4.7 Article

Terahertz transfer characterization for composite delamination under variable conditions based on deep adversarial domain adaptation

Related references

Note: Only part of the references are listed.
Article Engineering, Mechanical

Double Gaussian mixture model-based terahertz wave dispersion compensation method using convex optimization technique

Yafei Xu et al.

Summary: A novel dispersion compensation strategy based on the double Gaussian mixture model (DGMM) is proposed to suppress the dispersion effect in THz echoes, providing an effective approach for improving the accuracy of THz detection in nondestructive testing applications.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

Article Engineering, Multidisciplinary

Full scale promoted convolution neural network for intelligent terahertz 3D characterization of GFRP delamination

Yafei Xu et al.

Summary: In this paper, an effective and reliable 3D THz characterization system based on deep learning methods is proposed for automatic localization and imaging of delamination defects in GFRP composites. The system achieves high precision localization through the dual mechanisms of full-scale feature learning and promoted classifier, and obtains the 2D and 3D information of delamination defects using the class encoding strategy.

COMPOSITES PART B-ENGINEERING (2022)

Article Engineering, Electrical & Electronic

Infrared and Visible Image Fusion via Decoupling Network

Xue Wang et al.

Summary: This article proposes a decoupling network-based method for infrared and visible image fusion, which effectively retains the texture details and luminance information of the source images while preserving the high-contrast regions. Extensive experiments demonstrate that the proposed method generates fused images with saliency objects and clear details, outperforming other state-of-the-art methods.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

Article Mechanics

Three-dimensional mechanical behavior of composite with fibre-matrix delamination through homogenization of micro-structure

Simon P. H. Skovsgaard et al.

Summary: Delamination is a crucial failure mode in fibre composites, leading to loss of stiffness and ultimately structure failure. Modelling delamination is challenging due to material complexity. A new three-dimensional homogenization approach successfully incorporates delamination into the structural response.

COMPOSITE STRUCTURES (2021)

Article Engineering, Multidisciplinary

Three-dimensional nondestructive characterization of delamination in GFRP by terahertz time-of-flight tomography with sparse Bayesian learning-based spectrum-graph integration strategy

Yafei Xu et al.

Summary: The study proposes a sparse Bayesian learning-based spectrum-graph integration method for super-resolution characterization of multi-ply delamination defects in GFRP composites. By implementing spectrum localization and graph quantification processes, accurate depth location, transverse location, and size of each delamination defect can be obtained with an estimated accuracy of over 95%. This strategy enables quantitative and simultaneous characterization of axial and transverse information of delamination defects within GFRP composites with high resolution.

COMPOSITES PART B-ENGINEERING (2021)

Article Engineering, Civil

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Di Feng et al.

Summary: Deep learning is driving recent advancements in perception for autonomous driving through the fusion of multiple sensors, but questions regarding network architecture design, fusion timing, and methods remain open. This review aims to systematically summarize methodologies for deep multi-modal object detection and semantic segmentation in autonomous driving, while also discussing challenges and open questions. The reviewed study provides an overview of the topic, fusion methodologies, and offers an interactive online platform for further exploration.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

Article Materials Science, Characterization & Testing

Comparative study of ultrasonic techniques for reconstructing the multilayer structure of composites

Xiaoyu Yang et al.

Summary: This study compares the performance of different ultrasonic pulse-echo approaches for extracting the ply-by-ply structure of multilayered composites, with the 5 MHz ultrasound coupled to analyticsignal analysis with log-Gabor filter showing the best performance for reconstructing the multilayer structure of the studied composites.

NDT & E INTERNATIONAL (2021)

Article Computer Science, Artificial Intelligence

Multi-scale Attention Convolutional Neural Network for time series classification

Wei Chen et al.

Summary: With the rapid increase of data availability, a novel deep learning model MACNN has been developed to solve the TSC problem, achieving the best performance on 85 UCR standard datasets and outperforming other methods by a large margin.

NEURAL NETWORKS (2021)

Article Mechanics

Detection of delamination defects inside carbon fiber reinforced plastic laminates by measuring eddy-current loss

Teng Wang et al.

Summary: This study proposes a method to detect delamination inside carbon fiber reinforced plastics by measuring eddy-current loss, using an 8-shaped coil probe and unique signal extraction technique. Experimental results show that the vertical 8-shaped probe of the proposed method has higher sensitivity to delamination detection and less noise interference.

