检索结果-南通市图书馆

Predicting torsional capacity of reinforced concrete members by data-driven machine learning models

Frontiers of Structural and Civil engineering 2024年第3期18卷 444-460页

作者： Shenggang CHeN Congcong CHeN Shengyuan li junying guo Quanquan guo Chaolai li School of Mechanics and Civil engineering China University of Mining and TechnologyXuzhou 211116China jiangsu Key Laboratory environmental Impact and Structural Safety in engineering China University of Mining and TechnologyXuzhou 211116China China Nuclear Power Design Co.Ltd. Shenzhen 518031China School of transportation and science engineering Beihang UniversityBeijing 100191China China Construction First Group Corporation limited Beijing 100161China

Due to the complicated three-dimensional behaviors and testing limitations of reinforced concrete(RC)members in torsion,torsional mechanism exploration and torsional performance prediction have always been *** the present paper,several machine learning models were applied to predict the torsional capacity of RC *** results of a total of 287 torsional specimens were collected through an overall literature *** of extreme gradient boosting machine(XGBM),random forest regression,back propagation artificial neural network and support vector machine,were trained and tested by 10-fold cross-validation *** performances of proposed machine learning models were evaluated and compared,both with each other and with the calculated results of existing design codes,i.e.,GB 50010,ACI 318-19,and eurocode *** results demonstrated that better predictive performance was achieved by machine learning models,whereas GB 50010 slightly overestimated the torsional capacity,and ACI 318-19 and eurocode 2 underestimated it,especially in the case of ACI *** XGBM model gave the most favorable predictions with R^(2)=0.999,RMSe=1.386,MAe=0.86,andλ=***,strength of concrete was the most sensitive input parameters affecting the reliability of the predictive model,followed by transverse-to-longitudinal reinforcement ratio and total reinforcement ratio.

关键词： RC members torsional capacity machine learning models design codes

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

GMAT:A Graph Modeling Method for Group Preference Prediction

引用

journal of Systems Science and Systems engineering 2024年第4期33卷 475-493页

作者： Xiangyu li Xunhua guo guoqing Chen International Business School Jinan UniversityZhuhai519070China School of economics and Management Tsinghua UniversityBeijing100084China

Preference prediction is the building block of personalized services,and its implementation at the group level helps enterprises identify their target customers *** methods for preference prediction mainly focus on behavioral interactions to extract the associations between groups and products,ignoring the importance of other auxiliary records(e.g.,online reviews and social tags)in association *** paper proposes a novel method named GMAT for group preference prediction,aiming to collectively detect the sophisticated association patterns from user generated content(UGC)and behavioral *** doing so,we construct a tripartite graph to collaborate these two types of data,and design a deep-learning algorithm with mutual attention module for generating the contextualized representations of groups and *** experiments on two real-world datasets show that GMAT is superior to other baselines in terms of group preference ***,GMAT is able to improve prediction accuracy compared with its different variants,further verifying the proposed method’s effectiveness on association pattern detection.

关键词： Group preference UGC tripartite graph deep learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Corrosion behavior of Gd_(2)Zr_(2)O_(7)thermal barrier coatings under Fe-containing environmental sediment attack

引用

journal of Advanced Ceramics 2024年第4期13卷 447-462页

作者： Lei guo Yanyan li Kai Yan School of Materials Science and engineering Tianjin UniversityTianjin 300072China Tianjin Key Laboratory of Advanced joining Technology Key Lab of Advanced Ceramics and Machining Technology of Ministry of EducationTianjin 300072China Key Laboratory of Special equipment Safety and energy-saving for State Market Regulation China Special Equipment Inspection&Research InstituteBeijing 100029China

environmental sediments mainly consisting of CaO–MgO–Al_(2)O_(3)–SiO_(2)(CMAS)corrosion are a serious threat to thermal barrier coatings(TBCs),in which Fe element is usually ***_(2)Zr_(2)O_(7)TBCs are famous for their excellent CMAS *** this study,the characteristics of Fe-containing environmental sediments(CMAS-Fe)and their corrosiveness to Gd_(2)Zr_(2)O_(7)coatings were *** types of CMAS-Fe glass with different Fe contents were *** melting points were measured to be 1322–1344℃,and the high-temperature viscosity showed a decreasing trend with increasing Fe *** corrosion behavior of four types of CMAS-Fe to Gd_(2)Zr_(2)O_(7)coatings at 1350℃was *** the initial corrosion stage(0.1 h),anorthite was precipitated in CMAS-Fe with a high Ca:Si ratio,while Fe-garnet was formed in the melt with the highest Fe *** the corrosion time resulted in the formation of a reaction layer,which exhibited an interpenetrating network composed of Gd-oxyapatite,ZrO_(2),and residual *** spinel was precipitated within the reaction *** 1 h or even longer time,the reaction layers tended to be stable and compact,which had comparable hardness and fracture toughness to those of Gd_(2)Zr_(2)O_(7)*** the cyclic CMAS-Fe attack,the residual CMAS-Fe in the interpenetrating network provided a pathway for the redeposited CMAS-Fe infiltration,resulting in the continuous growth of the reaction *** a result,the Gd_(2)Zr_(2)O_(7)coatings had a large consumption in the thickness,degrading the coating ***,the Gd_(2)Zr_(2)O_(7)coatings exhibit unsatisfactory corrosion resistance to CMAS-Fe attack.

