4.7 Article

Digital image correlation (DIC) based damage detection for CFRP laminates by using machine learning based image semantic segmentation

Related references

Note: Only part of the references are listed.
Article Computer Science, Interdisciplinary Applications

Semantic segmentation of high-resolution remote sensing images based on a class feature attention mechanism fused with Deeplabv3+

Zhimin Wang et al.

Summary: This study proposed a new semantic segmentation network CFAMNet for remote sensing images, which improves semantic information extraction efficiency and segmentation accuracy through class feature attention mechanism and multi-parallel atrous spatial pyramid pooling structure. The network achieved excellent segmentation results in experiments on the public dataset.

COMPUTERS & GEOSCIENCES (2022)

Article Engineering, Industrial

Deep DIC: Deep learning-based digital image correlation for end-to-end displacement and strain measurement

Ru Yang et al.

Summary: Traditional digital image correlation (DIC) methods have limitations in dealing with large deformations and poor speckle pattern quality. To overcome these challenges, we propose a new deep learning-based DIC approach, Deep DIC, which achieves accurate, robust, and real-time displacement and strain prediction in experiments.

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY (2022)

Article Engineering, Mechanical

Deep learning based segmentation using full wavefield processing for delamination identification: A comparative study

Abdalraheem A. Ijjeh et al.

Summary: This paper investigates several deep fully convolutional neural network models for delamination detection and localization in composite materials. The models were trained and validated on a specific dataset and achieved improved accuracy compared to previous models.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

Article Engineering, Civil

Fatigue behavior of CFRP/Al adhesive joints - Failure mechanisms study using digital image correlation (DIC) technique

Zongkai He et al.

Summary: Fatigue failure is a common cause of structural failure. This study aims to explore the failure mechanisms of a CFRP/aluminum adhesive joint by using DIC technique to record real-time fatigue process. The results show that the fracture behavior of the joints is opposite between high and low stress levels, indicating the need for selective design and enhancement strategies according to working conditions.

THIN-WALLED STRUCTURES (2022)

Article Engineering, Mechanical

Vibration-based damage identification in composite plates using 3D-DIC and wavelet analysis

Guangyong Sun et al.

Summary: This study presents a damage detection method based on experimental modal analysis, combining the advantages of 3D-DIC and 2D-CWT techniques. The method is highly accurate and practical for nondestructive damage detection.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

Article Mechanics

Crack damage identification of a thick composite sandwich structure based on Gaussian Processes classification

Zeyu Liu et al.

Summary: The study focuses on crack damage identification of thick composite sandwich structures using Gaussian Processes classification based on numerical simulations. Data-driven probabilistic interpretation of damage detection is the main goal. Features extracted by Discrete Wavelet Transform are used to train and test the GP model for assessing the health status of the structure.

COMPOSITE STRUCTURES (2021)

Review Mechanics

Advances, limitations and prospects of nondestructive testing and evaluation of thick composites and sandwich structures: A state-of-the-art review

Walter Nsengiyumva et al.

Summary: Composite materials have become increasingly popular in high-tech and engineering applications, being used more frequently in primary and secondary load-bearing structures. Employing nondestructive testing and evaluation techniques can help detect and repair flaws in materials early, improving resource efficiency and safety.

COMPOSITE STRUCTURES (2021)

Article Optics

When Deep Learning Meets Digital Image Correlation

S. Boukhtache et al.

Summary: This paper introduces the development of a CNN model (StrainNet) for retrieving displacement and strain fields from pairs of images of a flat speckled surface, and demonstrates its successful performance of measurements. Compared to DIC, StrainNet achieves competitive results in terms of metrological performance and computing time, making it a viable alternative for real-time applications.

OPTICS AND LASERS IN ENGINEERING (2021)

Article Engineering, Mechanical

Automatic detection of fatigue crack paths using digital image correlation and convolutional neural networks

Tobias Strohmann et al.

Summary: The occurrence of fatigue cracks is a natural part of engineering structures subjected to nonconstant loads, making accurate description of cracks crucial for safety standards. This study successfully implemented a deep convolutional neural network with digital image correlation to detect crack paths and tips, demonstrating accuracy and effectiveness in experiments. Additionally, incorporating synthetic data from finite element analyses improved the detection accuracy of cracks beyond the range of original training data.

FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES (2021)

Article Materials Science, Composites

Advanced deep learning model-based impact characterization method for composite laminates

Kyung-Chae Jung et al.

Summary: This study aimed to develop a structural health monitoring system for smart composite structures using signal processing, deep learning algorithms, and optimization theory. Piezoelectric ribbon sensors and discrete wavelet transform were utilized for creating smart composite fabric and converting impact signals into input image data. Optimal hyperparameter values were determined based on Bayesian optimization theory, and data augmentation was employed to ensure sufficient data for training impact characterization models. Performance of each optimized neural network model was evaluated by comparing test errors under different conditions.

COMPOSITES SCIENCE AND TECHNOLOGY (2021)

Article Engineering, Manufacturing

Automated vision-based inspection of drilled CFRP composites using multi-light imaging and deep learning

Ali Maghami et al.

