检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Yunkai Wei, Shiyin Huang, Yong Su, Yawu Lu, Shanshan Li, Hui Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters Ministry of Industry and Information Technology School of Civil Engineering Harbin Institute of Technology Harbin150090 China Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education Harbin Institute of Technology Harbin150090 China CSCEC Digital Technology Co. Ltd. Beijing100000 China

Existing computer vision(CV)-based structural damage identification models demonstrate notable accuracy in categorizing and localizing damage. However, these models present several critical limitations that hinder their practical application in civil engineering(CE). Primarily, their ability to recognize damage types remains constrained, preventing comprehensive analysis of the highly varied and complex conditions encountered in real-world CE structures. Second, these models lack linguistic capabilities, rendering them unable to articulate structural damage characteristics through natural language descriptions. With the continuous advancement of artificial intelligence(AI), large multi-modal models(LMMs) have emerged as a transformative solution, enabling the unified encoding and alignment of textual and visual data. These models can autonomously generate detailed descriptive narratives of structural damage while demonstrating robust generalization across diverse scenarios and tasks. This study introduces SDIGLM, an innovative LMM for structural damage identification, developed based on the open-source VisualGLM-6B architecture. To address the challenge of adapting LMMs to the intricate and varied operating conditions in CE, this work integrates a U-Net-based semantic segmentation module to generate defect segmentation maps as visual Chain of Thought(CoT). Additionally, a multi-round dialogue fine-tuning dataset is constructed to enhance logical reasoning, complemented by a language CoT formed through prompt engineering. By leveraging this multi-modal CoT, SDIGLM surpasses general-purpose LMMs in structural damage identification, achieving an accuracy of 95.24% across various infrastructure types. Moreover, the model effectively describes damage characteristics such as hole size, crack direction, and corrosion severity. Copyright © 2025, The Authors. All rights reserved.

关键词： Structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Reconstruction and Monitoring of Large-Scale structures via Real-Time Multi-vision System 11th

Three-Dimensional Reconstruction and Monitoring of Large-Sca...

引用

11th International Symposium on Intelligence Computation and Applications, ISICA 2019

作者： Tang, Yunchao Chen, Mingyou Wu, Xiangguo Huang, Kuangyu Wu, Fengyun Zou, Xiangjun He, Yuxin College of Urban and Rural Construction Zhongkai University of Agriculture and Engineering Guangzhou510225 China Key Laboratory of Key Technology on Agricultural Machine and Equipment College of Engineering South China Agricultural University Guangzhou510642 China Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education and School of Civil Engineering Harbin Institute of Technology Harbin150001 China Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology Harbin Institute of Technology Harbin150090 China

ISBN: (纸本)9789811555763

A four-ocular vision system is proposed for the three-dimensional (3D) reconstruction of large-scale concrete-filled steel tube (CFST) materials under complex testing conditions. These measurements are vitally important for evaluating the seismic performance and 3D deformation of large-scale specimens. A four-ocular vision system is constructed to sample the large-scale CFST, then point cloud acquisition, filtering, and stitching algorithms are applied to obtain 3D point cloud of the specimen surface. Novel point cloud correction algorithms based on geometric features and deep learning are proposed to correct the coordinates of the stitched point cloud. The proposed algorithms center on the stitching error of the multi-view point cloud and the geometric and spatial characteristics of the targets for error compensation, which makes them highly adaptive and efficient. A high-accuracy multi-view 3D model for the purposes of real-time complex surface monitoring can be obtained via this method. Performance indicators of the two algorithms were evaluated on actual tasks. The cross-section diameters at specific heights in the reconstructed models were calculated and compared against laser range finder data to test the performance of the proposed method. A visual tracking test on a CFST under cyclic loading shows that the reconstructed output well reflects the complex 3D surface after point cloud correction and meets the requirements for dynamic monitoring. The proposed method is applicable to complex environments featuring dynamic movement, mechanical vibration, and continuously changing features. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Vibrations (mechanical)

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation of shear behavior in precast concrete beams with steel bolted splice connections

引用

structures 2025年 78卷

作者： Khalil Abualtayef Wei Zhou School of Civil Engineering Harbin Institute of Technology Harbin 150090 China Key Lab of Structures Dynamic Behavior and Control Ministry of Education School of Civil Engineering Harbin Institute of Technology Harbin 150090 China Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology School of Civil Engineering Harbin Institute of Technology Harbin 150090 China