关键词： thermal barrier coatings(TBCs) Gd_(2)Zr_(2)O_(7) Fe-containing CaO-MgO-Al2O3-SiO_(2)(CMAS) corrosion resistance reaction layer

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Deformation and stability of the seawall,considering the strength uncertainty of cement mixing piles

引用

journal of Zhejiang University-Science A(Applied Physics & engineering) 2024年第6期25卷 483-501页

作者： Yuansheng YU lingling li Xiangmiao KONG Chengyuan li Zhen guo Key Laboratory of Offshore Geotechnics and Material of Zhejiang Province College of Civil Engineering and ArchitectureZhejiang UniversityHangzhou310058China Hainan Institute Zhejiang UniversitySanya572000China Ninghai Highway and Transportation Management Center Ningbo315600China Ninghai Traffic engineering Construction Management Institute Ningbo315600China

The cement mixing (CM) pile is a common method of improving soft offshore ground. The strength growth of CM piles under complex conditions is affected by many factors, especially the cement and moisture contents, and shows significant uncertainty. To investigate the stochasticity of the early strength of CM piles and its impact on the displacement and stability of a seawall, a series of laboratory tests and numerical analyses were carried out in this study. Vane shear tests were conducted on the cement-solidified soil to determine the relationships between the undrained shear strength s_(u) of the cement soil curing in the seawater and the cement content a_(c), as well as the in situ soil moisture content w. It can be inferred that the 24 h undrained shear strength follows a normal distribution. A numerical model considering the random CM pile strength was established to investigate the deformation of the seawall. Due to the uncertainty of CM pile strength, the displacement of the seawall demonstrates a certain discreteness. The decrease of the mean undrained shear strength of CM piles causes a corresponding increase in the average displacement of the seawall. When the mean strength of CM piles is lower than a certain threshold, there is a risk of instability. Furthermore, the heterogeneity of the strength within an individual CM pile also has an impact on seawall displacement. Attention should be paid to the uncertainty of CM pile strength to control displacement and stability.

关键词： Construction uncertainty Cement mixing(CM)pile Strength of cement soil Seawall stability Random finite element method(RFeM) Monte Carlo simulation(MCS)

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Alignment efficient image-sentence retrieval considering transferable cross-modal representation learning

引用

Frontiers of Computer Science 2024年第1期18卷 77-91页

作者： Yang YANG jinyi guo Guangyu li Lanyu li Wenj.e li jian YANG School of Computer Science and engineering Nanjing University of Science and TechnologyNanjing 210094China Department of Computing Hong Kong Polytechnic UniversityHong Kong 100872China State Key Lab.for Novel Software Technology Nanjing UniversityNanjing 210094China 14th Research Institute of China electronics Technology Group Corporation Nanjing 210094China guangyu.li2017@***

Traditional image-sentence cross-modal retrieval methods usually aim to learn consistent representations of heterogeneous modalities,thereby to search similar instances in one modality according to the query from another modality in *** basic assumption behind these methods is that parallel multi-modal data(i.e.,different modalities of the same example are aligned)can be obtained in *** other words,the image-sentence cross-modal retrieval task is a supervised task with the alignments as ***,in many real-world applications,it is difficult to realign a large amount of parallel data for new scenarios due to the substantial labor costs,leading the non-parallel multi-modal data and existing methods cannot be used *** the other hand,there actually exists auxiliary parallel multi-modal data with similar semantics,which can assist the non-parallel data to learn the consistent ***,in this paper,we aim at“Alignment efficient Image-Sentence Retrieval”(AeIR),which recurs to the auxiliary parallel image-sentence data as the source domain data,and takes the non-parallel data as the target domain *** single-modal transfer learning,AeIR learns consistent image-sentence cross-modal representations of target domain by transferring the alignments of existing parallel ***,AeIR learns the image-sentence consistent representations in source domain with parallel data,while transferring the alignment knowledge across domains by jointly optimizing a novel designed cross-domain cross-modal metric learning based constraint with intra-modal domain adversarial ***,we can effectively learn the consistent representations for target domain considering both the structure and semantic ***,extensive experiments on different transfer scenarios validate that AeIR can achieve better retrieval results comparing with the baselines.

