<?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="en"><front><journal-meta><journal-id journal-id-type="publisher-id">donstu</journal-id><journal-title-group><journal-title xml:lang="en">Advanced Engineering Research (Rostov-on-Don)</journal-title><trans-title-group xml:lang="ru"><trans-title>Advanced Engineering Research (Rostov-on-Don)</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">2687-1653</issn><publisher><publisher-name>Don State Technical University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.23947/2687-1653-2021-21-2-143-153</article-id><article-id custom-type="elpub" pub-id-type="custom">donstu-1774</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="en"><subject>MECHANICS</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>МЕХАНИКА</subject></subj-group></article-categories><title-group><article-title>Visualization of internal defects using a deep generative neural network model  and ultrasonic nondestructive testing</article-title><trans-title-group xml:lang="ru"><trans-title>Визуализация внутренних дефектов с применением глубокой  генеративной нейросетевой модели и ультразвукового  неразрушающего контроля</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4112-7449</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Васильев</surname><given-names>П. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Vasiliev</surname><given-names>Р. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Васильев Павел Владимирович, старший преподаватель кафедры «Информационные технологии»</p><p>Scopus ID: 57193327081</p><p>Researcher ID: P-8366-2017</p><p>344003, РФ, г. Ростов-на-Дону, пл. Гагарина, 1</p></bio><email xlink:type="simple">lyftzeigen@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/0000-0003-2001-8235</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сеничев</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Senichev</surname><given-names>А. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Сеничев Александр Вадимович, аспирант кафедры «Информационные технологии»</p><p>344003, РФ, г. Ростов-на-Дону, пл. Гагарина, 1</p></bio><email xlink:type="simple">alexandr.senichev@gmail.com</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Джорджо</surname><given-names>И.</given-names></name><name name-style="western" xml:lang="en"><surname>Giorgio</surname><given-names>I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Джорджо Иван, профессор кафедры «Гражданское, строительно-архитектурное и экологическое проектирование», исследователь в Международном исследовательском центре математики и механики сложных систем кандидат наук</p><p>Scopus ID: 24757867200</p><p>Researcher ID: E-9341-2010</p><p>Via Camponeschi, 19 Piazza Santa Margherita, 2 Palazzo Camponeschi, 67100 L'Aquila AQ, Italy</p><p> </p></bio><xref ref-type="aff" rid="aff-3"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ФГБОУ ВО «Донской государственный технический университет»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Don State Technical University</institution><country>Russian Federation</country></aff></aff-alternatives><aff xml:lang="ru" id="aff-2"><institution>ФГБОУ ВО «Донской государственный технический университет»</institution><country>Russian Federation</country></aff><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>Университет Л’Акуилы</institution><country>Италия</country></aff><aff xml:lang="en"><institution>Università degli Studi dell'Aquila</institution><country>Italy</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2021</year></pub-date><pub-date pub-type="epub"><day>08</day><month>07</month><year>2021</year></pub-date><volume>21</volume><issue>2</issue><fpage>143</fpage><lpage>153</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Vasiliev Р.V., Senichev А.V., Giorgio I., 2021</copyright-statement><copyright-year>2021</copyright-year><copyright-holder xml:lang="ru">Васильев П.В., Сеничев А.В., Джорджо И.</copyright-holder><copyright-holder xml:lang="en">Vasiliev Р.V., Senichev А.V., Giorgio I.