Precast concrete structures with bolted connections offer significant advantages, including shorter construction times, improved quality control, and enhanced structural performance. This study investigates the shear behavior of precast concrete beams with steel-bolted splice connections (PCBSBs), which join the discontinuity of two short concrete beam segments, under monotonic loading. Afterwards, the shear performance of PCBSB beams was experimentally and analytically investigated. Six full-scale PCBSB specimens and one control concrete beam were tested to evaluate the effects of key parameters include the shear span ratio and steel plate thickness. The test results show that the failure modes of PCBSB beams are similar to those of reinforcement concrete beams, and the crack propagations can be well controlled by the steel plate thickness. Using a steel bolted connection with a thickness of 3 mm and 5 mm increased the shear crack load by 9 % and 24 %, respectively. After the loading reached 65 % of the peak load, the deflection of steel bolted connection begins to increase more than the shear load deflection till peak load. For beams with long shear span ratio, increase of steel plate thickness led to increase the stiffness, and peak load. Higher a/d ratios increase deflection and shift failure modes from ductile (shear-compression) to brittle (shear-tension). Finally, the experimental shear capacities of the PCBSBs exceeded the predictions of the GB, ACI, EN, and CSA standards for beams with a/d ratios of 1.5 and 2.0. However, discrepancies were observed for beams with a/d of 3.0, where flexural behavior becomes more dominant. Based on these findings, a preliminary design recommendation was proposed. Further studies were recommended to investigate the performance of beams with shorter a/d ratios and varying dimensions to optimize connection efficiency.

关键词： Precast concrete

来源：评论

学校读者我要写书评

暂无评论

Big-data driven building retrofitting: An integrated support vector machines and fuzzy c-means clustering method

Big-data driven building retrofitting: An integrated support...

引用

World Sustainable Built Environment - Beyond 2020, WSBE 2020

作者： Lu, Weizhuo Feng, Kailun Department of Civil Environmental and Natural Resources Engineering Luleå University of Technology Sweden Department of Construction Management Harbin Institute of Technology Harbin150009 China Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education Harbin Institute of Technology Harbin150090 China Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of Ministry of Industry and Information Technology Harbin Institute of Technology Harbin150090 China

It has become a mainstream to use physical models to quantify expected energy savings from alternative retrofit methods and technologies. However, they are not suitable for predicting energy use of buildings when detailed and specified input parameters are unavailable. The overall purpose of the research is to support the stakeholders in taking decisions on refurbishments options when not all of physical information is available, in order to achieve the Swedish Energy Agency's measurements of near-zero energy buildings. The research will transfer big data from Swedish Energy Performance Certificates for building retrofitting. A Support Vector Machines and Fuzzy C-means clustering (SVM-FCM) integrated machine learning algorithm is used directly to extract the case-specific knowledge from EPC big data regarding building characteristics and energy saving of retrofit measures. It enables to prioritize retrofit measures and compute their expected energy savings for buildings. This proposed data driven method is an attempt of taking advantage of big data for practical building retrofit selection. © 2020 Institute of Physics Publishing. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Structural strength deterioration of coastal bridge piers considering non-uniform corrosion in marine environments

引用

Earthquake Engineering and Engineering Vibration 2018年第2期17卷 429-444页

作者： Guo Anxin Yuan Wenting Li Haitao Li Hui Ministry of Education Key Laboratory of Structural Dynamic Behavior and Control School of Civil Engineering Harbin Institute of Technology

In the aggressive marine environment over a long-term service period,coastal bridges inevitably sustain corrosion-induced damage due to high sea salt and *** paper investigates the strength reduction of coastal bridges,especially focusing on the effects of non-uniform corrosion along the height of bridge ***,the corrosion initiation time and the degradation of reinforcement and concrete are analyzed for bridge piers in marine *** investigate the various damage modes of the concrete cover,a discretization method with fiber cells is used for calculating time-dependent interaction diagrams of cross-sections of the bridge piers at the atmospheric zone and the splash and tidal zone under a combination of axial force and bending ***,the shear strength of these aging structures is *** simulation indicates that the strength of a concrete pier experiences dramatic reduction from corrosion initiation to the spalling of the concrete *** loss in the splash and tidal zone is more significant than in the atmospheric zone when structures’service time is assumed to be the same.

关键词： Coastal bridge strength deterioration marine environment non-uniform corrosion interaction diagram

来源：评论

学校读者我要写书评

暂无评论

A new numerical scheme for simulating non-gaussian and non-stationary stochastic processes

arXiv

引用

arXiv 2020年

作者： Zheng, Zhibao Dai, Hongzhe Wang, Yuyin Wang, Wei Key Lab of Structures Dynamic Behavior and Control Harbin Institute of Technology Ministry of Education Harbin150090 China School of Civil Engineering Harbin Institute of Technology Harbin150090 China

