检索结果-内蒙古大学图书馆

Deep-Learning-Based Bridge Condition Assessment by Probability Density Distribution Reconstruction of Girder Vertical Deflection and Cable Tension Using Unsupervised Image Transformation Model 10th

Deep-Learning-Based Bridge Condition Assessment by Probabili...

引用

10th European Workshop on Structural Health Monitoring, EWSHM 2020

作者： Xu, Yang Tian, Yadi Zhang, Yufeng Li, Hui 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 Key Lab of Structures Dynamics Behavior and Control of the Ministry of Education Harbin Institute of Technology Harbin150090 China School of Civil Engineering Harbin Institute of Technology Harbin150090 China State Key Laboratory of Safety and Health for Inservice Long Span Bridges Nanjing211112 China

ISBN: (纸本)9783030649074

This study proposes a deep-learning-based condition assessment approach by reconstructing marginal probability density distributions of girder vertical deflection (GVD) and cable tension (CT) using unsupervised image transformation (UNIT) model for a real cable-stayed bridge. 27 and 139 sensors of GVD and CT are distributed along the full bridge, and both the sampling frequencies are 2 Hz. First, vehicle-induced components of GVD and CT are extracted by data pre-processing while the temperature-induced components are removed, a time window of 3 h with a sliding length of 10 min is used to obtain original GVD and CT segments, and the corresponding margin probability density distributions (PDFs) are calculated by kernel density estimation. The training and test sets consist of 2986 and 6236 PDFs, respectively. The proposed UNIT model consists of a series of variational autoencoders (VAEs) and generative adversarial networks (GANs). Both the PDFs of GVD and CT are used as inputs. Then, the proposed UNIT model is updated by solving the mini-max problem of training GANs, in which VAEs act as generative models. Finally, the Wasserstein distance between the predicted and ground-truth PDFs of CT acts as the indicator of bridge condition change. Results show that specific modes of PDF variations induced by SHM system upgrade, cable damage, data anomaly, and traffic jam can be recognized to assess bridge condition. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Study and Finite Element Analysis on Impact Resistance of Offshore Wind Turbine Steel Truss Foundation

SSRN

引用

SSRN 2023年

作者： Shi, Chenglong Zhang, Jigang Liu, Feifei Chen, Wenli Zhao, Guoliang Gu, Chi Song, Hanyu School of Civil Engineering Qingdao University of Technology Qingdao266520 China Co-operative Innovation Center of Engineering Construction and Safety in Shandong Blue Economic Zone Qingdao266033 China Key Lab of Structures Dynamic Behavior and Control the Ministry of Education Harbin Institute of Technology Harbin150090 China Qingdao First Municipal Engineering Co. Ltd. Qingdao266000 China China Shanghai Architectural Design &Research Institute Co. Ltd. Shanghai200062 China

In recent years, the global offshore wind turbines(OWTs) have been developing rapidly towards the deep sea. Offshore wind turbines are at risk of ship collisions during their installation and operation. In this paper, the pendulum impact test and finite element simulation analysis are carried out to study the impact load resistance of steel truss foundation of offshore wind turbine in Bohai Sea. The impact resistance of steel truss foundation was analyzed from the parameters of failure modes, impact response and energy dissipation capacity through multiple pendulum impact tests. The results show that after two impacts the stiffness of the impact leg is significantly reduced and even fracture at its foot. The branch tube near the point of impact are squeezed and bent, and the deformation and acceleration peak of the impact position are the largest. The denting of the impact leg is the main energy dissipation mechanism. An energy dissipation coefficient is proposed which can help to predict such a structure’s impact resistance. These data provide an experimental basis for improving the impact resistance of full-scale offshore wind turbine structures. © 2023, The Authors. All rights reserved.

关键词： Energy dissipation

来源：评论

学校读者我要写书评

暂无评论

Progressive collapse mechanism of three-dimensional self-centering precast concrete frame with infill walls and slabs

引用

Engineering Failure Analysis 2025年 179卷

作者： Haoran Wang Shuang Li Feng Lin School of Civil Engineering Shenyang Jianzhu University Shenyang 110168 China Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education 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 Department of Structural Engineering Tongji University Shanghai 200092 China Key Laboratory of Performance Evolution and Control for Engineering Structures of Ministry of Education Shanghai 200092 China

