检索结果-内蒙古大学图书馆

4th International Conference on Emerging Smart Technologies and Applications (eSmarTA)

作者： Hussain, Adil Qureshi, Kashif Naseer Zaman, Faizan Aslam, Ayesha Tariq Changan Univ Sch Elect & Control Engn Xian Peoples R China Univ Limerick Dept Elect & Comp Engn Limerick Ireland

ISBN: (纸本)9798350354140;9798350354133

The manual detection of road cracks is a timeconsuming process. On the other hand, solutions that are based on deep learning are both speedy and accurate. Recently, several different Convolutional Neural Networks (CNN) based on deep learning have been proposed. However, the performance of the CNN models has varied. The major challenge is the computational resources required to train a pretrained CNN model;however, a lightweight CNN is more suitable for better training efficiency. In this study work, the SCD11 CNN model is implemented and compared with the pretrained CNN models, including Inception V2, VGG19, and Xception CNN. The models are trained and tested using the public dataset i.e., the Surface cracks Dataset. The dataset is divided into training, validation and test sets. The SCD11 CNN along with the pre-trained CNN models are trained and validated and then tested using the splitting of the public dataset. Furthermore, the model's performance evaluation is performed by using a private dataset. The results show that the SCD11 CNN performs better than the pre-trained CNN models for both the public and private datasets.

关键词： Road cracks SCD11 CNN Deep Learning cracks detection Minor cracks.

来源：评论

学校读者我要写书评

暂无评论

The development of multiplexing capability for reflective matched fiber bragg gratings interrogation technique and its application in real-time micro cracks detection

引用

PHYSICA SCRIPTA 2024年第9期99卷 095524-095524页

作者： Khan, Raja Yasir Mehmood Ullah, Rahim Faisal, Muhammad Pakistan Inst Engn & Appl Sci Natl Inst Lasers & Optron Coll Islamabad 45650 Pakistan

cracks detection in engineering structures is pivotal for ensuring structural reliability and preventing catastrophic failures. In this article we developed multiplexing capability of reflective matched fiber Bragg Gratings (RM-FBGs) interrogation technique and utilized it for crack detection in an assembly aluminum plates. Firstly, the proposed multiplexing capability is analyzed by applying axial strain on an array of five FBGs pasted on five separate aluminum assemblies. The strain in any FBG due to localized micro-crack resulted in variation its output itself by ascertaining no effect in the outputs of other FBGs, certifying the multiplexing capability of RM-FBGs scheme. The developed RM-FBGs scheme is practically applied micro-cracks detection in a V-shape crack produced in assembly of aluminum plates. The crack is monitored by an array of three multiplexed FBGs epoxied to the plate's junction at three different positions P1, P2 and P3. Where P1 is at beginning, P2 is at middle and P3 is at end of the crack. Sensitivities of the FBGs at points P1, P2 and P3 were found to be 0.09 +/- 0.0001 V mu m-1, 0.10 +/- 0.007 V mu m-1 and 1.08 +/- 0.09 V mu m-1, respectively and resolutions were found to be 0.22 mu m, 0.20 mu m and 0.02 mu m, respectively. Variation in gauge length of the optical fiber from 100 mm to 200 mm resulted in 76.36% increase in crack width sensing range but at the cost of compromise in sensitivity and resolution. The proposed multiplexed RM-FBG can be deployed for early micro-cracks detection in metallic and non-metallic structures with sub-micrometers resolution.

关键词： RM-FBGs multiplexing cracks detection resolution gauge length temperature compensation

来源：评论

学校读者我要写书评

暂无评论

Research on cracks Image detection System for Subway Tunnel 4

Research on Cracks Image Detection System for Subway Tunnel

引用

IEEE 4th Information Technology and Mechatronics Engineering Conference (ITOEC)

作者： Liu, Xuanran Wang, Yaodong Yu, Zujun Zhu, Liqiang Shi, Hongmei Huang, Haitao Beijing Jiaotong Univ Sch Mech Elect & Control Engn Beijing Peoples R China Minist Educ Key Lab Vehicle Adv Mfg Measuring & Control Techn Beijing Peoples R China Beijing Res Inst Precise Mechatron & Controls Beijing Peoples R China