This paper presents a new numerical scheme for simulating stochastic processes specified by their marginal distribution functions and covariance functions. Stochastic samples are firstly generated to automatically satisfy target marginal distribution functions. An iterative algorithm is proposed to match the simulated covariance function of stochastic samples to the target covariance function, and only a few times iterations can converge to a required accuracy. Several explicit representations, based on Karhunen-Loève expansion and Polynomial Chaos expansion, are further developed to represent the obtained stochastic samples in series forms. Proposed methods can be applied to non-gaussian and non-stationary stochastic processes, and three examples illustrate their accuracies and efficiencies. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A sample-based stochastic finite element method for structural reliability analysis

arXiv

引用

arXiv 2020年

This paper presents a new methodology for structural reliability analysis via stochastic finite element method (SFEM). A novel sample-based SFEM is firstly used to compute structural stochastic responses of all spatial points at the same time, which decouples the stochastic response into a combination of a series of deterministic responses with random variable coefficients, and solves corresponding stochastic finite element equation through an iterative algorithm. Based on the stochastic response obtained by the SFEM, the limit state function described by the stochastic response and the multidimensional integral encountered in reliability analysis can be computed without any difficulties, and failure probabilities of all spatial points are calculated once time. The proposed method can be applied to high-dimensional stochastic problems, and one of the most challenging issues encountered in high-dimensional reliability analysis, known as Curse of Dimensionality, can be circumvented without expensive computational costs. Three practical ex- Copyright © 2020, The Authors. All rights reserved.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Experimental evaluation of mechanical properties and microstructure for recycled aggregate concrete collaboratively modified with nano-silica and mixed fibers” [Constr. Build. Mater. 403 (2023) 133125]

引用

Construction and Building Materials 2023年 404卷

作者： Hang Sun Liang Luo Huan Yuan Xi Li School of Transportation and Science Engineering Harbin Institute of Technology Harbin 150090 China Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education Harbin Institute of Technology Harbin 150090 China School of Civil Engineering Harbin Institute of Technology Harbin 150090 China

来源：评论

学校读者我要写书评

暂无评论

Machine-learning-based methods for output-only structural modal identification

arXiv

引用

arXiv 2020年

作者： Bao, Yuequan Liu, Dawei Tang, Zhiyi Li, Hui Key Lab of Structures Dynamic Behavior Control of the Ministry of Education Harbin Institute of Technology Harbin150090 China Key Lab of Intelligent Disaster Mitigation Ministry of Industry and Information Technology Harbin Institute of Technology Harbin150090 China

In this study, we propose a machine-learning-based approach to identify the modal parameters of the output-only data for structural health monitoring (SHM) that makes full use of the characteristic of independence of modal responses and the principle of machine learning. By taking advantage of the independence feature of each mode, we use the principle of unsupervised learning, making the training process of the deep neural network become the process of modal separation. A self-coding deep neural network is designed to identify the structural modal parameters from the vibration data of structures. The mixture signals, that is, the structural response data, are used as the input of the neural network. Then we use a complex cost function to restrict the training process of the neural network, making the output of the third layer the modal responses we want, and the weights of the last two layers are mode shapes. The deep neural network is essentially a nonlinear objective function optimization problem. A novel loss function is proposed to constrain the independent feature with consideration of uncorrelation and non-Gaussianity to restrict the designed neural network to obtain the structural modal parameters. A numerical example of a simple structure and an example of actual SHM data from a cable-stayed bridge are presented to illustrate the modal parameter identification ability of the proposed approach. The results show the approach's good capability in blindly extracting modal information from system responses. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring the potential of aramid nanofibers in advancing green-engineered cementitious composites

引用

Composites Part B: Engineering 2025年 305卷

作者： Huayang Sun Yan Wan Zhichao Xu Yanlin Huo Minjie Jia Yingzi Yang School of Civil Engineering Harbin Institute of Technology Harbin 150090 China Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education Harbin Institute of Technology Harbin 150090 China Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology Harbin Institute of Technology Harbin 150090 China School of Transportation Kashi University Kashi 844000 China School of Materials Science and Engineering Jiangsu Key Laboratory of Construction Materials Southeast University Nanjing 211189 China

This study developed an environmentally friendly engineered cementitious composite (ECC) reinforced with aramid nanofibers (ANFs) derived from recycled aramid fibers. ANFs were incorporated into ECC containing high-volume fly ash to improve their strength and ductility. Results showed that adding 0.05 wt % ANFs increased the compressive strength, tensile strength, and tensile strain of ECC by 46.71 %, 46.23 %, and 51.45 %, respectively. The mechanisms through which ANFs enhance the mechanical properties of ECC were investigated through single-fiber pull-out tests, micromechanical analysis, and microstructural analysis. ANFs contributed to filling the pores within the matrix, reducing the matrix porosity and inhibiting crack propagation, which consequently enhanced the compressive properties of ECC. Furthermore, ANFs significantly narrowed the interfacial transition zone (ITZ) at the fiber/matrix interface, thereby improving the frictional bond strength and pull-out energy, ultimately enhancing the tensile ductility of ECC. This study demonstrates the potential of ANFs-reinforced ECC as a sustainable and high-performance material.

关键词：

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：