In this study, the effects of infill walls and slabs on the progressive collapse resistance of three-dimension (3D) self-centering precast concrete (PC) frame under corner column failure, middle column failure and internal column failure scenarios were numerically investigated. Based on the verified numerical modeling methods, the failure modes and collapse mechanism of twelve 3D self-centering PC frames were analyzed. The results indicated that the number of spans connected to the failure column will directly influence the progressive collapse resisting-capacity of 3D self-centering PC frames. Compared with slabs, infill walls improved the progressive collapse resistance of 3D self-centering PC frame more obviously. For failure span with small aspect ratio, the presence of infill walls and slabs did not alter the failure mode of the structure. With the aspect ratio of the failure span increased, for 3D self-centering infilled PC frame, the stronger constraint of surrounding frame enhanced the overall stiffness of the infill walls, resulting in a change in the failure mode of the frame. When the slab was arranged, since the larger stiffness of the slabs improved the shear capacity of the beam section, the main concrete damage were still concentrated at the beam ends. A simplified calculation method considering the resistance contribution of structural and non-structural members was proposed to predict the vertical resistance of 3D self-centering PC frame structures under different failure column scenarios in the compressive arch action (CAA) stage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

dynamic shear responses of RC circular columns strengthened with recycled FRPs

引用

structures 2025年 78卷

作者： Yan, Zhi-Wei Song, Yanchen Bai, Yu-Lei Liu, Kun Faculty of Civil Engineering and Mechanics Jiangsu University Zhenjiang212013 China State Key Laboratory of Bridge Engineering Safety and Resilience Beijing University of Technology Beijing100124 China Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education Harbin Institute of Technology Harbin150090 China

Increasingly heavy urban traffic exacerbates vehicle impacts on reinforced concrete (RC) bridge columns, possibly leading to shear failure and structural collapse. To enhance the dynamic shear resistance of these columns, fiber reinforced polymers (FRPs) made from recycled polyethylene terephthalate (PET) plastic bottles were used for external strengthening. PET FRPs offer an eco-friendly alternative by repurposing plastic waste, reducing pollution, and promoting circular economy. This study focused on the dynamic shear responses of RC columns strengthened with PET FRPs. The influences of FRP types and number of FRP layers were experimentally revealed in terms of the failure modes, impact force, reaction force, shear force and impact force-displacement relationship. It was found that significant shear damage occurred in RC columns under horizontal impact loads, with carbon FRPs (CFRPs) strengthening unable to alter the failure mode. Nevertheless, the use of PET FRPs transformed the failure mode to a flexural-shear mode, significantly reducing the impact duration, maximum and residual displacements, and energy dissipation. Moreover, a finite element model was validated to describe the impact resistance of PET FRP-strengthened RC columns, as supported by experimental data. A parametric study further investigated the effects of impact velocity, impact mass, number of FRP layers, and reinforcement ratios on the dynamic shear responses. Based on the truss-arch model, a dynamic shear strength model was proposed and can well predict the dynamic shear capacity of FRP-strengthened RC circular columns. © 2025

关键词： Carbon fiber reinforced plastics

来源：评论

学校读者我要写书评

暂无评论

Functional outlier detection for density-valued data with application to robustify distribution to distribution regression

arXiv

引用

arXiv 2021年

作者： Lei, Xinyi Chen, Zhicheng Li, Hui Key Lab of Intelligent Disaster Mitigation of the Ministry of Industry and Information Technology 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 School of Civil Engineering Harbin Institute of Technology Harbin150090 China

Distributional data analysis, concerned with statistical analysis and modeling for data objects consisting of random probability density functions (PDFs) in the framework of functional data analysis (FDA), has received considerable interest in recent years. However, many important aspects remain unexplored, such as outlier detection and robustness. Existing functional outlier detection methods are mainly used for ordinary functional data and usually perform poorly when applied to PDFs. To fill this gap, this study focuses on PDF-valued outlier detection, as well as its application in robust distributional regression. Similar to ordinary functional data, detecting the shape outlier masked by the "curve net’’ formed by the bulk of the PDFs is the major challenge in PDF-outlier detection. To this end, we propose a tree-structured transformation system for feature extraction as well as converting the shape outliers to easily detectable magnitude outliers, relevant outlier detectors are designed for the specific transformed data. A multiple detection strategy is also proposed to account for detection uncertainties and to combine different detectors to form a more reliable detection tool. Moreover, we propose a distributional-regression-based approach for detecting the abnormal associations of PDF-valued two-tuples. As a specific application, the proposed outlier detection methods are applied to robustify a distribution-to-distribution regression method, and we develop a robust estimator for the regression operator by downweighting the detected outliers. The proposed methods are validated and evaluated by extensive simulation studies or real data applications. Relevant comparative studies demonstrate the superiority of the developed outlier detection method with other competitors in distributional outlier detection. © 2021, CC BY.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