ISBN: (纸本)9781538653739

The detection of cracks which is one of the main diseases of the tunnel lining plays an important role in the tunnel safety. In order to improve the efficiency and accuracy of crack detection, this paper proposes an improved crack detection algorithm and an interface program for interaction. An image acquisition scheme based on a linear array camera system is proposed, and the system can be mounted on a track vehicle for image capturing. Experiments show that for the same image, the detection speed of improved algorithm is twenty times faster than the speed on MATLAB platform. In addition, this paper presents the design of three-dimensional display software for subway tunnel based on OpenGL, which is used to locate the position and predict the tendency of tunnel diseases.

关键词： cracks detection image acquisition image processing three-dimensional display

来源：评论

学校读者我要写书评

暂无评论

Automatic image cracks detection and removal on mobile devices

Automatic image cracks detection and removal on mobile devic...

引用

Conference on Mobile Multimedia/Image Processing, Security, and Applications

作者： Voronin, V. Marchuk, V. Sizyakin, R. Gapon, N. Pismenskova, M. Tokareva, S. Don State Tech Univ Dept Radioelect Syst Rostov Na Donu Russia

ISBN: (纸本)9781510601109

Some of old photographs are damaged due to improper archiving (e.g. affected by direct sunlight, humidity, insects, etc.) or have a physical damage resulting on appearance of cracks, scratches on photographs, non-necessary signs, spots, dust, and so on. This paper focuses on detection and removal of cracks from digital images. The proposed method consists of the following steps: pre-processing, crack detection and image reconstruction. A pre-processing step is used to suppress a noise and small defects in images. For a crack identification we use modified local binary patterns to form a feature vectors, and a non-linear SVM for a crack recognition. The combined inpainting method using structure and texture restoration is applied at the image reconstruction step. Image inpainting is the process of restoring the lost or damaged regions or modifying the image contents imperceptibly. This technique detects and removes the horizontal, vertical, diagonal cracks and other defects on complex scenes of image. We implemented proposed method on some mobile platforms for automatic image enhancement. Presented examples demonstrate the effectiveness of the algorithm in cracks detection and removal.

关键词： cracks detection texture descriptors LBP support vector machine inpainting

来源：评论

学校读者我要写书评

暂无评论

Online crack detection on photovoltaic devices using a dynamic response analysis

引用

RENEWABLE ENERGY 2025年 248卷

作者： Cardenas-Bravo, Carlos Cortes-Severino, Rodrigo Morales, Felipe Barraza, Rodrigo Sanchez-Squella, Antonio Valdivia-Lefort, Patricio Univ Tecn Feder Santa Maria Dept Elect Engn Valparaiso 8320000 Chile Univ Adolfo Ibanez Fac Engn & Sci Ctr Energy Transit Santiago 7941169 Chile Univ Santiago Dept Elect Engn Santiago 9170022 Chile

This study presents a method to detect cracks in solar photovoltaic modules by analyzing their dynamic electrical response without interrupting operation. The approach evaluates indicators like settling time and damping coefficient using dynamic current and voltage measurements. Baseline assessments rely on electroluminescence imaging and I-V curve analysis. A DC/DC converter generates transient responses, and outdoor tests under stable irradiance confirm the method's reliability, achieving a correlation coefficient above 0.89. Results show that cracks affect the damping coefficient in both current and voltage. Cracked modules exhibit a damping coefficient notably different from healthy ones. A linear dynamic electrical model supports this, showing healthy modules have a more oscillatory response. This method enables real-time, non-intrusive fault detection in PV modules, offering a practical solution for continuous health monitoring in solar energy systems. Its effectiveness across varying temperatures and irradiance suggests broad applicability in real-world conditions. Future research should address nonlinear aspects of the transient response, extend testing to diverse conditions, and integrate this method with current diagnostic techniques to improve accuracy. Additionally, incorporating advanced signal processing and machine learning could further enhance its ability to identify faults.

