检索结果-南通市图书馆

Surrounding rock classification from onsite images with deep transfer learning based on EfficientNet

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

Frontiers of Structural and Civil Engineering 2024年第9期18卷 1311-1320页

作者： Xiaoying zhuang Wenjie FAN Hongwei GUO Xuefeng CHEN Qimin WANG Department of Geotechnical Engineering College of Civil EngineeringTongji UniversityShanghai 200092China Chair of Computational Science and Simulation Technology Institute of PhotonicsLeibniz University HannoverHannover 30167Germany Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education Tongji UniversityShanghai 200092China Guizhou Xingyi Huancheng Expressway Co. Ltd.Xingyi 562400China

This paper proposes an accurate,efficient and explainable method for the classification of the surrounding rock based on a convolutional neural network(CNN).The state-of-the-art robust CNN model(EfficientNet)is applied to tunnel wall image *** filtering,data augmentation and other data pre-processing techniques are used to improve the data quality and *** with transfer learning,the generality,accuracy and efficiency of the deep learning(DL)model are further improved,and finally we achieve 89.96%*** with other state-of-the-art CNN architectures,such as ResNet and Inception-ResNet-V2(IRV2),the presented deep transfer learning model is more stable,accurate and *** reveal the rock classification mechanism of the proposed model,Gradient-weight Class Activation Map(Grad-CAM)visualizations are integrated into the model to enable its explainability and *** developed deep transfer learning model has been applied to support the tunneling of the Xingyi City Bypass in the high mountain area of Guizhou,China,with great results.

关键词： surrounding rock classification convolutional neural network EfficientNet Gradient-weight Class Activation Map

Numerical analysis of the correlation between fluid dynamic modes and hydrodynamic noise in flows around a three-dimensional circular cylinder

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

Journal of Hydrodynamics 2024年第1期36卷 119-129页

作者： Jia-jia Qin Ming-xin Zou Yuan zhuang De-cheng Wan Computational Marine Hydrodynamics Lab(CMHL) School of Naval ArchitectureOcean and Civil EngineeringShanghai Jiao Tong UniversityShanghai200240China Wuhan Second Ship Design and Research Institute Wuhan430205China

The flow around a circular cylinder for Re=1000 is characterized by flow separation and Karman vortex *** typical flow features can be captured to study the correlation between fluid fields and sound *** this paper,the three-dimensional circular cylinder is taken as the research object,and the probes of surface fluctuating pressure and far field sound pressure are arranged every 10°.The directional diagram and the coherence of fluctuating pressure and sound pressure are *** relationship between the flow mode and hydrodynamic noise is studied by using dynamic mode decomposition(DMD).The characteristics of the dipole and quadrupole sound source term of a long span cylinder are *** results show that at the angles between 30°–120°and 190°–350°,the fluctuating pressure contributes more to the generation of dipole *** quadrupole sound source shows three-dimensional effects,which is more obvious in a cylinder with large spanwise length.

关键词： Pressure coherence dynamic mode decomposition flow-sound correlation circular cylinder

“Co-coordination force”assisted rigid-flexible coupling crystalline polymer for high-performance aqueous zinc-organic batteries

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

Chinese Chemical Letters 2024年第9期35卷 501-506页

作者： Jun Guo Zhenbang zhuang Wanqiang Liu Gang Huang School of Materials Science and Engineering Changchun University of Science and TechnologyChangchun 130022China State Key Laboratory of Rare Earth Resource Utilization Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022China Key Laboratory of Automobile Materials Ministry of EducationDepartment of Materials Science and EngineeringJilin UniversityChangchun 130022China

Organic electrode materials(OEMs)have attracted substantial attention for aqueous zinc-ion batteries(AZIBs)due to their advantages in relieving resource and environmental ***,the potential of OEMs is plagued by their low achievable capacity and high ***,we have proposed a new concept of“co-coordination force”and designed a rigid-flexible coupling crystalline polymer that can overcome the abovementioned *** obtained crystalline polymer(BQSPNs)with multiredox centres makes the BQSPNs exist intermolecular hydrogen bonds(HB)among-C=O,-C=N,and-NH and consequently exhibits transverse two-dimensional arrays and longitudinalπ-πstacking ***,in-situ FTIR,Raman,variable temperature FTIR spectra,and 2D nuclear overhauser effect spectroscopy(NOESY)well capture the existence and evolution process of HB during the electrochemistry reaction process of BQSPNs,uncovering the effect of HB in stabilizing the structure and promoting the reaction *** a result,the BQSPNs with rationally designed“co-coordination force”deliver a high capacity of 459.6 m Ah/g and a stable cycling lifetime for more than 100,000 cycles at 10 A/g in *** results disclose the HB effect and provide a brand-new strategy for high-performance OEMs design.

