检索结果-内蒙古大学图书馆

defect quantification Using Novel Civil RGB-D Dataset 1

Annual Conference of the Canadian-Society-for-Civil-Engineering (CSCE)

作者： Midwinter, Max Al-Sabbag, Zaid Abbas Bajaj, Rishabh Yeum, Chul Min Univ Waterloo Waterloo ON N2L 3G1 Canada

ISBN: (数字)9783031615399

ISBN: (纸本)9783031615412;9783031615399;9783031615382

Routine visual structural inspection is a tedious but vital part of structural health monitoring. Many researchers have proposed novel methodologies to automatically classify, detect, and segment structural defects (i.e., crack, spall, etc.) from images. Yet, the scale from single images is ambiguous, which is an important prior for severity classification. While monocular depth estimation is an ill-posed problem, deep learning methods have made great progress field, greatly spurred by a plethora of open RGB-D datasets. However, to the best knowledge of the authors, there is no RGB-D dataset in the civil engineering domain. In this work, the authors seek to develop an efficient method to build an RGB-D dataset for the civil research community. The authors review popular RGB-D data collection paradigms and propose a LiDAR-based data collection method. Finally, the authors use the collected data to create a deep convolutional monocular depth estimation model for defect quantification. The authors hope this work can help other researchers incorporate depth information in their projects and to create a community to share civil RGB-D data to help advance the state-of-the-art in the automated visual structural inspection.

关键词： RGB-D dataset Deep learning defect quantification

来源：评论

学校读者我要写书评

暂无评论

Brief Review of Vibrothermography and Optical Thermography for defect quantification in CFRP Material

引用

SENSORS 2025年第6期25卷 1847-1847页

作者： Hidayat, Zulham Avdelidis, Nicolas P. Fernandes, Henrique Cranfield Univ Fac Engn & Appl Sci Integrated Vehicle Hlth Management IVHM Ctr Bedford MK43 0AL England Univ Southampton Sch Engn Dept Aeronaut & Astronaut Boldrewood Innovat Campus Southampton SO16 7QF England Univ Fed Uberlandia Fac Comp BR-38408100 Uberlandia Brazil

Quantifying defects in carbon-fiber-reinforced polymer (CFRP) composites is crucial for ensuring quality control and structural integrity. Among non-destructive evaluation techniques, thermography has emerged as a promising solution for defect detection and characterization. This literature review synthesizes current advancements in active thermography methods, with a particular focus on vibrothermography and optical thermography, in identifying defects such as delaminations and barely visible impact damage (BVID) in CFRP composites. The review evaluates state-of-the-art techniques, highlighting the advanced applications of optical thermography. It identifies a critical research gap in the integration of vibrothermography with advanced image-processing methods, such as computer vision, which is more commonly applied in optical thermography. Addressing this gap holds significant potential to enhance defect quantification accuracy, improve maintenance practices, and ensure the safety of composite structures.

关键词： thermography pulsed thermography vibrothermography defect quantification principal component analysis variant of principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A High-Precision defect quantification Method Using a Unilateral Oblique Focusing Guided Wave EMAT and a Theory-Informed Explainable Progressive Residual Deep Convolutional Network

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Sun, Hongyu Tu, Jun Feng, Qibo Huang, Songling Peng, Lisha He, Qixin Li, Jiakun Li, Shisong Beijing Jiaotong Univ Sch Phys Sci & Engn Beijing 100044 Peoples R China East China Jiaotong Univ State Key Lab Performance Monitoring & Protecting Nanchang 330013 Jiangxi Peoples R China Hubei Univ Technol Sch Mech Engn Key Lab Modern Mfg Qual Engn Wuhan 430068 Hubei Peoples R China Tsinghua Univ Dept Elect Engn State Key Lab Power Syst Beijing 100084 Peoples R China