关键词： Photovoltaic Fault detection cracks detection Dynamic PV response Solar photovoltaic Reliable operation Maintenance

来源：评论

学校读者我要写书评

暂无评论

Assessment of Convolutional Neural Network Pre-Trained Models for detection and Orientation of cracks

引用

MATERIALS 2023年第2期16卷 826页

作者： Qayyum, Waqas Ehtisham, Rana Bahrami, Alireza Camp, Charles Mir, Junaid Ahmad, Afaq Univ Engn & Technol Dept Civil Engn Rawalpindi 46600 Pakistan Univ Gavle Fac Engn & Sustainable Dev Dept Bldg Engn Energy Syst & Sustainabil Sci S-80176 Gavle Sweden Univ Memphis Dept Civil Engn Memphis TN 38152 USA Univ Engn & Technol Dept Elect Engn Rawalpindi 46600 Pakistan

Failure due to cracks is a major structural safety issue for engineering constructions. Human examination is the most common method for detecting crack failure, although it is subjective and time-consuming. Inspection of civil engineering structures must include crack detection and categorization as a key component of the process. Images can automatically be classified using convolutional neural networks (CNNs), a subtype of deep learning (DL). For image categorization, a variety of pre-trained CNN architectures are available. This study assesses seven pre-trained neural networks, including GoogLeNet, MobileNet-V2, Inception-V3, ResNet18, ResNet50, ResNet101, and ShuffleNet, for crack detection and categorization. Images are classified as diagonal crack (DC), horizontal crack (HC), uncracked (UC), and vertical crack (VC). Each architecture is trained with 32,000 images equally divided among each class. A total of 100 images from each category are used to test the trained models, and the results are compared. Inception-V3 outperforms all the other models with accuracies of 96%, 94%, 92%, and 96% for DC, HC, UC, and VC classifications, respectively. ResNet101 has the longest training time at 171 min, while ResNet18 has the lowest at 32 min. This research allows the best CNN architecture for automatic detection and orientation of cracks to be selected, based on the accuracy and time taken for the training of the model.

关键词： convolutional neural networks orientation of cracks cracks detection deep learning pre-trained models

来源：评论

学校读者我要写书评

暂无评论

A survey on crack detection in concrete surface using image processing and machine learning

引用

Journal of Building Pathology and Rehabilitation 2024年第1期9卷 1-25页

作者： Kirthiga, R. Elavenil, S. School of Civil Engineering Vellore Institute of Technology Chennai Campus Chennai 600127 India

Crack is the earliest indication of structural deterioration. It is necessary to examine the structural elements as cracks can affect the durability and safety of civil infrastructures. Visual inspection of cracks is laborious and time-consuming, rendering the technique unsuitable for inspection of numerous structural elements. Therefore, it is essential to develop highly reliable and efficient automatic crack identification techniques. Image processing methods are employed to review the captured pictures of the structural elements and to determine every possible defect. In addition to image processing, techniques based on machine learning are often used in crack detection to ensure results with better accuracy and predictability. This review presents an overview of the different image processing and machine learning techniques used to detect cracks on concrete surfaces. This study provides evidence for the application of machine learning methods for autonomous crack inspections and the advancement of these methods in the discipline of civil engineering. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Crack cracks detection Image processing Machine learning Visual inspection

来源：评论

学校读者我要写书评

暂无评论

An Investigation Into the Advancements of Edge-AI Capabilities for Structural Health Monitoring

引用

IEEE ACCESS 2024年 12卷 25325-25345页

作者： Mishra, Anoop Gangisetti, Gopinath Khazanchi, Deepak Univ Nebraska Coll Informat Sci & Technol Omaha NE 68182 USA