A change-point detection method for detecting and locating the abrupt changes in distributions of damage-sensitive features of SHM data, with application to structural condition assessment

arXiv

引用

arXiv 2021年

作者： Lei, Xinyi Chen, Zhichng Li, Hui Wei, Shiyin Key Lab of Intelligent Disaster Mitigation The Ministry of Industry and Information Technology Harbin Institute of Technology Harbin150090 China Key Lab of Structures Dynamic Behavior and Control The Ministry of Education Harbin Institute of Technology Harbin150090 China School of Civil Engineering Harbin Institute of Technology Harbin150090 China

Diagnosing the changes of structural behaviors using monitoring data is an important objective of structural health monitoring (SHM). The changes in structural behaviors are usually manifested as the feature changes in monitored structural responses;thus, developing effective methods for automatically detecting such changes is of considerable significance. Existing methods for change detection in SHM are mainly used for scalar or vector data, thus incapable of detecting the changes of the features represented by complex data, e.g., the probability density functions (PDFs). Detecting the abrupt changes occurred in the distributions (represented by PDFs) associated with the damage-sensitive features extracted from SHM data are usually of crucial interest for structural condition assessment;however, the SHM community still lacks effective diagnostic tools for detecting such changes. In this study, a change-point detection method is developed in the functional data-analytic framework for PDF-valued sequence, and it is leveraged to diagnose the distributional information break encountered in structural condition assessment. A major challenge in PDF-valued data modeling or analysis is that the PDFs are special functional data subjecting to nonlinear constraints. To tackle this issue, the PDFs are embedded into the Bayes space, and the associated change-point model is constructed by using the linear structure of the Bayes space;then, a hypothesis testing procedure is presented for distributional change-point detection based on the isomorphic mapping between the Bayes space and a functional linear space. Comprehensive simulation studies are conducted to validate the effectiveness of the proposed method as well as demonstrate its superiority over the competing method. Finally, an application to real SHM data illustrates its practical utility in structural condition assessment. Copyright © 2021, The Authors. All rights reserved.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Discovering Governing Equations by Machine Learning implemented with Invariance

arXiv

引用

arXiv 2022年

作者： Chen, Chao Jin, Xiaowei Li, Hui 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 Key Lab of Structures Dynamics Behavior and Control of the Ministry of Education Harbin Institute of Technology Harbin150090 China School of Civil Engineering Harbin Institute of Technology Harbin150090 China

The partial differential equation (PDE) plays a significantly important role in many fields of science and engineering. The conventional case of the derivation of PDE mainly relies on first principles and empirical observation. However, the development of machine learning technology allows us to mine potential control equations from the massive amounts of stored data in a fresh way. Although there has been considerable progress in the data-driven discovery of PDE, the extant literature mostly focuses on the improvements of discovery methods, without substantial breakthroughs in the discovery process itself, including the principles for the construction of candidates and how to incorporate physical priors. In this paper, through rigorous derivation of formulas, novel physically enhanced machining learning discovery methods for control equations: GSNN (Galileo Symbolic Neural Network) and LSNN (Lorentz Symbolic Neural Network) are firstly proposed based on Galileo invariance and Lorentz invariance respectively, setting forth guidelines for building the candidates of discovering equations. The adoption of mandatory embedding of physical constraints is fundamentally different from PINN in the form of the loss function, thus ensuring that the designed Neural Network strictly obeys the physical prior of invariance and enhancing the interpretability of the network. By comparing the results with PDE-NET in numerical experiments of Burgers equation and Sine-Gordon equation, it shows that the method presented in this study has better accuracy, parsimony, and interpretability. © 2022, CC BY.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Sustainable synthesis of hydrophobic waste glass powder for enhanced water and frost resistance in mortar

引用

Construction and Building Materials 2025年 487卷

作者： Wen, Juncheng Wan, Yan Yang, Yingzi 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 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

