检索结果-南通市图书馆

Transfer learning-based encoder-decoder model with visual explanations for infrastructure crack segmentation:New open database and comprehensive evaluation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Underground Space 2024年第4期17卷 60-81页

作者： Fangyu Liu Wenqi Ding Yafei Qiao Linbing Wang Illinois Center for Transporation Department of Civil and Environmental EngineeringUniversity of Illinois Urbana-ChampaignIllinois 61801USA department of Geotechnical engineering College of Civil EngineeringTongji UniversityShanghai 200092China Key Laboratory of Geotechnical and Underground engineering of the Ministry of Education Tongji UniversityShanghai 200092China School of Environmental CivilAgricultural and Mechanical EngineeringUniversity of GeorgiaGeorgia 30602USA

Contemporary demands necessitate the swift and accurate detection of cracks in critical infrastructures,including tunnels and *** study proposed a transfer learning-based encoder-decoder method with visual explanations for infrastructure crack ***,a vast dataset containing 7089 images was developed,comprising diverse conditions—simple and complex crack patterns as well as clean and rough ***,leveraging transfer learning,an encoder-decoder model with visual explanations was formulated,utilizing varied pre-trained convolutional neural network(CNN)as the *** explanations were achieved through gradient-weighted class activation mapping(Grad-CAM)to interpret the CNN segmentation ***,accuracy,complexity(computation and model),and memory usage assessed CNN feasibility in practical *** performance was gauged via prediction and visual *** investigation encompassed hyperparameters,data augmentation,deep learning from scratch *** learning,segmentation model architectures,segmentation model encoders,and encoder pre-training *** underscored transfer learning’s potency in enhancing CNN accuracy for crack segmentation,surpassing deep learning from ***,encoder classification accuracy bore no significant correlation with CNN segmentation *** all tested models,UNet-EfficientNet_B7 excelled in crack segmentation,harmonizing accuracy,complexity,memory usage,prediction,and visual explanation.

关键词： Crack segmentation Transfer learning Visual explanation infrastructure Database

Exploring Multi-Task Learning for Forecasting Energy-Cost Resource Allocation in IoT-Cloud Systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4603-4620页

作者： Mohammad Aldossary Hatem A.Alharbi Nasir Ayub department of Computer engineering and Information College of EngineeringPrince Sattam Bin Abdulaziz UniversityWadi Al-Dawasir11991Saudi Arabia department of Computer engineering College of Computer Science and EngineeringTaibah UniversityMadinah42353Saudi Arabia department of Creative Technologies Air University IslamabadIslamabad44000Pakistan

Cloud computing has become increasingly popular due to its capacity to perform computations without relying on physical infrastructure,thereby revolutionizing computer ***,the rising energy consumption in cloud centers poses a significant challenge,especially with the escalating energy *** paper tackles this issue by introducing efficient solutions for data placement and node management,with a clear emphasis on the crucial role of the Internet of Things(IoT)throughout the research *** IoT assumes a pivotal role in this study by actively collecting real-time data from various sensors strategically positioned in and around data *** sensors continuously monitor vital parameters such as energy usage and temperature,thereby providing a comprehensive dataset for *** data generated by the IoT is seamlessly integrated into the Hybrid TCN-GRU-NBeat(NGT)model,enabling a dynamic and accurate representation of the current state of the data center *** the incorporation of the Seagull Optimization Algorithm(SOA),the NGT model optimizes storage migration strategies based on the latest information provided by IoT *** model is trained using 80%of the available dataset and subsequently tested on the remaining 20%.The results demonstrate the effectiveness of the proposed approach,with a Mean Squared Error(MSE)of 5.33%and a Mean Absolute Error(MAE)of 2.83%,accurately estimating power prices and leading to an average reduction of 23.88%in power ***,the integration of IoT data significantly enhances the accuracy of the NGT model,outperforming benchmark algorithms such as DenseNet,Support Vector Machine(SVM),Decision Trees,and *** NGT model achieves an impressive accuracy rate of 97.9%,surpassing the rates of 87%,83%,80%,and 79%,respectively,for the benchmark *** findings underscore the effectiveness of the proposed method in optimizing energy efficiency and enhancing the predictive

关键词： Cloud computing energy efficiency data center optimization internet of things(IoT) hybrid models

