Automatic segmentation of microporous defects in composite film materials based on the improved attention U-Net module

Automatic segmentation of microporous defects in composite film materials based on the improved attention U-Net module

Dades bibliogràfiques
Parent link:	Quantitative InfraRed Thermography Journal.— .— London: Taylor & Francis Group Vol. 22, iss. 4.— 2025.— P. 313-328
Autor corporatiu:	National Research Tomsk Polytechnic University (570)
Altres autors:	Zhiyang Zhang, Jue Hu, Rongbang Wang, Xueyan Chen, Dazhi Yang, Vavilov V. P. Vladimir Platonovich, Yuxia Duan, Hai Zhang
Sumari:	Title screen Composite film materials offer several advantages, such as high strength-to-weight ratios, flexibility, durability, or cost-effectiveness, which make them ideal for a wide range of applications across various industries. However, microporous defects in the material compromise its durability and air-tightness. Thus far, few works have been performed on inquiring non-destructive testing methods intended for the detection of microporous defects in composite film materials. In this study, the automatic detection of microporous defects is achieved by using a thermal imaging inspection system developed on the basis of a laser infrared system and the U-Net. Innovatively, an improved attention module is added to U-Net to boost its detection performance. While using a laser as a heat source, a fibre laser beam shaper is chosen as the laser beam expansion to ensure a uniform intensity distribution of the laser beam within a small heating area. Experimental results show that the proposed method can reliably detect microporous defects in the composite film materials with sizes in the order of millimeters/micrometers. Текстовый файл AM_Agreement
Idioma:	anglès
Publicat:	2025
Matèries:	composite film material thermography microporous defect non-destructive testing U-Net электронный ресурс труды учёных ТПУ
Accés en línia:	https://doi.org/10.1080/17686733.2024.2387406
Format:	Electrònic Capítol de llibre
KOHA link:	https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=675795

Ítems similars

Improved U-Net deep network for rectal cancer tumour segmentation algorithm
per: Аксёнов С. В. Сергей Владимирович
Publicat: (2024)

The multi-dimensional ensemble empirical mode decomposition (MEEMD)
Publicat: (2017)

Rectal cancer image segmentation method based on U-Net network
per: Gubin E. I. Evgeny Ivanovich
Publicat: (2022)

Research on lung tumor image segmentation algorithm based on U⁃Net
per: Ван Юйцянь
Publicat: (2025)

Review of Defect Types in Metal Mold Castings
per: Bolotina I. O. Irina Olegovna
Publicat: (2018)

Contactless and nondestructive evaluation of residual stress distribution in modified and pure HDPE materials using a novel terahertz method and line-scan thermographic technique
Publicat: (2024)

Characterizing Depth of Defects with Low Size/Depth Aspect Ratio and Low Thermal Reflection by Using Pulsed IR Thermography
Publicat: (2021)

Using the Unsupervised Mixture of Gaussian Models for Multispectral Non-destructive Evaluation of the Replica of Botticelli’s “The Birth of Venus”
Publicat: (2023)

Модификация архитектуры сети U-Net для задач классификации и сегментации образцов пород
Publicat: (2025)

Thermographic Non-Destructive Evaluation for Natural Fiber-Reinforced Composite Laminates
Publicat: (2018)

Robust quantitative depth estimation on CFRP samples using active thermography inspection and numerical simulation updating
Publicat: (2017)

Optical excitation thermography for twill/plain weaves and stitched fabric dry carbon fibre preform inspection
Publicat: (2018)

Исследование эффективности сверточных нейронных сетей класса U-Net
per: Игольников Н. А.
Publicat: (2020)

Разработка алгоритмов для сегментации патологий сетчатки при диабетической ретинопатии с использованием архитектуры нейронной сети U-net
per: Лушников В. А.
Publicat: (2025)

Сегментация деревьев пихты на зашумленных снимках с БПЛА с использованием сверточной нейронной сети U-net
per: Малкин А. Ю. Артем Юрьевич
Publicat: (2024)

Modification of U-Net Network Architecture for Core Samples Analysis Automation
per: Denisov V. I. Vladislav Igorevich
Publicat: (2025)

Проектирование устройства управления оптическими нагревателями для теплового неразрушающего контроля композитных материалов методом LOCK-IN термографии на основе ESP32
per: Козлова М. А. Маргарита Александровна
Publicat: (2023)

Active IR Thermography Evaluation of Coating Thickness by Determining Apparent Thermal Effusivity
Publicat: (2020)

Применение сверточной нейронной сети U-Net для сегментации текстовых областей на изображениях реальных сцен
per: Иванова Ю. А. Юлия Александровна
Publicat: (2021)

Analyzing probability of detection as a function of defect size and depth in pulsed IR thermography
Publicat: (2022)

Сравнение архитектур U-Net и FCN для детектирования текстовых надписей на изображениях реальных сцен
per: Иванова Ю. А. Юлия Александровна
Publicat: (2022)

Characterising Hidden Defects in GFRP/CFRP Composites by using Laser Vibrometry and Active IR Thermography
Publicat: (2022)

Enhancing Generalizability of a Machine Learning Model for Infrared Thermographic Defect Detection by Using 3D Numerical Modeling
per: Chulkov A. O. Arseniy Olegovich
Publicat: (2024)

Automated detection and characterization of defects in composite-metal structures by using active infrared thermography
Publicat: (2023)

Классификация пихты, поврежденной уссурийским полиграфом, по снимкам С БПЛА с использованием нейронной сети U-Net
per: Маслов К. А.
Publicat: (2020)

Модели U-Net для семантической сегментации повреждённых деревьев сосны сибирской кедровой на снимках с БПЛА
Publicat: (2022)

Вихретоковый дефектоскоп с накладным преобразователем
per: Разуваев И. Н. Иван Николаевич
Publicat: (2021)

Исследование аппаратно-реализованных сверточных нейронных сетей класса U-Net
Publicat: (2023)

Nondestructive testing of composite T-Joints by TNDT and other methods
Publicat: (2021)

Automated procedure for detecting and characterizing defects in GFRP composite by using thermal nondestructive testing
Publicat: (2021)

Исследование модели сверточной нейронной сети Mo-U-Net с робастной функции потерь Хьюбера в условиях зашумленных изображений
per: Малкин А. Ю. Артем Юрьевич
Publicat: (2025)

Analyzing patterns of heat generated by the tensile loading of steel rods containing discontinuity-like defects
per: Moyseychik E. Eugeny
Publicat: (2017)

An Automated Algorithm for Constructing Maps of Defects in Active Thermal Testing
per: Chulkov A. O. Arseniy Olegovich
Publicat: (2019)

Automatic Segmentation by the Method of Interval Fusion with Preference Aggregation When Recognizing Weld Defects
per: Muravyov (Murav’ev) S. V. Sergey Vasilyevich
Publicat: (2023)

Вихретоковый контроль структуры электропроводящих объектов
per: Мокровицкий М. Е. Максим Евгеньевич
Publicat: (2024)

Thermal stresses applied on helicopter blades useful to retrieve defects by means of infrared thermography and speckle patterns
Publicat: (2020)

Применение средств машинного обучения для исследования образцов керна
per: Денисов В. И.
Publicat: (2024)

Noise-limited thermal/infrared nondestructive testing
per: Vavilov V. P. Vladimir Platonovich
Publicat: (2014)

Principle, Equipment and Applications of Line-Scanning Infrared Thermographic NDT
Publicat: (2023)

Modelling of Infrared Glow in Rock Holes
Publicat: (2019)