1. Главная
  2. Ресурсы
  3. Библиотечный поиск
Assessment ofAnisotropic AcousticProperties inAdditivelyManufacturedMaterials:Experimental,Computational, andDeep LearningApproaches Malashin IvanTynchenko VadimMartysyuk Dmitry2024 год

Assessment of Anisotropic Acoustic Properties in Additively Manufactured Materials: Experimental, Computational, and Deep Learning Approaches
статья из журнала

Дополнительные ссылки: eLibrary
База данных: Каталог библиотеки СФУ
Библиографическое описание: Assessment of Anisotropic Acoustic Properties in Additively Manufactured Materials: Experimental, Computational, and Deep Learning Approaches : научное издание / I. I. Malashin [et al.]. - Текст : непосредственный // Sensors. - 2024. - Т. 24, № 14. - P. 4488. - ISSN 1424-8220. - ISSN 1424-3210, DOI 10.3390/s24144488.
Аннотация: <jats:p>The influence of acoustic anisotropy on ultrasonic testing reliability poses a challenge in evaluating products from additive technologies (AT). This study investigates how elasticity constants of anisotropic materials affect defect signal amplitudes in AT products. Experimental measurements on AT samples were conducted to determine elasticity constants. Using Computational Modeling and Simulation Software (CIVA), simulations explored echo signal changes across ultrasound propagation directions. The parameters A13 (the ratio between the velocities of ultrasonic transverse waves with vertical and horizontal polarizations at a 45-degree angle to the growth direction), A3 (the ratio for waves at a 90-degree angle), and Ag (the modulus of the difference between A13 and A3) were derived from wave velocity relationships and used to characterize acoustic anisotropy. Comparative analysis revealed a strong correlation (0.97) between the proposed anisotropy coefficient Ag and the amplitude changes. Threshold values of Ag were introduced to classify anisotropic materials based on observed amplitude changes in defect echo signals. In addition, a method leveraging deep learning to predict Ag based on data from other anisotropy constants through genetic algorithm (GA)-optimized neural network (NN) architectures is proposed, offering an approach that can reduce the computational costs associated with calculating such constants.</jats:p>
Год издания: 2024
Авторы: Malashin Ivan , Tynchenko Vadim , Martysyuk Dmitry , Shchipakov Nikita , Krysko Nikolay , Degtyarev Maxim , Nelyub Vladimir , Gantimurov Andrei , Borodulin Aleksei , Galinovsky Andrey
Издательство: Molecular Diversity Preservation International
Источник: Sensors
Выпуск: Т. 24, № 14
Номера страниц: 4488
Держатель оригинала документа: Bauman Moscow State Technical University, Moscow 105005, Russia, Far Eastern Federal University, Vladivostok 690922, Russia
Количество экземпляров:
Твёрдая копия издания отсутствует в фонде библиотеки

Похожие публикации

Assessment of WaterHydrochemicalParameters UsingMachine LearningTools Malashin IvanNelyub VladimirBorodulin Aleksei2025 год

Assessment of Water Hydrochemical Parameters Using Machine Learning Tools : научное издание

  • Malashin Ivan и др.
  • 2025 год
Application ofnon-parametriclearning method insoil suitabilityassessment in presentday economy Kukartsev VladislavGantimurov AndreiKravtsov Kirill2024 год

Application of non-parametric learning method in soil suitability assessment in present day economy : научное издание

  • Kukartsev Vladislav и др.
  • 2024 год
Controlled Porosityof Selective LaserMelting-ProducedThermal Pipes:Experimental Analysisand Machine Learning… Malashin IvanMartysyuk DmitryTynchenko Vadim2024 год

Controlled Porosity of Selective Laser Melting-Produced Thermal Pipes: Experimental Analysis and… : статья из журнала

  • Malashin Ivan и др.
  • 2024 год