Summary: The study proposes a novel and fully autonomous system for detecting and segmenting damages and cracks around drilled holes in CFRPs. The system includes an automated multi-light imaging end-effector, image processing steps, and a deep Fully Convolutional Network (FCN) with the U-Net architecture for pixel-wise semantic segmentation.

CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY (2021)

Article Mechanics

Autonomous damage recognition in visual inspection of laminated composite structures using deep learning

Sakineh Fotouhi et al.

Summary: This study utilized deep learning techniques to quantitatively assess the visual detectability of different types of in-service damage in laminated composite structures. By creating an image dataset and utilizing various convolutional neural networks for classification, the study successfully identified the severity and types of damage with high accuracy. It was found that using AlexNet network with a relatively small image dataset provided the highest accuracy level compared to other models.

COMPOSITE STRUCTURES (2021)

Article Engineering, Marine

Bridge Crack Semantic Segmentation Based on Improved Deeplabv3+

Huixuan Fu et al.

Summary: The study proposed a crack detection method based on an improved DeepLabv3+ algorithm utilizing deep learning technology. Experimental results demonstrated that the method achieved higher accuracy in crack segmentation, showing improved ability to accurately identify crack details, thereby proving the effectiveness of the algorithm.

JOURNAL OF MARINE SCIENCE AND ENGINEERING (2021)

Article Engineering, Multidisciplinary

Strain measurement during tensile testing using deep learning-based digital image correlation

Hyeon-Gyu Min et al.

MEASUREMENT SCIENCE AND TECHNOLOGY (2020)

Article Engineering, Mechanical

Comparative study on metal/CFRP hybrid structures under static and dynamic loading

Guohua Zhu et al.

INTERNATIONAL JOURNAL OF IMPACT ENGINEERING (2020)

Article Engineering, Mechanical

Tensile performance of basalt fiber composites with open circular holes and straight notches

Guangyong Sun et al.

INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES (2020)

Article Computer Science, Artificial Intelligence

A Brief Survey on Semantic Segmentation with Deep Learning

Shijie Hao et al.

NEUROCOMPUTING (2020)

Article Materials Science, Composites

Fatigue monitoring of flax fibre reinforced epoxy composites using integrated fibre-optical FBG sensors

Gabor Szebenyi et al.

COMPOSITES SCIENCE AND TECHNOLOGY (2020)

Article Engineering, Multidisciplinary

A novel failure criterion based upon forming limit curve for thermoplastic composites

Zhen Wang et al.

COMPOSITES PART B-ENGINEERING (2020)

Article Computer Science, Information Systems

Semantic Segmentation of Litchi Branches Using DeepLabV3+Model

Hongxing Peng et al.

IEEE ACCESS (2020)

Article Engineering, Multidisciplinary

A novel method of vibration modes selection for improving accuracy of frequency-based damage detection

Jingwen Pan et al.

COMPOSITES PART B-ENGINEERING (2019)

Article Computer Science, Artificial Intelligence

Survey on semantic segmentation using deep learning techniques

Fahad Lateef et al.

NEUROCOMPUTING (2019)

Article Engineering, Multidisciplinary

Full-field strain prediction using mode shapes measured with digital image correlation

Kedar Bharadwaj et al.

MEASUREMENT (2019)

Article Engineering, Multidisciplinary

Low velocity impact behavior of interlayer hybrid composite laminates with carbon/glass/basalt fibres

Dongdong Chen et al.

COMPOSITES PART B-ENGINEERING (2019)

Article Instruments & Instrumentation

Automatic defects detection in CFRP thermograms, using convolutional neural networks and transfer learning

Numan Saeed et al.

INFRARED PHYSICS & TECHNOLOGY (2019)

Review Computer Science, Artificial Intelligence

A survey on deep learning techniques for image and video semantic segmentation

Alberto Garcia-Garcia et al.

APPLIED SOFT COMPUTING (2018)

Article Computer Science, Artificial Intelligence

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Liang-Chieh Chen et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

Article Engineering, Mechanical

Mechanical properties of hybrid composites reinforced by carbon and basalt fibers

Guangyong Sun et al.

INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES (2018)

Proceedings Paper Engineering, Mechanical

NDT thermographic techniques on CFRP structural components for aeronautical application

V. Dattoma et al.

AIAS2017 - 46TH CONFERENCE ON STRESS ANALYSIS AND MECHANICAL ENGINEERING DESIGN (2018)

Article Computer Science, Information Systems

Benchmark Analysis of Representative Deep Neural Network Architectures

Simone Bianco et al.

IEEE ACCESS (2018)

Article Computer Science, Artificial Intelligence

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Vijay Badrinarayanan et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Article Computer Science, Artificial Intelligence

The PASCAL Visual Object Classes Challenge: A Retrospective

Mark Everingham et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2015)

Article Mechanics

Analysis of adhesively bonded repairs in composites: Damage detection and prognosis

M. A. Caminero et al.

COMPOSITE STRUCTURES (2013)

Article Instruments & Instrumentation

Automatic detection of impact damage in carbon fiber composites using active thermography

R. Usamentiaga et al.

INFRARED PHYSICS & TECHNOLOGY (2013)

Review Green & Sustainable Science & Technology

Review of structural health and cure monitoring techniques for large wind turbine blades

P. J. Schubel et al.

RENEWABLE ENERGY (2013)