关键词： Co-coordination force Crystalline polymer Hydrogen bonds Organic electrode materials Aqueous zinc-ion batteries

Detection of Turbulence Anomalies Using a Symbolic Classifier Algorithm in Airborne Quick Access Record(QAR)Data Analysis

在线全文

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2024年第7期41卷 1438-1449页

作者： Zibo zhuang Kunyun LIN Hongying ZHANG Pak-Wai CHAN Flight Academy Civil Aviation University of ChinaTianjin 300300China School of Electronic Information and Automation Civil Aviation University of ChinaTianjin 300300China Aviation Weather Services Hong Kong ObservatoryHong KongChina

As the risks associated with air turbulence are intensified by climate change and the growth of the aviation industry,it has become imperative to monitor and mitigate these threats to ensure civil aviation *** eddy dissipation rate(EDR)has been established as the standard metric for quantifying turbulence in civil *** study aims to explore a universally applicable symbolic classification approach based on genetic programming to detect turbulence anomalies using quick access recorder(QAR)*** detection of atmospheric turbulence is approached as an anomaly detection *** evaluations demonstrate that this approach performs on par with direct EDR calculation methods in identifying turbulence ***,comparisons with alternative machine learning techniques indicate that the proposed technique is the optimal methodology currently *** summary,the use of symbolic classification via genetic programming enables accurate turbulence detection from QAR data,comparable to that with established EDR approaches and surpassing that achieved with machine learning *** finding highlights the potential of integrating symbolic classifiers into turbulence monitoring systems to enhance civil aviation safety amidst rising environmental and operational hazards.

关键词： turbulence detection symbolic classifier quick access recorder data

Classifying Chinese Medicine Constitution Using Multimodal Deep-Learning Model

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Integrative Medicine 2024年第2期30卷 163-170页

作者： GU Tian-yu YAN zhuang-zhi JIANG Jie-hui School of Communication&Information Engineering Shanghai UniversityShanghai(200444)China School of Life Science Shanghai UniversityShanghai(200444)China

Objective:To develop a multimodal deep-learning model for classifying Chinese medicine constitution,i.e.,the balanced and unbalanced constitutions,based on inspection of tongue and face images,pulse waves from palpation,and health information from a total of 540 ***:This study data consisted of tongue and face images,pulse waves obtained by palpation,and health information,including personal information,life habits,medical history,and current symptoms,from 540 subjects(202 males and 338 females).Convolutional neural networks,recurrent neural networks,and fully connected neural networks were used to extract deep features from the *** fusion and decision fusion models were constructed for the multimodal ***:The optimal models for tongue and face images,pulse waves and health information were ResNet18,Gate Recurrent Unit,and entity embedding,*** fusion was superior to decision *** multimodal analysis revealed that multimodal data compensated for the loss of information from a single mode,resulting in improved classification ***:Multimodal data fusion can supplement single model information and improve classification *** research underscores the effectiveness of multimodal deep learning technology to identify body constitution for modernizing and improving the intelligent application of Chinese medicine.

关键词： Chinese medicine constitution classification multimodal deep learning tongue image face image pulsewave health information

Metal complexes of bipyridine-functionalized covalent organic frameworks as efficient electrocatalysts for oxygen evolution reaction

在线全文

学校读者我要写书评

暂无评论

Rare Metals 2024年第7期43卷 3096-3106页

作者： zhuang-zhuang Wu Tian Xia Ying Liang Yong-Peng Li Zhu-Yin Sui Li-Juan Feng Dao-Xiong Wu Xin-Long Tian Qi Chen State Key Laboratory of Marine Resource Utilization in South China Sea School of Marine Science and EngineeringHainan UniversityHaikou 570228China School of Chemistry and Chemical Engineering Yantai UniversityZhuhai519041China School of Bioengineering Zhuhai Campus of Zunyi Medical UniversityZhuhai519041China

Electrocatalytic water splitting is considered a clean and practic al method for producing *** this study,COF-Bpy,a bipyridine-functionalized covalent organic framework(COF),was prepared via post-synthetic modification,after which electrocatalysts for the oxygen evolution reactions(OER)were formed through coordination to single-or double-transition metals(Fe,Co,Ni,FeCo,FeNi or CoNi).COF-Bpy@FeNi delivered the best OER performance among the studied electrocatalysts,with an overpotential of 399 mV at 10 mA·cm^(-2)in an alkaline electrolyte(1.0 mol·L^(-1)KOH aqueous).Notably,the electrocatalytic performance of COF-Bpy@FeNi showed slight degradation during durability testing,which is ascribable to its irreversible benzoquinoline structure and strong metal *** expected,COF-Bpy@FeNi exhibited a low overpotential of 347 mV at a turnover frequency(TOF)of 0.1 s^(-1),which suggests that COF-Bpy@FeNi possesses excellent intrinsic electroc atalytic OER ***,density functional theory(DFT)calculations reveal that the Ni site plays a major role,while the Fe site adjusts the electronic structure of the Ni ions,which rationalizes the excellent OER properties of COF-Bpy@*** study not only provides a simple and efficient method for complexing COFs with transition metals,but also offers a novel strategy for designing porous organic polymer electrocatalysts.

