Article
Construction & Building Technology
Dang Quang Ngo, Huy Cuong Nguyen, Huu Tai Dinh, Duy Tien Nguyen, Dinh Loc Mai
Summary: This paper investigates the shear behavior of corroded stirrups reinforced concrete beams strengthened with textile reinforced concrete. Experimental results show that the shear strength of corroded specimens decreased by 16.08% to 25.34%, while the shear capacity of corroded beams strengthened with carbon TRC improved by 60.6%.
CASE STUDIES IN CONSTRUCTION MATERIALS
(2022)
Article
Agronomy
Tong Zhou, Yongxin Jiang, Xuenong Wang, Jianhua Xie, Changyun Wang, Qian Shi, Yi Zhang
Summary: An intelligent picking equipment is developed to collect small pieces of film remaining on the field after the film is recycled. The study proposes a method of object detection algorithm (MFFM Faster R-CNN) based on improved Faster R-CNN. The experimental results show that the model can effectively detect surface residual film in complex environments.
Article
Mechanics
Philipp Preinstorfer, Serdar Yanik, Johannes Kirnbauer, Janet M. Lees, Agathe Robisson
Summary: This study investigates the cracking behavior of textile-reinforced concrete (TRC) with epoxy-impregnated textiles. The results show that sand-coating treatment can significantly decrease the transverse crack width, while the geometry of the plain fibre strands leads to differences in measured crack widths. Regardless of the surface treatment, splitting cracks are observed in TRC structures with concrete covers thicker than 15 mm. These findings contribute to a deeper understanding of TRC cracking behavior and provide a comprehensive database for further research, establishing the basis for unified regulations regarding the limit states of TRC structures.
COMPOSITE STRUCTURES
(2023)
Article
Computer Science, Information Systems
Kubra Uyar, Sakir Tasdemir, Erkan Ulker, Mehmet Ozturk, Huseyin Kasap
Summary: This study introduces a novel model for diagnosing brain normality and abnormalities, achieving an accuracy rate of 99.75%. Experimental results demonstrate that the proposed model has shown better performance for detection and classification tasks.
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
(2021)
Article
Construction & Building Technology
Haozheng Tian, Hongxia Qiao, Qiong Feng, Wenwen Han
Summary: This study investigates the corrosion characteristics of reinforced concrete in saline soil areas using electrochemical tests and chloride ion concentration tests. The results show that the deterioration of reinforced concrete increases nonlinearly with time. The corrosion current density and concrete damage degree can be used as effective indices for evaluating deterioration in reinforced concrete.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2023)
Article
Construction & Building Technology
A. De La Rosa, J. J. Ortega, G. Ruiz, J. L. Garcia Calvo, F. J. Rubiano Sanchez, A. Castillo
Summary: This study investigates the use of fatigue loads to activate the self-healing mechanism of concrete, contrary to the conventional belief that cyclic loads only cause damage. The experimental results show that fatigue loads can actually improve the strength of the material. Compression fatigue tests were conducted on fiber-reinforced concrete, and the runout specimens exhibited a mean increase of 23% in strength after enduring more than 165,000 cycles. Microstructure analyses confirmed the presence of new hydration products and a reduction in porosity, which explain the enhanced capacity of the concrete. Additionally, a unique relationship between strain rate and fatigue life was observed for each fatigue stress level.
CEMENT AND CONCRETE RESEARCH
(2023)
Article
Chemistry, Analytical
Xiangyang Xu, Mian Zhao, Peixin Shi, Ruiqi Ren, Xuhui He, Xiaojun Wei, Hao Yang
Summary: The intelligent crack detection method is of great significance for intelligent operation and maintenance as well as traffic safety. This paper investigates the application of deep learning in intelligently detecting road cracks and compares and analyzes Faster R-CNN and Mask R-CNN. The results show that the joint training strategy is effective, but it degrades the effectiveness of the bounding box detected by Mask R-CNN.
Article
Computer Science, Information Systems
Soner Kiziloluk, Eser Sert
Summary: This study proposes an early hurricane detection method called Hurricane-Faster R-CNN-JS, which achieves a higher accuracy compared to other methods by optimizing model parameters.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Yixin Tang, Yu Chen, Sagar A. S. M. Sharifuzzaman, Tie Li
Summary: Animation dramas and movies serve as important sources of entertainment for children and young people, but often contain unsuitable violence. To protect children from viewing violent content, researchers have proposed a deep learning-based system that can detect blood in videos in real-time. By modifying the Faster R-CNN model, this system achieves high accuracy in detecting violence in cartoon and animation images.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Construction & Building Technology
Andressa Cristine Hamilko Giese, Davi Nowicki Giese, Vanessa Fatima Pasa Dutra, Luiz Carlos Pinto Da Silva Filho
Summary: The experimental study on flexural strengthening of reinforced concrete beams showed that all beams experienced an increment in ultimate load and load at serviceability conditions. Different TRM ages and precracking levels affected cracking and yielding loads but not ultimate load significantly. The load-carrying capacity increased as the number of textile layers increased.