Using ultrasonic guided wave technology to quantify defects has always been challenging, especially for nonarray electromagnetic acoustic transducers (EMATs). This is because EMATs are always implemented with complicated defect feature extraction and signal processing algorithms and have a low signal-to-noise ratio. Therefore, we propose a high-intensity unilateral oblique focusing EMAT (UOF-EMAT) to address these problems. Based on this new EMAT, the principle of guided wave defect quantification was studied, and a theory-informed progressive residual deep convolutional network (ProResNet) was developed. The results demonstrate that the proposed UOF-EMAT can achieve unilateral focusing of the guided wave signal and increase the signal intensity at the preset focal position by 11 dB compared with the traditional bilateral focusing EMAT. Moreover, compared with the quantification results of general shallow and deep neural networks (NNs), the defect quantification error of ProResNet is reduced by approximately 9-10 and 1.6-5.2 times, respectively. Furthermore, to explain the internal functions of ProResNet visually and verify the training logic of the network, the Grad-CAM++ method was used. Compared with the unexplainable direct visual method, the Grad-CAM++ method can effectively interpret the function of ProResNet visually, and the effectiveness of the theory-informed deep ProResNet in defect quantification is verified. The source code (with description) and database used in this article are available at (https://***/ShyTHU/***).

关键词： Acoustics Feature extraction Artificial neural networks Focusing Transducers Convolutional neural networks Visualization defect quantification electromagnetic acoustic transducers (EMAT) Grad-CAM plus plus progressive residual network unilateral oblique focusing (UOF) visual explanation

来源：评论

学校读者我要写书评

暂无评论

Microcrack defect quantification Using a Focusing High-Order SH Guided Wave EMAT: The Physics-Informed Deep Neural Network GuwNet

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第5期18卷 3235-3247页

作者： Sun, Hongyu Peng, Lisha Lin, Junming Wang, Shen Zhao, Wei Huang, Songling Tsinghua Univ State Key Lab Power Syst Dept Elect Engn Beijing 100084 Peoples R China Eddysun Xiamen Elect Co Ltd Xiamen 361008 Peoples R China

It is challenging to apply deep learning in professional fields that lack big data support, especially in industrial structure health assessments using ultrasonic guided wave nondestructive testing (NDT) method. To solve this problem, one feasible solution is to introduce the concept of NDT physics into a deep neural network to compensate for the network's poor predictive abilities when trained on small datasets. Therefore, we propose a physics-informed deep neural network, named GuwNet, based on a unidirectional oblique-focusing (UOF) high-frequency, high-order shear horizontal guided wave electromagnetic acoustic transducer (EMAT) to quantify microcrack defects more accurately. First, the designed focused-transmission omnidirectional-reception UOF-EMAT can produce pure high-frequency, high-order guided waves. Through a circumferential arrangement of multiple receiving transducers, the maximum amount of information can be obtained regarding the reflected waves of the defect. This method solves the inherent problems of an EMAT (i.e., low energy conversion efficiency) and achieves effective detection of microcrack defects. Second, we study the quantification principle of microcrack defects suitable for UOF-EMAT, and propose a deep neural network using physical knowledge regarding this theory. We rationally design the network structure based on the quantitative principles and logic obtained from this article. In addition, feedback and feedforward loss functions suitable for evaluating different forms of variables are proposed to integrate the physical concepts of ultrasonic guided wave testing into the neural network training. Finally, we verify the performance of the proposed GuwNet based on the UOF-EMAT. Compared with traditional nonphysics-informed methods, the length, depth, and direction of the quantification errors are reduced to 0.127 mm, 0.279% d(t), and 1.843 degrees, respectively, and the average quantification error is reduced by more than 80%.

关键词： Acoustics Deep learning Feature extraction Transducers Focusing Neural networks Informatics Deep neural network defect quantification electromagnetic acoustic transducer (EMAT) focusing microcrack physics-informed ultrasonic guided waves

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional modeling and defect quantification of existing concrete bridges based on photogrammetry and computer aided design

引用

AIN SHAMS ENGINEERING JOURNAL 2023年第12期14卷

作者： Abu Dabous, Saleh Al-Ruzouq, Rami Llort, Daniel Univ Sharjah Dept Civil & Environm Engn Sharjah U Arab Emirates Univ Sharjah Res Inst Sci & Engn Sustainable Civil Infrastructure Syst Res Grp Sharjah U Arab Emirates Minist Energy & Infrastruct Abu Dhabi U Arab Emirates