关键词： Covalent organic framework Oxygen evolution reactions(OER)electrocatalyst Nickel-iron synergy Water splitting

Microbial Sulfate Reduction and Its Role in Carbon Sequestration in Marine Sediments

在线全文

学校读者我要写书评

暂无评论

Journal of Earth Science 2024年第4期35卷 1378-1381页

作者： Xiting Liu Houjie Wang Jiarui Liu Guang-Chao zhuang Key Laboratory of Submarine Geosciences and Prospecting Technology College of Marine GeosciencesOcean University of ChinaQingdao266100China Qingdao Marine Science and Technology Center Laboratory for Marine GeologyQingdao266237China Department of Earth Planetaryand Space SciencesUniversity of CaliforniaLos Angeles90095USA Frontiers Science Center for Deep Ocean Multispheres and Earth System(FDOMES)and Key Laboratory of Marine Chemistry Theory and Technology Ministry of EducationOcean University of ChinaQingdao266100China

0 INTRODUCTION The carbon buried in marine sediments in the form of organic carbon or carbonate minerals represents the largest pathway for carbon removal from Earth's surface environments(Sun and Turchyn,2014).Microbial sulfate reduction(MSR)is a fundamental biogeochemical process occurring in marine sediments,where sulfate-reducing bacteria(SRB)reduce sulfate(SO42-)to sulfide(S2-)using organic matter or methane as electron donors(Jorgensen,2021).

关键词： buried carbonate environments

A novel high-Cr CoNi-based superalloy with superior high-temperature microstructural stability, oxidation resistance and mechanical properties

在线全文

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2024年第6期31卷 1373-1381页

作者： Xiaorui Zhang Min Zou Song Lu Longfei Li Xiaoli zhuang Qiang Feng Beijing Advanced Innovation Center for Materials Genome Engineering State Key Laboratory for Advanced MetalsUniversity of Science and Technology BeijingBeijing 100083China

A novel multicomponent high-Cr CoNi-based superalloy with superior comprehensive performance was prepared,and the evaluation of its high-temperature microstructural stability,oxidation resistance,and mechanical properties was conducted mainly using its cast polycrystalline *** results disclosed that the morphology of theγ′phase remained stable,and the coarsening rate was slow during the long-term aging at 900–1000℃.The activation energy forγ′precipitate coarsening of alloy 9CoNi-Cr was(402±51)kJ/mol,which is higher compared with those of CMSX-4 and some other Ni-based and Co-based ***,there was no indica-tion of the formation of topologically close-packed phases during this *** these factors demonstrated the superior microstructural stability of the *** mass gain of alloy 9CoNi-Cr was 0.6 mg/cm^(2) after oxidation at 1000℃ for 100 h,and the oxidation resistance was comparable to advanced Ni-based superalloys CMSX-4,which can be attributed to the formation of a continuous Al_(2)O_(3) protective ***,the compressive yield strength of this cast polycrystalline alloy at high temperatures is clearly higher than that of the conventional Ni-based cast superalloy and the compressive minimum creep rate at 950℃ is comparable to that of the conventional Ni-based cast superalloy,demonstrating the alloy’s good mechanical properties at high *** is partially because high Cr is bene-ficial in improving theγandγ′phase strengths of alloy 9CoNi-Cr.

关键词： CoNi-based superalloys microstructure coarsening oxidation mechanical properties

Dynamic coverage of mobile multi-target in sensor networks based on virtual force

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2024年第4期31卷 83-94页

作者： Huang Qingdong Wang Mei Chen Chen Han zhuang School of Communication and Information Engineering Xi'an University of Posts and TelecommunicationsXi'an 710121China

A distributed self-control coverage method for mobile multi-target based on virtual force(MMTVF)is proposed to monitor dynamic targets using a mobile sensor network(MSN).The dynamic coverage method is introduced to maintain network connectivity and optimize the coverage of moving *** method consists of two parts,one is the virtual force model which is proposed for motion control,and the other is the whale optimization algorithm which is improved to optimize node positions and achieve a steady state *** virtual resultant force stretches the network towards uncovered targets using its multi-target attractive force,maintains network connectivity during network stretching using its attractive force,and prevents node collisions while nodes are moving using its repulsive *** operating mechanism of the multi-target attractive force and other forces is thoroughly *** criteria for the model in different application scenarios are also *** comparisons demonstrate MMTVF has significant advantages over other similar approaches.

关键词： mobile sensor network(MSN) dynamic coverage virtual force moving targets