Most durability issues in cement-based materials stem from water intrusion, which can be mitigated by hydrophobic materials with excellent waterproofing properties. This study proposes a green wet chemical method using stearic acid (SA) and waste glass powder (WGP) to synthesize hydrophobic WGP (HWGP). The effect of SA dosage on the water contact angle of HWGP was investigated, and the optimal SA dosage for preparing HWGP was determined through TG analysis. XRD, FTIR, XPS, and TEM tests revealed the synthesis mechanism of HWGP. The effects of HWGP on mortar's mechanical properties, water and frost resistance were also studied, and the optimal dosage of HWGP for preparing hydrophobic mortar was determined. The results show that 8 % SA is optimal for preparing HWGP, and its water contact angle is 132.2°. The synthesis occurs through reactions between SA and Na+, Ca2+, and Si-OH groups, with the long carbon chains of SA grafted onto WGP, forming a hydrophobic layer about 4 nm thick. As HWGP content increases, compressive strength initially increases and then decreases, while water and frost resistance improve significantly. The optimal dosage for preparing hydrophobic mortar is 15 % HWGP, where compressive strength decreases by only 6.9 %, flexural strength increases by 12.5 %, and water contact angle increases by 91.2°. Additionally, initial and secondary water absorption rates decrease by 79.4 % and 92.2 %, respectively, total water absorption amount over 8d decreases by 64.9 %, and frost resistance improves by 70.9 %. © 2025 Elsevier Ltd

关键词： Bending strength

来源：评论

学校读者我要写书评

暂无评论

Artificial flaw design for engineered cementitious composites via sand coating strategy: Optimization and mechanism

引用

Construction and Building Materials 2025年 489卷

作者： Zhuo Tang Ming Zhang Jing Zhong Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education (Harbin Institute of Technology) Harbin 150090 PR China School of Civil Engineering Harbin Institute of Technology Harbin 150090 PR China China State Construction International Holdings Limited 999077 Hong Kong

The multiple cracking phenomenon of Engineered Cementitious Composites (ECC) is strongly governed by the size and distribution of flaws, which remain challenging to control. Conventional approaches for introducing artificial flaws to induce multiple cracking typically substantially reduce compressive strength. Recently, a strategy was proposed using sands coated with a thin and porous defective coating of polymer nanocomposites to enhance the tensile behaviors of ECC with limited loss of compressive strength. In this study, the ECC performance is further enhanced by controlling the microstructure and interaction with hydrates of the carbon nanotube (CNT) polymer nanocomposite coating and the agglomeration of sands. Relative to the control group, the ductility and compressive strength of the optimized ECC increased by 178 % and 10 %, respectively, with very stable cracking behaviors among all the tested samples. This improvement is mainly because increasing the CNT content in the nanocomposite altered the physicochemical properties and microstructure of coatings, leading to the varied properties of coated sand, which determines the distribution of flaws in the matrix. Interestingly, it was found that the well-separated coated sand ensures high ductility and performance stability of ECC. The formation of diverse sand/matrix interfaces, transitioning from polymer-matrix to CNT-matrix, eventually allows us to overcome the traditional dilemma between ductility and compressive strength.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mechanical properties of an innovative variable stiffness bonded-type anchorage for CFRP cables

Transactions of Materials Research

引用

Transactions of Materials Research 2025年第2期1卷

作者： Yanzhao Niu Makeev Aleksander Chen Wang Rui Guo Guijun Xian Key Lab of Structures Dynamic Behavior and Control (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 Civil Engineering Harbin Institute of Technology Harbin 150090 China

To address the challenges of anchoring Carbon Fiber Reinforced Polymer (CFRP) cables, this paper presents an innovative variable stiffness bonded-type anchorage, which builds upon traditional anchorage designs and incorporates high-temperature resistant bonding media with variable stiffness, along with bent CFRP cables. To evaluate the anchoring performance of this anchorage, mechanical tests were conducted and compared with traditional bond-type anchorage systems. The results show that when the bending angle of CFRP bars exceeds 4°, the tensile strength will be less than 95 % of ultimate strength. As the amount of additive increases, both the tensile strength and elastic modulus of the high-temperature resistant bonding medium gradually improve. The mechanical properties of the high-temperature resistant bonding medium are similar to those of traditional bonding media, but its glass transition temperature ( T g ) is significantly higher than that of traditional bonding media. Additionally, when the bonding layer thickness exceeds 2 mm, it has no effect on the bonding performance. The average bonding stress gradually decreases as the anchorage length increases and the internal cone angle decreases. Furthermore, the Ф4-7 and Ф4-19 CFRP cables anchored by VB anchorage demonstrate ideal brittle failure modes, with anchorage efficiencies exceeding 95 %, and the average slip amounts are 2.78 mm and 5.44 mm, respectively, and the anchorage demonstrates good stability. In contrast, EP anchorage shows less desirable failure modes, with most anchorage efficiencies falling below 95 %. The average slip amounts are 3.22 mm and 7.62 mm, but the results display greater variability.

关键词： CFRP cable Variable stiffness bonding-type anchorage Tensile test High-temperature resin Anchoring performance

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：