Bridge infrastructure is aging and deteriorating and requires innovative condition monitoring and assessment to ensure safety and maintain serviceability. Current practices for bridge condition assessment depend mainly on visual inspection. Innovative data collection technologies can assist in bridge inspection and defect identification and circumvent the limitations of traditional visual inspection. This research aims to apply photogrammetry principles and image processing techniques to develop a fullscale three-dimensional (3D) bridge structure model for defect identification and quantification. The data source to establish the point cloud models is a set of digital images taken at the bridge site. The point cloud models are developed by analyzing high-resolution images captured using a Nikon D4S camera. The images are captured from different positions/locations to provide extensive stereo coverage and maximum overlapping. Two hundred images of the bridge are processed with PhotoModeler software along with the calibration information, and ground control points (GCPs) coordinates to create the models. A standard digital close-range image processing is implemented to generate the 3D points cloud model. The calibration and orientation processes are made over a deformed situation. However, the developed CAD bridge drawings depict the original undeformed geometry. The extracted bridge inventory data from the 3D model, including bridge geometry information and bridge damage quantification, can provide a baseline for the bridge monitoring system to detect bridge deterioration over the years. The developed photogrammetric 3D model has an RMSE of 0.0081 m and uncertainty of +/- 0.0041 m. Future research can aim at developing reusable parametric objects for bridges in Revit and coding scripts using programming languages such as Dynamo or Python to perform further analysis of the captured information.(c) 2023 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engi

关键词： Bridge Failure 3D model Close-range photogrammetry Image processing defect quantification Bridge Monitoring

来源：评论

学校读者我要写书评

暂无评论

Probability of Detection or Eddy Current Pulsed Thermography of Angular defect quantification

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2018年第12期14卷 5658-5666页

作者： Zhu, Junzhen Min, Qingxu Wu, Jianbo Tian, Gui Yun Newcastle Univ Sch Engn Newcastle Upon Tyne NE1 7RU Tyne & Wear England Army Acad Armored Forces Dept Vehicle Engn Beijing Peoples R China Sichuan Univ Sch Mfg Sci & Engn Chengdu Sichuan Peoples R China Univ Elect Sci & Technol China Sch Automat Engn Chengdu Sichuan Peoples R China

Eddy current pulsed thermography (ECPT) as one of the emerging nondestructive testing and evaluation (NDT&E) techniques has been used for the evaluation of the integrity of rail tracks, especially for rolling contact fatigue (RCF) detection and crack sizing. This paper proposes a probability of detection (POD) analysis framework for the ECPT system. Specifically, three different features, i.e., max thermal response, first-order differential imaging, and ratio mapping of the first-order differential imaging, were used to quantify the length of the angular slot by linear fitting. Based on the fitting relation between these features and the slot length, POD curves for linear-coil-based ECPT system of angular defect detection were calculated and compared. Results show that the max thermal response feature has the highest repeatability and detectability for shorter slot detection. First-order differential imaging and ratio mapping features are more convincing for longer slot detection.

关键词： Angular defect defect quantification eddy current pulsed thermography (ECPT) feature extraction and evaluation probability of detection (POD) rolling contact fatigue (RCF)

来源：评论

学校读者我要写书评

暂无评论

Investigation of a new feature for angular defect quantification by eddy current pulsed thermography

Investigation of a new feature for angular defect quantifica...

引用

IEEE International Instrumentation and Measurement Technology Conference

作者： Junzhen Zhu Guiyun Tian Wenbo Duan School of Engineering Newcastle University Newcastle upon Tyne UK Department of Mechanical Aerospace and Civil Engineering Brunel University London Uxbridge UK

ISBN: (纸本)9781538622230

Eddy current pulsed thermography (ECPT) as one of the emerging NDT&E techniques has been used for the evaluation of the integrity of rail tracks, especially for rolling contact fatigue (RCF) or angular defect detection and quantification. This paper proposed a new feature for angular defect quantification. Specifically, first-order differential of the transient thermal response was first obtained. Then a new feature derived from the first-order differential result was used to quantify the length of the angular slot. R-squared value and 2-norm of the residual were used to evaluate and compare the fitted linear relationship between different extracted features and the angular slot lengths. Through the comparison with other features, the strength and limitation of this new feature were summarized.