JOURNAL OF BUILDING ENGINEERING
(2021)
Article
Construction & Building Technology
Biruk Hailu Tekle, Dennis Messerer, Klaus Holschemacher
Summary: Textile-reinforced concrete is a combination of high-performance concrete and textile reinforcements, with impregnation commonly used to improve mechanical performance. This study experimentally and numerically investigates splitting failure, finding that compaction enhances splitting resistance and vertically cast specimens show higher resistance than horizontally cast ones. The finite element model reveals that the main cause of splitting failure is the varying cross-section of the textile reinforcement and its flat elliptical shape, impacting bond stress distribution.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Biotechnology & Applied Microbiology
Shilin Wu, Yan Wang, Huayu Yang, Pingfeng Wang
Summary: In this study, an improved faster R-CNN network is proposed to address the problems in developing the industrial control SAMA logic diagram. By introducing the ResNet101 network, optimizing the anchor size ratio, and improving the candidate box screening problem, the recognition accuracy of similar elements is greatly enhanced.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Chemistry, Physical
Giorgio Mattarollo, Norbert Randl, Margherita Pauletta
Summary: Recently, innovations in textile-reinforced concrete (TRC) have led to the development of a promising material called fiber/textile-reinforced concrete (F/TRC). However, there is limited experimental research on the performance of TRC and F/TRC using basalt and carbon textile fabrics with high-performance concrete (HPC) matrices. Therefore, an investigation was conducted to study the effects of different variables on the behavior of the materials. The results showed that the failure mode of the specimens was primarily influenced by the type of textile fabric, and the use of carbon fabric resulted in higher post-elastic displacement compared to basalt fabric.
Review
Materials Science, Multidisciplinary
Mahdi Kioumarsi, Armando Benenato, Barbara Ferracuti, Stefania Imperatore
Summary: This paper reviews experimental tests for residual capacity assessment of corroded prestressed reinforced concrete beams and suggests a degradation law for the flexural strength.
Article
Computer Science, Artificial Intelligence
M. Emin Sahin, Hasan Ulutas, Esra Yuce, Mustafa Fatih Erkoc
Summary: The COVID-19 pandemic has had a devastating impact on daily lives and healthcare systems. This study aims to accurately diagnose COVID-19 using deep learning techniques on CT images. The results show that the models have high accuracy rates and can help with automated COVID-19 severity quantification in CT images.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Engineering, Marine
Jinzhao Li, Xuan Kong, Yilin Yang, Lu Deng, Wen Xiong
Summary: This paper presents a numerical investigation on tsunami-induced scour around bridge piers, showing that the scour depth highly depends on the tsunami period and peak velocity. The study demonstrates that a reliable CFD model can accurately predict the scour development and final depth, offering a practical engineering methodology to estimate tsunami-induced pier scour.
Article
Construction & Building Technology
Zhen Chen, Lu Deng, Xuan Kong
Summary: In this study, a modified truncated singular value decomposition (MTSVD) method is proposed for identifying dynamic moving forces on simply-supported beams. The MTSVD method focuses on overcoming ill-posed problems in force identification by regularizing the truncated singular value decomposition (TSVD) method, with regularization matrix and truncating point being the most important parameters. Comparison results with conventional SVD and TSVD methods demonstrate the improved performance of MTSVD in high noise level cases, as well as compared to the piecewise polynomial truncated singular value decomposition (PP-TSVD) method.
ADVANCES IN STRUCTURAL ENGINEERING
(2022)
Article
Engineering, Civil
Xuan Kong, Kui Luo, Wei Ji, Quanyu Tang, Lu Deng
Summary: This study investigates the dynamic characteristics of an improved composite box girder with corrugated steel webs (ICBGCSWs) through theoretical analysis and verification. The proposed method accurately calculates the natural frequencies and mode shapes of vertical bending vibration, considering the effects of shear lag and shear deformation. A general formula for calculating the fundamental frequency of different types of girders is also proposed.
JOURNAL OF BRIDGE ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Xuan Kong, Tengyi Wang, Jie Zhang, Lu Deng, Jiwei Zhong, Yuping Cui, Shudong Xia
Summary: Overloaded vehicles cause various negative effects on infrastructure and human safety. Researchers have developed a computer vision-based method for identifying vehicle weight, which accurately determines the tire-road contact force using tire images. This method offers advantages such as high accuracy, low cost, and easy operation.