</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.vestnik-donstu.ru/jour/article/view/1774">https://www.vestnik-donstu.ru/jour/article/view/1774</self-uri><abstract><sec><title>Introduction</title><p>Introduction. The development of machine learning methods has given a new impulse to solving inverse problems in mechanics. Many studies show that along with well-behaved techniques of ultrasonic, magnetic, and thermal nondestructive testing, the latest methods are used, including those based on neural network models. In this paper, we demonstrate the potential application of machine learning methods in the problem of two-dimensional ultrasound imaging.</p></sec><sec><title>Materials and Methods</title><p> Materials and Methods. We have developed an experimental model of acoustic ultrasonic non-destructive testing, in which the probing of the object under study takes place, followed by the recording of the response signals. The propagation of an ultrasonic wave is modeled by the finite difference method in the time domain. An ultrasonic signal received at the internal points of the control object is applied to the input of the convolutional neural network. At the output, an image that visualizes the internal defect is generated.</p></sec><sec><title>Results</title><p>Results. In the course of the performed complex of numerical experiments, a data set was generated for training a convolutional neural network. A convolutional neural network model, which is developed to solve the problem of visualizing internal defects based on methods of ultrasonic nondestructive testing, is presented. This model has a small size, which is 3.8 million parameters. Its simplicity and versatility provide high-speed learning and a wide range of applications in the class of related problems. The presented results show a high degree of information content of the ultrasonic response and its correspondence to the real form of an internal defect located inside the test object. The effect of geometric parameters of defects on the accuracy of the neural network model is investigated.</p><p>Discussion and Conclusion. The results obtained have established that the proposed model shows a high operating accuracy (F1 &gt; 0.95) in cases when the wavelength of the probe pulse is tens of times less than the size of the defect. We believe that the combination of the proposed methods in this approach can serve as a good starting point for future research in solving flaw defection problems and inverse problems in general. </p></sec></abstract><trans-abstract xml:lang="ru"><sec><title>Введение</title><p>Введение. Развитие методов машинного обучения дало новый толчок в области решения обратных задач механики. Многие работы показывают, что наряду с хорошо зарекомендовавшими себя техниками ультразвукового, магнитного, теплового неразрушающего контроля, применяются новейшие методы, в том числе на основе нейросетевых моделей. В данной работе продемонстрирован потенциал применения методов машинного обучения в задаче двумерной ультразвуковой визуализации.</p></sec><sec><title>Материалы и методы</title><p> Материалы и методы. Авторами построена тестовая модель акустического ультразвукового неразрушающего контроля, в которой происходит зондирование исследуемого объекта с последующей фиксацией сигналовоткликов. Распространение ультразвуковой волны моделируется методом конечных разностей во временной области. На вход сверточной нейронной сети подается ультразвуковой сигнал, полученный во внутренних точках объекта контроля. На выходе генерируется изображение, визуализирующее внутренний дефект.</p></sec><sec><title>Результаты исследования</title><p> Результаты исследования. В ходе проведенного комплекса численных экспериментов был создан набор данных, предназначенный для обучения сверточной нейронной сети. Представлена сверточная нейросетевая модель, разработанная для решения задачи визуализации внутренних дефектов на основе методов ультразвукового неразрушающего контроля. Данная модель имеет небольшой размер, который составляет 3,8 миллиона параметров. Её простота и универсальность обеспечивают высокую скорость обучения и широкие возможности применения в классе смежных задач. Представленные результаты показывают высокую степень информативности ультразвукового отклика и его соответствия реальной форме внутреннего дефекта, находящегося внутри объекта контроля. Исследовано влияние геометрических параметров дефектов на точность работы нейросетевой модели.