关键词： Eddy current pulsed thermography Rolling contact fatigue Angular defect defect quantification

来源：评论

学校读者我要写书评

暂无评论

A tool for pattern information extraction and defect quantification from crystal structures

引用

COMPUTER PHYSICS COMMUNICATIONS 2015年 187卷 266-267页

作者： Okuyan, Erhan Okuyan, Erkan TAI Inc Ankara Turkey Bilkent Univ Comp Engn Dept Ankara Turkey

In this paper, we present a revised version of BilKristal 2.0 tool. We added defect quantification functionality to assess crystalline defects. We improved visualization capabilities by adding transparency support and... 详细信息

关键词： Crystallography Material science Pattern recognition Primitive vectors Basis vectors Space group Symmetry defect quantification

来源：评论

学校读者我要写书评

暂无评论

Carbon-based solid lubricants:An overview

引用

Friction 2025年第1期13卷 101-139页

作者： JoséDaniel Biasoli de Mello Laboratório de Tribologia e Materiais Universidade Federal de UberlândiaUberlândia 38408-100Brazil Laboratório de Materiais Universidade Federal de Santa CatarinaFlorianópolis 88040-900Brazil

Solid lubrication is an excellent option to reduce friction and wear in dry sliding conditions,as well as a secondary source of protection in fluid-lubricated *** the most widely used solid lubricants,carbon-based lubricants are among the most versatile for tribological *** reasons for this include their availability and their innate ability to adopt various *** crystalline ordering of carbon has been identified as the main factor governing its tribological *** work presents and discusses the most significant findings from an ongoing research program aimed at developing carbon-based solid *** this sense,several carbon-based materials with diverse levels of nanostructural order have been studied:three-dimensional(3D)crystalline graphite(GR);novel carbide-derived two-dimensional(2D)turbostratic carbon(CDC)produced from Fe–SiC(GSF)and B4C–Cr3C2(GBC)solid-state reactions;NH3 plasma-functionalized multilayer graphene(MLG);in situ fluorinated diamond-like carbon(DLC)(isfDLC);vertically aligned carbon nanotube(CNT)***,we present a brief description of the processing route for obtaining these materials,followed by their microstructural characterization and a synthesis of the most relevant aspects of tribological *** sliding tests in reciprocating motion were employed with different tribo-pair geometries,specimens and counter-body materials,varied surface topography,and diverse routes to add solid lubricants to the contact(vacuum impregnation of sintered steels,drop-casting,self-lubricating composites and vertically aligned films).The results provide a holistic view of the nature of the tribolayers formed by these ***,a new micro-Raman(µRaman)analysis technique for quantifying the point and line defects of the carbon present in tribolayers is used to correlate the lubrication and degradation mechanism of carbonaceous solid lubricants with their initial nanostructure and testing condit

关键词： carbon nanostructures solid lubrication defect quantification tribolayer micro-Raman(μRaman)spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Multi-scale contrast-to-noise ratio (MS-CNR): a novel metric for quantitative defect characterisation without manual region specification

引用

NONDESTRUCTIVE TESTING AND EVALUATION 2025年

作者： Usamentiaga, R. Sfarra, S. Ibarra-Castanedo, C. Zhang, H. Maldague, X. Univ Oviedo Dept Comp Engn Gijon Spain Univ Laquila Dept Ind & Informat Engn & Econ DIIIE Laquila Italy Laval Univ Comp Vis & Syst Lab CVSL Dept Elect & Comp Engn Quebec City PQ Canada

In numerous research domains where imaging plays a pivotal role in analysing specific objects or processes, it is crucial to quantitatively evaluate the performance of acquisition systems and processing algorithms in differentiating the target from its background. This paper presents the Multi-Scale Contrast-to-Noise Ratio (MS-CNR) metric, a novel tool for precise defect quantification across various imaging modalities. The MS-CNR metric employs the Laplacian of Gaussian (LoG) operator to analyse contrast at multiple scales, allowing for effective quantitative defect characterisation without relying on predefined regions for defects or noise. Through comprehensive evaluation with synthetic and real data, the MS-CNR metric demonstrates a strong correlation with human visual perception and other well-established SNR metrics. It provides consistent and reproducible results, outperforming traditional SNR metrics that may be affected by specific types of noise. The MS-CNR metric's robust performance and alignment with visual assessments make it a valuable addition to imaging analysis, offering a reliable and automated approach for evaluating defect visibility.

关键词： Signal-to-noise ratio (SNR) defect contrast defect quantification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：