Triple the steady-state reaction rate by decorating the In_(2)O_(3)surface with SiO_(x)for CO_(2)hydrogenation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第8期95卷 96-105,I0003页

作者： Hao Wang Chun Yang Xiaoyan Yu Mingrui Wang Runze Yang Xiaowa Nie Ben Hang Yin Alex C.K.Yip Chunshan Song Guanghui Zhang Xinwen Guo State Key Laboratory of Fine Chemicals Frontier Science Center for Smart MaterialsPSU-DUT Joint Center for Energy ResearchSchool of Chemical EngineeringDalian University of TechnologyDalian 116024LiaoningChina department of Chemistry the Chinese University of Hong KongHong Kong 999077China Paihau-Robinson Research Institute the MacDiarmid Institute for Advanced Materials and NanotechnologyVictoria University of WellingtonWellington 6012New Zealand department of Chemical and Process engineering The University of CanterburyChristchurch 8041New Zealand

Indium oxide(In_(2)O_(3)),as a promising candidate for CO_(2)hydrogenation to C_(1) products,often suffers from sintering and activity decline,closely related to the undesirable structural evolution under reaction *** on the comprehension of the dynamic evolution,this study presents an efficient strategy to alleviate the agglomeration of In_(2)O_(3)nanoparticles by the surface decoration with highly dispersed silica species(SiO_(x)).Various structural characterizations combined with density functional theory calculations demonstrated that the sintering resulted from the over-reduction,while the enhanced stability originated from the anchoring effect of highly stable In-OSi bonds,which hinders the substantial formation of metallic In(In^(0))and the subsequent agglomeration.0.6Si/In_(2)O_(3)exhibited CO_(2)conversion rate of10.0 mmol g^(-1)h^(-1)at steady state vs.3.5 mmol g^(-1)h^(-1)on In_(2)O_(3)in CO_(2)*** steady-state activity was also achieved on Pd-modified *** to the traditional Pd/In_(2)O_(3)catalyst,the methanol production rate of Pd catalyst supported on 0.6Si/In_(2)O_(3)was enhanced by 23%,showing the potential of In_(2)O_(3)modified by SiO_(x)in serving as a platform *** work provides a promising method to design new In_(2)O_(3)-based catalysts with improved activity and stability in CO_(2)hydrogenation.

关键词： CO_(2)hydrogenation In_(2)O_(3)sintering Dynamic structural evolution Surface SiO_(x)modification DFT simulations

Enhancing crystal integrity and structural rigidity of CsPbBr_(3) nanoplatelets to achieve a narrow colorsaturated blue emission

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

Light(Science & Applications) 2024年第5期13卷 985-997页

作者： Qianqian Huang Wenxu Yin Bo Gao Qingsen Zeng Dong Yao Hao Zhang Yinghe Zhao Weijia Zheng Jiaqi Zhang Xuyong Yang Xiaoyu Zhang Andrey L.Rogach Key Laboratory of Automobile Materials MOE School of Materials Science&Engineeringand Jilin Provincial International Cooperation Key Laboratory of High-Efficiency Clean Energy MaterialsJilin UniversityChangchunChina. State Key Laboratory of Supramolecular Structure and Materials College of ChemistryJilin UniversityChangchunChina. State Key Laboratory of Materials Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhanHubeiChina. department of Chemistry University of VictoriaVictoriaBCCanada. Key Laboratory of Advanced Display and System Applications of Ministry of Education Shanghai UniversityShanghaiChina. department of Materials Science and engineering and Centre for Functional Photonics(CFP)City University of Hong KongHong Kong S.A.RChina

Quantum-confined CsPbBr_(3) perovskites are promising blue emitters for ultra-high-definition displays,but their soft lattice caused by highly ionic nature has a limited ***,we endow CsPbBr_(3) nanoplatelets(NPLs)with atomic crystal-like structural rigidity through proper surface engineering,by using strongly bound N-dodecylbenzene sulfonic acid(DBSA).A stable,rigid crystal structure,as well as uniform,orderly-arranged surface of these NPLs is achieved by optimizing intermediate reaction stage,by switching from molecular clusters to mono-octahedra,while interaction with DBSA resulted in formation of a Cs_(x)O monolayer shell capping the NPL *** a result,both structural and optical stability of the CsPbBr3 NPLs is enhanced by strong covalent bonding of DBSA,which inhibits undesired phase transitions and decomposition of the perovskite phase potentially caused by ligand ***,rather small amount of DBSA ligands at the NPL surface results in a short inter-NPL spacing in their closely-packed films,which facilitates efficient charge injection and *** photoluminescence of the produced CsPbBr_(3) NPLs is bright(nearly unity emission quantum yield)and peaks at 457 nm with an extremely narrow bandwidth of 3.7 nm at 80 K,while the bandwidth of the electroluminescence(peaked at 460 nm)also reaches a record-narrow value of 15 nm at room *** value corresponds to the CIE coordinates of(0.141,0.062),which meets Rec.2020 standards for ultra-high-definition displays.