</p></sec><sec><title>Обсуждение и заключение</title><p> Обсуждение и заключение. На основе полученных результатов выявлено, что предлагаемая модель показывает высокую точность работы (F1 &gt; 0,95) в случаях, когда длина волны зондирующего импульса в десятки раз меньше размера дефекта. Авторы полагают, что комбинация предложенных методов в данном подходе может послужить хорошей отправной точкой для будущих исследований в области решения задач дефектоскопии и обратных задач в целом. </p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>ультразвуковой неразрушающий контроль</kwd><kwd>дефект</kwd><kwd>ультразвуковой отклик</kwd><kwd>сверточные нейронные сети</kwd></kwd-group><kwd-group xml:lang="en"><kwd>ultrasonic nondestructive testing</kwd><kwd>defect</kwd><kwd>ultrasonic response</kwd><kwd>convolutional neural networks</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">Steel crack depth estimation based on 2D images using artificial neural networks / Yasser S. Mohamed, Hesham M. Shehata, Mohamed Abdellatif [et al.] // Alexandria Engineering Journal. — 2019. — Vol. 58 (4). — P. 1167—1174. https://doi.org/10.1016/j.aej.2019.10.001</mixed-citation><mixed-citation xml:lang="en">Steel crack depth estimation based on 2D images using artificial neural networks / Yasser S. Mohamed, Hesham M. Shehata, Mohamed Abdellatif [et al.] // Alexandria Engineering Journal. — 2019. — Vol. 58 (4). — P. 1167—1174. https://doi.org/10.1016/j.aej.2019.10.001</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">A deep transfer learning model for inclusion defect detection of aeronautics composite materials / Yanfeng Gong, Hongliang Shao, Jun Luo, Zhixue Li // Composite Structures. — 2020. — Vol. 252. — 112681. https://doi.org/10.1016/j.compstruct.2020.112681</mixed-citation><mixed-citation xml:lang="en">A deep transfer learning model for inclusion defect detection of aeronautics composite materials / Yanfeng Gong, Hongliang Shao, Jun Luo, Zhixue Li // Composite Structures. — 2020. — Vol. 252. — 112681. https://doi.org/10.1016/j.compstruct.2020.112681</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Three-dimensional subsurface defect shape reconstruction and visualisation by pulsed thermography / Adisorn Sirikham, Yifan Zhao, Haochen Liu [et al.] // Infrared Physics &amp; Technology. — 2020. — Vol. 104. — 103151. https://doi.org/10.1016/j.infrared.2019.103151</mixed-citation><mixed-citation xml:lang="en">Three-dimensional subsurface defect shape reconstruction and visualisation by pulsed thermography / Adisorn Sirikham, Yifan Zhao, Haochen Liu [et al.] // Infrared Physics &amp; Technology. — 2020. — Vol. 104. — 103151. https://doi.org/10.1016/j.infrared.2019.103151</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Luiz Felipe Simões Hoffmann. Detection of liner surface defects in solid rocket motors using multilayer perceptron neural networks / Luiz Felipe Simões Hoffmann, Francisco Carlos Parquet Bizarria, José Walter Parquet Bizarria // Polymer Testing. — 2020. — Vol. 88. — 106559. https://doi.org/10.1016/j.polymertesting.2020.106559</mixed-citation><mixed-citation xml:lang="en">Luiz Felipe Simões Hoffmann. Detection of liner surface defects in solid rocket motors using multilayer perceptron neural networks / Luiz Felipe Simões Hoffmann, Francisco Carlos Parquet Bizarria, José Walter Parquet Bizarria // Polymer Testing. — 2020. — Vol. 88. — 106559. https://doi.org/10.1016/j.polymertesting.2020.106559</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Artificial Neural Networks and Fuzzy Logic in Nondestructive Evaluation / Ryszard Sikora, Piotr Baniukiewicz, Tomasz Chady [et al.] // Studies in Applied Electromagnetics and Mechanics. — 2014. — Vol. 38. — P.137−151. https://doi.org/10.3233/978-1-61499-354-4-137</mixed-citation><mixed-citation xml:lang="en">Artificial Neural Networks and Fuzzy Logic in Nondestructive Evaluation / Ryszard Sikora, Piotr Baniukiewicz, Tomasz Chady [et al.] // Studies in Applied Electromagnetics and Mechanics.  — 2014. — Vol. 38. — P.137−151. https://doi.org/10.3233/978-1-61499-354-4-137</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Puzyrev, V. Deep learning electromagnetic inversion with convolutional neural networks / Vladimir Puzyrev // Geophysical Journal International. — 2019. — Vol. 218 (2). — P. 817–832. https://doi.org/10.1093/gji/ggz204</mixed-citation><mixed-citation xml:lang="en">Puzyrev, V. Deep learning electromagnetic inversion with convolutional neural networks / Vladimir Puzyrev // Geophysical Journal International. — 2019. — Vol. 218 (2).  — P. 817–832. https://doi.org/10.1093/gji/ggz204</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Soloviev, A. N. Ultrasonic and Magnetic Flow Inspection Methods of Identification of Cracks in the Pipe Coupled with Artificial Neural Networks / A.N. Soloviev, B.V. Sobol, P. V. Vasiliev // Advanced Materials. Springer Proceedings in Physics. — 2017. — Vol. 193. — P. 381−395.</mixed-citation><mixed-citation xml:lang="en">Soloviev, A. N. Ultrasonic and Magnetic Flow Inspection Methods of Identification of Cracks in the Pipe Coupled with Artificial Neural Networks  / A.N. Soloviev, B.V. Sobol, P. V. Vasiliev // Advanced Materials. Springer Proceedings in Physics. — 2017. — Vol. 193. — P. 381−395.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Generative Artificial Neural Network Model for Visualization of Internal Defects of Structural Elements / A. Soloviev, B. Sobol, P. Vasiliev, A. Senichev // Advanced Materials. Springer Proceedings in Materials. — 2020. — Vol. 6. — P. 587−595. https://doi.org/10.1007/978-3-030-45120-2_48</mixed-citation><mixed-citation xml:lang="en">Generative Artificial Neural Network Model for Visualization of Internal Defects of Structural Elements / A. Soloviev, B. Sobol, P. Vasiliev, A.  Senichev // Advanced Materials. Springer Proceedings in Materials. — 2020. — Vol. 6. — P. 587−595. https://doi.org/10.1007/978-3-030-45120-2_48</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Identification of crack-like defect and investigation of stress concentration in coated bar / B.V. Sobol, A.N. Soloviev, E. V. Rashidova P. V. Vasiliev // PNRPU Mechanics Bulletin. — 2019. — No. 4. — P. 165−174. https://doi.org/10.15593/perm.mech/2019.4.16</mixed-citation><mixed-citation xml:lang="en">Identification of crack-like defect and investigation of stress concentration in coated bar / B.V. Sobol, A.N. Soloviev, E. V. Rashidova P. V. Vasiliev // PNRPU Mechanics Bulletin. — 2019. — No. 4. — P. 165−174. https://doi.org/10.15593/perm.mech/2019.4.16</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Yee, K. Numerical solution of initial boundary value problems involving Maxwell's equations in isotropic media / Kane Yee // IEEE Transactions on Antennas and Propagation. — 1966. — Vol. 14 (3). — P. 302−307. https://doi.org/10.1109/TAP.1966.1138693</mixed-citation><mixed-citation xml:lang="en">Yee, K. Numerical solution of initial boundary value problems involving Maxwell's equations in isotropic media / Kane Yee // IEEE Transactions on Antennas and Propagation. — 1966. — Vol. 14 (3). — P. 302−307. https://doi.org/10.1109/TAP.1966.1138693</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Berenger, J.-P. A perfectly matched layer for the absorption of electromagnetic waves / Jean-Pierre Berenger // Journal of Computational Physics. — 1994. — Vol. 114 (2). — P. 185−200.</mixed-citation><mixed-citation xml:lang="en">Berenger, J.-P. A perfectly matched layer for the absorption of electromagnetic waves / Jean-Pierre Berenger // Journal of Computational Physics. — 1994. — Vol. 114 (2). — P. 185−200.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Backpropagation applied to handwritten zip code recognition / Y. LeCun, B. Boser, J.S. Denker [et al.] // Neural Computation. — 1989. — Vol. 1 (4). — P. 541−551. https://doi.org/10.1162/neco.1989.1.4.541</mixed-citation><mixed-citation xml:lang="en">Backpropagation applied to handwritten zip code recognition / Y. LeCun, B. Boser, J.S. Denker [et al.] // Neural Computation. — 1989. — Vol. 1 (4). — P. 541−551. https://doi.org/10.1162/neco.1989.1.4.541</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Goodfellow, I. Deep learning. Vol. 1. /Ian. Goodfellow, Yoshua Bengio, Aaron Courville // MIT Press, Cambridge, 2016. — 800 p.</mixed-citation><mixed-citation xml:lang="en">Goodfellow, I. Deep learning. Vol. 1. /Ian. Goodfellow, Yoshua Bengio, Aaron Courville // MIT Press, Cambridge, 2016. — 800 p.