COMPOSITE STRUCTURES (2021)

Review Instruments & Instrumentation

Automatic defect prediction in glass fiber reinforced polymer based on THz-TDS signal analysis with neural networks

Qiang Wang et al.

Summary: This study presents a novel approach to predict defect depths in GFRP using terahertz time-domain spectroscopy signal analysis with neural networks. Results indicate that the one-dimension convolutional neural network model outperforms other models in defect detection and classification, achieving high recall rates and macro F1 scores. With automatic defect detection and classification, a terahertz image showing defect locations and depths can be efficiently reconstructed.

INFRARED PHYSICS & TECHNOLOGY (2021)

Article Computer Science, Artificial Intelligence

Zero-shot domain adaptation for natural language inference by projecting superficial words out

Wanyun Cui et al.

Summary: This paper introduces HardDrop and SoftDrop models to project superficial information and optimize general representation in natural language inference, achieving better adaptation and inference accuracy across different domains.

KNOWLEDGE-BASED SYSTEMS (2021)

Article Engineering, Electrical & Electronic

Terahertz Time-of-Flight Tomography Beyond the Axial Resolution Limit: Autoregressive Spectral Estimation Based on the Modified Covariance Method

Min Zhai et al.

JOURNAL OF INFRARED MILLIMETER AND TERAHERTZ WAVES (2020)

Article Computer Science, Hardware & Architecture

Generative Adversarial Networks

Ian Goodfellow et al.

COMMUNICATIONS OF THE ACM (2020)

Article Computer Science, Artificial Intelligence

InceptionTime: Finding AlexNet for time series classification

Hassan Ismail Fawaz et al.

DATA MINING AND KNOWLEDGE DISCOVERY (2020)

Article Engineering, Electrical & Electronic

Deep Semisupervised Domain Generalization Network for Rotary Machinery Fault Diagnosis Under Variable Speed

Yixiao Liao et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

Article Engineering, Electrical & Electronic

Detection of Small Defects in Composite Insulators Using Terahertz Technique and Deconvolution Method

Hongwei Mei et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

Article Geochemistry & Geophysics

Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set

Shunping Ji et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

Review Computer Science, Artificial Intelligence

Deep learning for time series classification: a review

Hassan Ismail Fawaz et al.

DATA MINING AND KNOWLEDGE DISCOVERY (2019)

Article Automation & Control Systems

Estimation of Damage Thickness in Fiber-Reinforced Composites using Pulsed Thermography

Adisorn Sirikham et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Article Engineering, Electrical & Electronic

Multi-Layer domain adaptation method for rolling bearing fault diagnosis

Xiang Li et al.

SIGNAL PROCESSING (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep Learning-Based Image Segmentation on Multimodal Medical Imaging

Zhe Guo et al.

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES (2019)

Article Materials Science, Composites

Microwave nondestructive detection and quantitative evaluation of kissing defects in GFRP laminates

Peiyu Wang et al.

COMPOSITES SCIENCE AND TECHNOLOGY (2018)

Article Computer Science, Information Systems

LSTM Fully Convolutional Networks for Time Series Classification

Fazle Karim et al.

IEEE ACCESS (2018)

Article Engineering, Multidisciplinary

Non-destructive evaluation of puncture region in polyethylene composite by terahertz and X-ray radiation

Norbert Palka et al.

COMPOSITES PART B-ENGINEERING (2016)

Article Engineering, Multidisciplinary

Monitoring fatigue-induced transverse matrix cracks in laminated composites using built-in acousto-ultrasonic techniques

Cecilia Larrosa Wilson et al.

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL (2016)

Article Multidisciplinary Sciences

Terahertz time-gated spectral imaging for content extraction through layered structures

Albert Redo-Sanchez et al.

NATURE COMMUNICATIONS (2016)

Article Statistics & Probability

KERNEL DENSITY ESTIMATION VIA DIFFUSION

Z. I. Botev et al.

ANNALS OF STATISTICS (2010)

Article Engineering, Electrical & Electronic

Terahertz quality control of polymeric products

Frank Rutz et al.

INTERNATIONAL JOURNAL OF INFRARED AND MILLIMETER WAVES (2006)