关键词： temperature stability narrow

Distributed fiber optic sensors for tunnel monitoring:A state-of-the-art review

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Rock Mechanics and Geotechnical engineering 2024年第9期16卷 3841-3863页

作者： Xuehui Zhang Honghu Zhu Xi Jiang Wout Broere Geo-engineering Section Department of Geoscience and EngineeringDelft University of TechnologyDelft2628CNthe Netherlands School of Earth Sciences and engineering Nanjing UniversityNanjing210023China department of Civil and Environmental engineering The Hong Kong Polytechnic UniversityKowloonHong KongChina

Distributed fiber optic sensors(DFOSs)possess the capability to measure strain and temperature variations over long distances,demonstrating outstanding potential for monitoring underground *** study presents a state-of-the-art review of the DFOS applications for monitoring and assessing the deformation behavior of typical tunnel infrastructure,including bored tunnels,conventional tunnels,as well as immersed and cut-and-cover *** systems based on Brillouin and Rayleigh scattering principles are both *** implementing DFOS monitoring,the fiber optic cable can be primarily installed along transverse and longitudinal directions to(1)measure distributed strains by continuously adhering the fiber to the structure’s surface or embedding it in the lining,or(2)measure point displacements by spot-anchoring it on the lining *** are four critical aspects of DFOS monitoring,including proper selection of the sensing fiber,selection of the measuring principle for the specific application,design of an effective sensor layout,and establishment of robust field sensor *** four issues are comprehensively discussed,and practical suggestions are provided for the implementation of DFOS in tunnel infrastructure monitoring.

关键词： Distributed fiber optic sensor(DFOS) Tunnel infrastructure Distributed strain sensing Point displacement monitoring Field instrumentation

Digital twin‐based multi‐objective autonomous vehicle navigation approach as applied in infrastructure construction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IET Cyber-Systems and Robotics 2024年第2期6卷 1-19页

作者： Tingjun Lei Timothy Sellers Chaomin Luo Lei Cao Zhuming Bi department of Electrical and Computer engineering Mississippi State UniversityMississippi StateMississippiUSA department of Electrical and Computer engineering University of MississippiUniversityMississippiUSA department of Civil and Mechanical engineering Purdue University Fort WayneFort WayneIndianaUSA

The widespread adoption of autonomous vehicles has generated considerable interest in their autonomous operation,with path planning emerging as a critical ***,existing road infrastructure confronts challenges due to prolonged use and insufficient *** research on autonomous vehicle navigation has focused on determining the trajectory with the shortest distance,while neglecting road construction information,leading to potential time and energy inefficiencies in real-world scenarios involving infrastructure *** address this issue,a digital twin-embedded multi-objective autonomous vehicle navigation is proposed under the condition of infrastructure *** authors propose an image processing algorithm that leverages captured images of the road construction environment to enable road extrac-tion and modelling of the autonomous vehicle ***,a wavelet neural network is developed to predict real-time traffic flow,considering its inherent ***,a multi-objective brainstorm optimisation(BSO)-based method for path planning is introduced,which optimises total time-cost and energy consumption objective *** ensure optimal trajectory planning during infrastructure con-struction,the algorithm incorporates a real-time updated digital twin throughout autonomous vehicle *** effectiveness and robustness of the proposed model are validated through simulation and comparative studies conducted in diverse scenarios involving road *** results highlight the improved performance and reli-ability of the autonomous vehicle system when equipped with the authors’approach,demonstrating its potential for enhancing efficiency and minimising disruptions caused by road infrastructure development.