关键词： image-sentence retrieval transfer learning semantic transfer structure transfer

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fullerenes and derivatives as electrocatalysts: Promises and challenges

引用

Green energy & environment 2024年第1期9卷 7-27页

作者： Kun guo Ning li lipiao Bao Xing Lu State Key Laboratory of Materials Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhan430074China

Carbon-based metal-free nanomaterials are promising alternatives to precious metals as electrocatalysts of key energy storage and conversion *** paramount signiﬁcance are the establishment of design principles by understanding the catalytic mechanisms and identifying the active *** from sp2-conjugated graphene and carbon nanotube,fullerene possesses unique characteristics that are growingly being discovered and exploited by the electrocatalysis *** instance,the well-deﬁned atomic and molecular structures,the good electron afﬁnity to tune the electronic structures of other substances,the intermolecular self-assembly into superlattices,and the on-demand chemical modiﬁcation have endowed fullerene with incomparable advantages as electrocatalysts that are otherwise not applicable to other carbon *** increasing studies are being reported on this intriguing topic,it is necessary to provide a state-of-the-art overview of the recent *** review takes such an initiative by summarizing the promises and challenges in the electrocatalytic applications of fullerene and its *** content is structured according to the composition and structure of fullerene,including intact fullerene(e.g.,fullerene composite and superlattices)and fullerene derivatives(e.g.,doped,endohedral,and disintegrated fullerene).The synthesis,characterization,catalytic mechanisms,and deﬁciencies of these fullerene-based materials are explicitly *** conclude it by sharing our perspectives on the key aspects that future efforts shall consider.

关键词： Fullerene Fullerene derivative Metal-free catalyst Structural defect electrocatalyst

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

liquid metal compartmented by polyphenol-mediated nanointerfaces enables high-performance thermal management on electronic devices

引用

InfoMat 2024年第1期6卷 83-95页

作者： Chaojun Zhang Yang Tang Tianyu guo Yizhou Sang Ding li Xiaoling Wang Orlando j.Rojas junling guo BMI Center for Biomass Materials and Nanointerfaces College of Biomass Science and EngineeringSichuan UniversityChengduSichuanthe People's Republic of China Bioproducts Institute Departments of Chemical and Biological EngineeringThe University of British ColumbiaVancouverBritish ColumbiaCanada Institute of Development Studies Southwestern University of Finance and EconomicsChengduSichuanthe People's Republic of China National engineering Laboratory for Clean Technology of Leather Manufacture Sichuan UniversityChengduSichuanthe People's Republic of China State Key Laboratory of Polymer Materials engineering Sichuan UniversityChengduSichuanthe People's Republic of China

The exponentially increasing heat generation in electronic devices,induced by high power density and miniaturization,has become a dominant issue that affects carbon footprint,cost,performance,reliability,and *** metals(LMs)with high thermal conductivity are promising candidates for effective thermal management yet are facing pump-out and surface-spreading *** in the form of metallic particles can address these problems,but apparent alloying processes elevate the LM melting point,leading to severely deteriorated ***,we propose a facile and sustainable approach to address these challenges by using a biogenic supramolecular network as an effective diffusion barrier at copper particle-LM(eGaIn/Cu@TA)interfaces to achieve superior thermal *** supramolecular network promotes LM stability by reducing unfavorable alloying and fluidity *** eGaIn/Cu@TA exhibits a record-high metallic-mediated thermal conductivity(66.1 W m^(-1) K^(-1))and fluidic ***,mechanistic studies suggest the enhanced heat flow path after the incorporation of copper particles,generating heat dissipation suitable for computer central processing units,exceeding that of commercial *** results highlight the prospects of renewable macromolecules isolated from biomass for the rational design of nanointerfaces based on metallic particles and LM,paving a new and sustainable avenue for high-performance thermal management.