APPLIED SCIENCES-BASEL
(2022)
Article
Construction & Building Technology
Chao Xiang, Wei Wang, Lu Deng, Peng Shi, Xuan Kong
Summary: This paper proposes an automatic microcrack detection method based on super-resolution reconstruction and semantic segmentation. By using deep learning for super-resolution reconstruction and semantic segmentation, the accuracy of crack detection and feature quantification is significantly improved.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Computer Science, Interdisciplinary Applications
Honghu Chu, Wei Wang, Lu Deng
Summary: This study proposes a multiscale feature fusion network named Tiny-Crack-Net (TCN) to address the class imbalance and limited local receptive field issues in crack segmentation. By modifying the residual network, incorporating dual attention modules, and implementing multiscale fusion operations, the network's ability to segment tiny cracks is significantly enhanced. Evaluation on an open-source dataset and field test results validate the effectiveness and robustness of Tiny-Crack-Net.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Construction & Building Technology
Hong-Hu Chu, Sattam Fahad Almojil, Abdulaziz Ibrahim Almohana, Abdulrhman Fahmi Alali, Ali E. Anqi, Ali A. Rajhi, Sagr Alamri
Summary: China, being one of the largest energy consumers worldwide, utilizes paraffin-based phase change materials to reduce energy demand associated with air conditioning. The addition of C18 paraffin has shown significant effects in reducing energy consumption for temperature regulation.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Engineering, Marine
Jinzhao Li, Xuan Kong, Yilin Yang, Zhiwen Yang, Jiexuan Hu
Summary: In this study, a non-contact computer vision (CV)-based method is proposed to conveniently acquire wave pressure and force without the need for pressure sensors or load cells. The method uses optical flow technique to measure velocity field and solves the Poisson pressure equation to compute pressure field. The wave force is determined by integrating pressure over the structure surface. The method is verified through laboratory experiments and shows good agreement with results from pressure sensors.
Article
Chemistry, Multidisciplinary
Xuan Kong, Jinxin Yi, Xiuyan Wang, Kui Luo, Jiexuan Hu
Summary: This study proposes a computer vision-based method for full-field mode shape identification, which uses subpixel edge detection and tracking techniques. By identifying and tracking the movement of the structure's edge, high-resolution full-field mode shapes can be determined without a preset target.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Marine
Jinzhao Li, Xuan Kong, Yilin Yang, Jiexuan Hu, Ruijia Jin
Summary: This paper presents a numerical study of the solitary wave-induced flow and scour around a square onshore structure. The results show that the simulated scour depth develops faster at the early stage compared to the experimental result. The scour starts at the front corner of the structure and develops rapidly, almost completed in the first half of the wave period.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Honghu Chu, Lizhi Long, Jingjing Guo, Huaqing Yuan, Lu Deng
Summary: High-resolution crack images provide detailed information for assessing structural condition and formulating effective maintenance or rehabilitation plans. However, the segmentation of HR crack images has been challenging due to limitations of mainstream deep learning algorithms and computing resources. To address this issue, a novel architecture called CCRN, using continuous representation, was proposed for meticulous segmentation of cracks from HR images.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2023)
Article
Construction & Building Technology
Hong -Hu Chu, Abdulaziz Ibrahim Almohana, Ghassan A. QasMarrogy, Sattam Fahad Almojil, Abdulrhman Fahmi Alali, Khaled Twfiq Almoalimi, Amir Raise
Summary: The increase in traffic and changes in weather conditions have led to many distresses in the pavement. Asphalt binder modification is the best way to control these stresses. Meanwhile, utilizing warm mix asphalt additives has significant environmental benefits. This research investigates the influence of using waste materials (ground tire rubber and natural bitumen) on the performance behavior of asphalt binders and mixtures containing warm mix asphalt additive. The results show that the combination of waste materials improves the fatigue and rutting performance, and adding waste natural bitumen decreases the low-temperature behavior of the asphalt binder while adding waste ground tire rubber improves the resistance against low-temperature cracking.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Engineering, Multidisciplinary
Jie Zhang, Xuan Kong, Eugene J. OBrien, Jiaqiang Peng, Lu Deng
Summary: This study proposes a noncontact measurement method of tire deformation based on computer vision and deep learning techniques. A diverse dataset of tire images is established and a semantic segmentation Tire-Net is developed to segment the tire images. The proposed quantification algorithm calculates the physical value of tire deformation using subpixel-level edge detection, key point positioning, and scale factor determination. Field tests on various vehicles verify the effectiveness of the proposed method.
Article
Engineering, Mechanical
Kui Luo, Xuan Kong, Xiuyan Wang, Tengjiao Jiang, Gunnstein T. Froseth, Anders Ronnquist
Summary: This study proposes a method based on broad-band phase-based video motion magnification and line tracking algorithms for measuring small-amplitude vibration of cables, which improves the measurement accuracy.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Information Systems
Hong -Hu Chu, Muhammad Rizwan Saeed, Javed Rashid, Muhammad Tahir Mehmood, Israr Ahmad, Rao Sohail Iqbal, Ghulam Ali
Summary: This study proposes a decision support system (DSS) for an autonomous road information system using deep learning to detect road cracks and potholes. The DSS captures road images, attaches coordinates with GPS, and passes the information to the decision layer for crack and pothole detection. The results show that the proposed system achieves higher precision, recall, and accuracy compared to existing models.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)