 2020;(11):28–29. (In Russ.) https://elibrary.ru/DTVJNS</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Hassan E, El-Rashidy N, Talaat FM. Mask R-CNN models. Nile Journal of Communication and Computer Science. 2022;3(1):17–27. https://doi.org/10.21608/njccs.2022.280047</mixed-citation><mixed-citation xml:lang="en">Hassan E, El-Rashidy N, Talaat FM. Mask R-CNN models. Nile Journal of Communication and Computer Science. 2022;3(1):17–27. https://doi.org/10.21608/njccs.2022.280047</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Olorunshola OE, Jemitola PO, Ademuwagun A. Comparative study of some deep learning object detection algorithms: R-CNN, fast R-CNN, faster R-CNN, SSD, and YOLO. Nile Journal of Engineering and Applied Science. 2023;1(1):70–80. https://doi.org/10.5455/NJEAS.150264</mixed-citation><mixed-citation xml:lang="en">Olorunshola OE, Jemitola PO, Ademuwagun A. Comparative study of some deep learning object detection algorithms: R-CNN, fast R-CNN, faster R-CNN, SSD, and YOLO. Nile Journal of Engineering and Applied Science. 2023;1(1):70–80. https://doi.org/10.5455/NJEAS.150264</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Prakash SR, Singh PN. Object detection through region proposal based techniques. Materials Today: Proceedings. 2021;46(9):3997–4002. https://doi.org/10.1016/j.matpr.2021.02.533</mixed-citation><mixed-citation xml:lang="en">Prakash SR, Singh PN. Object detection through region proposal based techniques. Materials Today: Proceedings. 2021;46(9):3997–4002. https://doi.org/10.1016/j.matpr.2021.02.533</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Zhu L, Lee F, Cai J, Yu H, Chen Q. An improved feature pyramid network for object detection. Neurocomputing. 2022;483:127–139. https://doi.org/10.1016/j.neucom.2022.02.016</mixed-citation><mixed-citation xml:lang="en">Zhu L, Lee F, Cai J, Yu H, Chen Q. An improved feature pyramid network for object detection. Neurocomputing. 2022;483:127–139. https://doi.org/10.1016/j.neucom.2022.02.016</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Xavier AI, Villavicencio C, Macrohon JJ, Jeng J-H, Hsieh J-G. Object detection via gradient-based mask R-CNN using machine learning algorithms. Machines. 2022;10(5):340. https://doi.org/10.3390/machines10050340</mixed-citation><mixed-citation xml:lang="en">Xavier AI, Villavicencio C, Macrohon JJ, Jeng J-H, Hsieh J-G. Object detection via gradient-based mask R-CNN using machine learning algorithms. Machines. 2022;10(5):340. https://doi.org/10.3390/machines10050340</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Jabir B, Falih N, Rahmani K. Accuracy and efficiency comparison of object detection open-source models. International Journal of Online and Biomedical Engineering. 2021;17(5):165–184. https://doi.org/10.3991/ijoe.v17i05.21833</mixed-citation><mixed-citation xml:lang="en">Jabir B, Falih N, Rahmani K. Accuracy and efficiency comparison of object detection open-source models. International Journal of Online and Biomedical Engineering. 2021;17(5):165–184. https://doi.org/10.3991/ijoe.v17i05.21833</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Peng H, Yu S. A systematic IOU-related method: Beyond simplified regression for better localization. IEEE Transactions on Image Processing. 2021;30:5032–5044. https://doi.org/10.1109/TIP.2021.3077144</mixed-citation><mixed-citation xml:lang="en">Peng H, Yu S. A systematic IOU-related method: Beyond simplified regression for better localization. IEEE Transactions on Image Processing. 2021;30:5032–5044. https://doi.org/10.1109/TIP.2021.3077144</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>