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Krizhevsky, A. ImageNet classification with deep convolutional neural networks / A. Krizhevsky, I. Sutskever, G. E. Hinton // Advances in Neural Information Processing Systems. — 2012. — Vol. 25. — P. 1097– 1105.</mixed-citation><mixed-citation xml:lang="en">Krizhevsky, A. ImageNet classification with deep convolutional neural networks / A. Krizhevsky, I. Sutskever, G. E. Hinton // Advances in Neural Information Processing Systems. — 2012. — Vol. 25. — P. 1097– 1105.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Deep residual learning for image recognition / Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. — 2016. — P. 770−778. https://doi.org/10.1109/CVPR.2016.90</mixed-citation><mixed-citation xml:lang="en">Deep residual learning for image recognition / Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. — 2016. — P. 770−778. https://doi.org/10.1109/CVPR.2016.90</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Glorot, X. Understanding the difficulty of training deep feedforward neural networks / Xavier Glorot, Yoshua Bengio // JMLR Proceedings. — 2010. — Vol. 9. — P. 249−256.</mixed-citation><mixed-citation xml:lang="en">Glorot, X. Understanding the difficulty of training deep feedforward neural networks / Xavier Glorot, Yoshua Bengio // JMLR Proceedings. — 2010. — Vol. 9. — P. 249−256.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Ioffe, S. Batch normalization: accelerating deep network training by reducing internal covariate shift. / S. Ioffe, Ch. Szegedy // Proceedings of the 32nd International Conference on International Conference on Machine Learning. — 2015. — Vol. 37. — P. 448–456.</mixed-citation><mixed-citation xml:lang="en">Ioffe, S. Batch normalization: accelerating deep network training by reducing internal covariate shift. / S. Ioffe, Ch. Szegedy // Proceedings of the 32nd International Conference on International Conference on Machine Learning. — 2015. — Vol. 37. — P. 448–456.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Kingma, D. P. Adam: A method for stochastic optimization / D. P. Kingma, J. Ba // In: Proc. 3rd International Conference for Learning Representations. — 2014. arXiv preprint arXiv:1412.6980</mixed-citation><mixed-citation xml:lang="en">Kingma, D. P. Adam: A method for stochastic optimization / D. P. Kingma, J. Ba // In: Proc. 3rd International Conference for Learning Representations. — 2014. arXiv preprint arXiv:1412.6980</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Puzyrev, V. Deep learning electromagnetic inversion with convolutional neural networks / Vladimir Puzyrev // Geophysical Journal International. — 2019. — Vol. 218 (2). — P. 817–832. https://doi.org/10.1093/gji/ggz204</mixed-citation><mixed-citation xml:lang="en">Puzyrev, V. Deep learning electromagnetic inversion with convolutional neural networks / Vladimir Puzyrev // Geophysical Journal International. — 2019. — Vol. 218 (2). — P. 817–832. https://doi.org/10.1093/gji/ggz204</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Two-dimensional Ultrasound Imaging Technique based on Neural Network using Acoustic Simulation / Y. Nagatani, S. Okumura, S. Wu, T. Matsuda // Medical Physics. — 2020. arXiv:2004.08775v1</mixed-citation><mixed-citation xml:lang="en">Two-dimensional Ultrasound Imaging Technique based on Neural Network using Acoustic Simulation / Y. Nagatani, S. Okumura, S. Wu, T. Matsuda // Medical Physics. — 2020. arXiv:2004.08775v1</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Solov’ev, A. N. Ultrasonic Location of Inner Crack Defects in a Compound Elastic Cylinder Using an Artificial Neural-Network Apparatus / A. N. Solov’ev, B. V. Sobol’, P. V. Vasil’ev // Russian Journal of Nondestructive Testing. — 2016. — Vol. 52 (3). — P. 119–124.</mixed-citation><mixed-citation xml:lang="en">Solov’ev, A. N. Ultrasonic Location of Inner Crack Defects in a Compound Elastic Cylinder Using an Artificial Neural-Network Apparatus / A. N. Solov’ev, B. V. Sobol’, P. V. Vasil’ev // Russian Journal of Nondestructive Testing. — 2016. — Vol. 52 (3). — P. 119–124.</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>