关键词： electronic devices High thermal conductivity liquid metals Natural polyphenols Thermal management

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fast and Adaptive Multi-Agent Planning under Collaborative Temporal Logic Tasks via Poset Products

引用

Research 2024年第2期2024卷 81-94页

作者： Zesen liu Meng guo Weimin Bao Zhongkui li Deparment of Mechanics and engineering Science College of EngineeringPeking UniversityBejing 0081 China Science and Technology Commission of China Aerospace Science and Technology Corporation Beijing 100048China

efficient coordination and planning is essential for large-scale multi-agent systems that collaborate in a shared dynamic environment. Heuristic search methods or learning-based approaches often lack the guarantee on correctness and performance. Moreover, when the collaborative tasks contain both spatial and temporal requirements, e.g., as linear temporal logic (LTL) formulas, formal methods provide a verifiable framework for task planning. However, since the planning complexity grows exponentially with the number of agents and the length of the task formula, existing studies are mostly limited to small artificial cases. To address this issue, a new planning paradigm is proposed in this work for system-wide temporal task formulas that are released online and continually. It avoids two common bottlenecks in the traditional methods, i.e., (a) the direct translation of the complete task formula to the associated B點hi automaton and (b) the synchronized product between the B點hi automaton and the transition models of all agents. Instead, an adaptive planning algorithm is proposed, which computes the product of relaxed partially ordered sets (R-posets) on-the-fly and assigns these subtasks to the agents subject to the ordering constraints. It is shown that the first valid plan can be derived with a polynomial time and memory complexity with respect to the system size and the formula length. Our method can take into account task formulas with a length of more than 400 and a fleet with more than 400 agents, while most existing methods fail at the formula length of 25 within a reasonable duration. The proposed method is validated on large fleets of service robots in both simulation and hardware experiments.

关键词： hardware service system

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Distribution of oxide inclusions in H13 castings under super-gravity field with multi-stage rotation speeds

引用

journal of Iron and Steel Research International 2024年第1期31卷 121-133页

作者： Shao-ying li Xiao-jun Xi Xing-ming Zhao Han-j.e guo jing guo School of Metallurgical and ecological engineering University of Science and Technology Beijing(USTB)Beijing100083China Beijing Key Laboratory of Special Melting and Preparation of High-end Metal Materials Beijing100083China Beijing Beiye Functional Materials Corporation Beijing100192China Shandong Tianwu Forming Technology Co. Ltd.Liaocheng252024ShandongChina

The 42 kg industrial H13 castings were prepared by different super-gravity fields with multi-rotation speeds,and the distribution of oxide inclusions in the castings was *** addition,the inward movement Reynolds number and inward movement time of oxide inclusions as well as the solidification time of molten steel at different positions in the castings were calculated to clarify the removal mechanism of oxide inclusions in super-gravity *** results show that the large size(i.e.,greater than 10μm)oxide inclusions are mainly concentrated in the inner and outer parts of the super-gravity castings with constant rotation speed(500 r min^(-1))and five-stage rotation speeds(500,600,750,850,and 950 r min^(-1)),respectively,while there are no large oxide inclusions in the super-gravity castings with three-stage rotation speeds(500,600,and 750 r min^(-1)).Although an increase in the particle size of inclusion and the rotation speed in super-gravity field is conducive to the increase in the inward movement Reynolds number of oxide inclusions and reduction in the inward movement time of oxide inclusions,it will reduce the local solidification time of molten *** the range of the rotation speed studied,the super-gravity field with three-stage rotation speeds has the best effect on the removal of inclusions in H13 molten steel.

关键词： Distribution Oxide inclusion H13 casting Super-gravity field Rotation speed

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Humanoid robot heads for human-robot interaction:A review

引用

Science China(Technological Sciences) 2024年第2期67卷 357-379页

作者： li Yi ZHU liXiang ZHANG ZiQian guo MingFei li ZhiXin li YanBiao HASHIMOTO Minoru Key Laboratory of Special Purpose equipment and Advanced Processing Technology of Ministry of education Zhejiang University of TechnologyHangzhou 310023China Zhejiang Provincial Key Laboratoryof Special Purpose equipment and Advanced Processing Technology Zhejang Universityof Technology Hangzhou 310023 China Faculy of Textile Science and Technology Shinshu UniversityUeda 386-8567Japan

The humanoid robot head plays an important role in the emotional expression of human-robot interaction(HRI).They are emerging in industrial manufacturing,business reception,entertainment,teaching assistance,and tour *** recent years,significant progress has been made in the field of humanoid ***,there is still a lack of humanoid robots that can interact with humans naturally and *** review comprises a comprehensive survey of state-of-the-art technologies for humanoid robot heads over the last three decades,which covers the aspects of mechanical structures,actuators and sensors,anthropomorphic behavior control,emotional expression,and human-robot ***,the current challenges and possible future directions are discussed.

关键词： humanoid robot head anthropomorphic behaviors emotional expression human-robot interaction

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：