关键词： autonomous vehicle intelligent robots motion planning navigation path planning robot planning

Internal flow in sessile droplets induced by substrate oscillation:towards enhanced mixing and mass transfer in microfluidic systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第3期10卷 369-379页

作者： Tianyi Zhang Peng Zhou Terrence Simon Tianhong Cui department of Mechanical engineering University of MinnesotaMinneapolisMN 55455USA

The introduction of flows within sessile droplets is highly effective for many lab-on-a-chip chemical and biomedical ***,generating such flows is difficult due to the typically small droplet ***,we present a simple,non-contact strategy to generate internal flows in sessile droplets for enhancing mixing and mass *** flows are driven by actuating a rigid substrate into oscillation with certain amplitude distributions without relying on the resonance of the droplet *** oscillation characteristics and corresponding flow patterns are documented *** indices and mass transfer coefficients of sessile droplets on the substrate surface are measured using optical and electrochemical *** demonstrate complete mixing within the droplets in 1.35 s and increases in mass transfer rates of more than seven times static *** of concept was conducted with experiments of silver nanoparticle synthesis and with heavy metal ion sensing employing the sessile droplet as a microreactor for synthesis and an electrochemical cell for *** degrees of enhancement of synthesis efficiency and detection sensitivity attributed to the internal flows are experimentally documented.

关键词： mixing oscillation synthesis

A Survey on Model Predictive Control of DFIGs in Wind Energy Conversion Systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第3期10卷 1085-1104页

作者： Shuo Yan Junyu Chen Minghao Wang Yongheng Yang Jose M.Rodriguez STEM College RMIT UniversityMelbourneAustralia Hong Kong Polytechnic university Hong KongChina State Key Laboratory of Internet of Things for Smart City(UM) Department of Electrical and Computer EngineeringUniversity of MacaoMacaoChina College of Electrical engineering Zhejiang UniversityHangzhou 310027China Universidad San Sebastin Campus BellavistaSantiago de ChileCLSantiago de Chile 000000Chile IEEE

This paper presents a comprehensive study on the model predictive control(MPC)of doubly fed induction generators(DFIG)in wind energy conversion systems(WECS);in particular the MPC of the rotor side *** general principle of prevalent MPC strategies is discussed to introduce the theoretical framework in the first ***,mainstream and high-performance MPC methods of DFIGs have been identified as model predictive current control(MPCC),model predictive torque control(MPTC),and model predictive power control(MPPC).Starting from analyzing dynamic models,these MPC strategies are investigated in terms of operating principles and technical *** paper further investigates implementation of MPC strategies in unbalanced *** on the quantitative and qualitative analysis of several case studies,performance of various MPC schemes is compared and their special features are *** for designing MPC strategies of DFIGs in WECS are provided.

关键词： Doubly fed induction generator(DFIG) model predictive control(MPC) wind energy

Distributed Platooning Control of Automated Vehicles Subject to Replay Attacks Based on Proportional Integral Observers

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第9期11卷 1954-1966页

作者： Meiling Xie Derui Ding Xiaohua Ge Qing-Long Han Hongli Dong Yan Song department of Control Science and engineering University of Shanghai for Science and TechnologyShanghai 200093China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia Artificial Intelligence Energy Research Institute Northeast Petroleum UniversityDaqing 163318the Heilongjiang Provincial Key Laboratory of Networking and Intelligent ControlNortheast Petroleum UniversityDaqing 163318 Sanya Offshore Oil&Gas Research Institute Northeast Petroleum UniversitySanya 572024China

Secure platooning control plays an important role in enhancing the cooperative driving safety of automated vehicles subject to various security *** paper focuses on the distributed secure control issue of automated vehicles affected by replay attacks.A proportional-integral-observer(PIO)with predetermined forgetting parameters is first constructed to acquire the dynamical information of ***,a time-varying parameter and two positive scalars are employed to describe the temporal behavior of replay *** light of such a scheme and the common properties of Laplace matrices,the closed-loop system with PIO-based controllers is transformed into a switched and time-delayed ***,some sufficient conditions are derived to achieve the desired platooning performance by the view of the Lyapunov stability *** controller gains are analytically determined by resorting to the solution of certain matrix inequalities only dependent on maximum and minimum eigenvalues of communication ***,a simulation example is provided to illustrate the effectiveness of the proposed control strategy.

关键词： Automated vehicles platooning control proportional-integral-observers(PIOs) replay attacks time-delays