The aim of this study is to investigate the capabilities of edge-AI in the field of structural health monitoring, with a particular emphasis on detecting cracks in concrete bridges. Comprehensive literature suggests that edge-AI approaches have not been utilized in the structural health monitoring domain (SHM). This article proposed two novel frameworks: an edge-AI framework for the SHM domain and a cloud-edge adaptive intelligence for crack detection (CEAIC) to utilize edge-AI approaches for real-time scenarios. The framework incorporates a novel edge-AI framework, the crowd intelligence approach, and the CrANET framework to perform weakly supervised crack segmentation. Quantization approaches are used to transform the deep learning model into an optimized model to be compatible with edge devices. The edge-AI experiments for the cracks detection task are conducted using Kneron KL520 and Google Coral development board. A responsive website has been developed to demonstrate the real-world implications of the CEAIC framework. This study has the potential to provide a cost-effective and reliable solution for real-time monitoring and assessment of concrete bridge cracks, thereby improving the safety and longevity of bridges. The outcomes of this research endeavor will furnish us with invaluable insights regarding the feasibility and potential advantages of incorporating edge AI into the SHM domain.

关键词： Image edge detection Bridges Monitoring Cloud computing Task analysis Computational modeling Real-time systems Edge computing Artificial intelligence Neural networks Quantization (signal) Structural engineering detection algorithms Surface cracks cracks detection edge-AI neural networks quantization structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

A novel SCD11 CNN model Performance Evaluation with Inception V3, VGG16 and ResNet50 using Surface Crack Dataset 2

A novel SCD11 CNN model Performance Evaluation with Inceptio...

引用

2nd International Conference on Unmanned Vehicle Systems (UVS-Oman)

作者： Hussain, Adil Qureshi, Kashif Naseer Anwar, Raja Waseem Aslam, Ayesha Changan Univ Sch Elect & Control Engn Xian Peoples R China Univ Limerick Dept Comp Engn & Elect Limerick Ireland German Univ Technol Oman Dep Comp Sci POB 1816 Muscat 130 Oman Changan Univ Sch Informat Engn Line 4 Xian Peoples R China

ISBN: (纸本)9798350372557

Image processing techniques can be used to detect potential defects in images of infrastructure elements that have been collected or scanned. Aside from image processing, machine learning technologies are increasingly being applied to increase crack detection performance and resilience. A novel Surface Crack detection Convolutional Neural Network (CNN) named the SCD11 CNN model is proposed. The main aim of this research paper is to improve efficiency and minimize the loss rate. The proposed CNN model is compared with the CNNs, including Inception V3, VGG16, and ResNet50, using a Surface cracks Dataset. The accuracy and loss of the proposed model are compared. The results show that the proposed SCD11 CNN model performs better in test accuracy than Inception V3 and VGG16 and has a slightly lower accuracy than ResNet50.

关键词： road cracks cracks detection neural networks

来源：评论

学校读者我要写书评

暂无评论

Extraction and measurement of recessive and conventional cracks in underground engineering concrete structures

引用

JOURNAL OF BUILDING ENGINEERING 2024年 94卷

作者： Tang, Wenchong Tang, Liang Kong, Xiangxun Ling, Xianzhang Rong, Zhongdi Zhang, Yifan Yao, Changrui Harbin Inst Technol Sch Civil Engn Harbin 150090 Peoples R China Chongqing Res Inst Harbin Inst Technol Chongqing 401135 Peoples R China Heilongjiang Res Ctr Rail Transit Engn Cold Reg Harbin 150090 Peoples R China

Crack damage is a crucial aspect of monitoring the health of concrete structures. This study introduces the concept of recessive cracks and proposes novel methods for their visualization. These methods enable the early detection and potential prevention of damage in underground concrete structures before cracks fully develop. Parameters such as infiltration time, evaporation rate, infiltration shadow width, and damage depth were measured during the visualization of recessive cracks, thereby achieving the primary objective of assessing the extent of damage caused by these cracks. Additionally, a novel algorithm, the "Similarity -Difference Algorithm, " was developed to track the development and evolution of recessive cracks at different stress stages. Furthermore, this study addresses the extraction, segmentation, and measurement of conventional cracks with spiderweb-like interlacing. Finally, outdoor experiments were conducted to validate the reliability and suitability of the proposed method for real -world applications.

关键词： cracks detection Deep learning Semantic segmentation Metro tunnel Image analysis

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：