期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到13,413篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Analysis of extent and grain effects in multi-level ecological security network structure 认领 引用
1
作者 PENG Lizhi LIAO Shan +3 位作者 WANG Senpeng ZHANG Jinting WU Xiu TAN Huaqing 《Journal of Geographical Sciences》 SCIE CSCD 2026年第8期1869-1890,共22页
In the context of global change,a central challenge in ecology is to establish the multi-scale evolution and coupling mechanisms of ecosystems.In particular,it is necessary to clarify the structural mismatch between h... In the context of global change,a central challenge in ecology is to establish the multi-scale evolution and coupling mechanisms of ecosystems.In particular,it is necessary to clarify the structural mismatch between hierarchical levels that arises when ecological networks(ENs)are constructed across varying extents or grains.Using city-and central urban-level examples,we introduced a cross-level ENs spatial mismatch measurement index(SMI)and a scale-effect analysis framework.Five representative cities from the Northeast,Northwest,Central,Southwest,and Southeast China were selected as research areas.A unified approach combining minimum cumulative resistance and XGBoost models enable the preliminary construction of two-level ENs.SMI is then applied to evaluate cross-level mismatches,followed by analysis of extent and grain effects.Mechanisms underlying EN disconnection and potential solution pathways are further examined.The results show that:(1)spatial mismatch indicators(SMI_source,SMI_corridor,SMI_nodes)defined on ecological source areas(ESA),corridor,and strategic nodes,reflect mismatch degrees across EN levels;(2)scale effects reveal decreasing SMI with expanding observation extent in central urban area,fluctuating values with synchronous change in data grain,and increasing values with higher statistical grid density;(3)the largest patch index and landscape division index exert a strong influence on SMI_source,while patch number and Shannon's diversity index play key roles in SMI_corridor;and(4)variation in landscape composition and configuration heterogeneity across scales provides explanatory power of mismatch phenomenon and scale effects.The study contributes to ecological pattern analysis by offering a quantitative method for multi-scale EN research,with implications for ecological protection and regional landscape planning. 展开更多
关键词 multi-level ecological networks spatial mismatch scale effect ecosystem protection random forest regression spatial heterogeneity
暂未订购 下载PDF
Nonlinear coupling mechanism of quasi-zero-stiffness units in multi-level structures 认领 引用
2
作者 Shaokun YANG Xingxing SHI +2 位作者 Xingzhong WANG Jiuhui WU Fuyin MA 《Applied Mathematics and Mechanics(English Edition)》 SCIE EI CSCD 2026年第6期1215-1240,共26页
Multilayer structures composed of quasi-zero-stiffness(QZS)units exhibit mechanical characteristics distinct from those of a single unit,and their behaviors are governed by the coupling mechanism between the QZS units... Multilayer structures composed of quasi-zero-stiffness(QZS)units exhibit mechanical characteristics distinct from those of a single unit,and their behaviors are governed by the coupling mechanism between the QZS units.This paper introduces the coupling coefficient to quantitatively describe this mechanism,classifying the system into strongly coupled and weakly coupled states.Through theoretical analysis,numerical simulation,and experimental testing,the static and dynamic responses under different coupling states are comparatively investigated.The results show that in the strongly coupled system,the deformation behavior of each QZS unit shows high consistency,leading to a wider QZS region,weaker nonlinear characteristics,and stronger dynamic response.In the weakly coupled systems,the low degree of deformation coordinations among the units results in different QZS regions,enabling low-frequency vibration isolation under varying loads.The analytical approach of the coupling mechanisms and the static and dynamic response behaviors generated by the two coupling mechanisms provide guidance for the structural design of multifunctional and highly adaptable multi-level QZS metamaterials. 展开更多
关键词 multi-level structure coupling mechanism strong coupling weak coupling deformation coordination
暂未订购 下载PDF
Structural Optimization of a Multi-Story Frame Structure Based on a Pre-Trained Physics-Informed Neural Network(PINN)Surrogate Model 认领 引用
3
作者 An Xu Zhixiong Liu +4 位作者 Hua Rong Liang Han Wei Shi Jun Huang Jiyang Fu 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第4期279-313,共35页
In structural optimization,data-driven surrogate models are often explored as alternatives to finite element analysis to reduce computational cost.However,conventional neural networks usually fail to capture key struc... In structural optimization,data-driven surrogate models are often explored as alternatives to finite element analysis to reduce computational cost.However,conventional neural networks usually fail to capture key structural characteristics and are limited to predicting global responses(e.g.,top displacement),but usually fail to achieve accurate internal force predictions with conventional training data volumes.As a result,most existing studies involving surrogate models did not concern internal force constraints.To address this issue,this study proposes a structural optimization framework based on a pre-trained Physics-Informed Neural Network(PINN)surrogate model.By embedding static equilibrium equation into the loss function,the model achieves higher predictive accuracy,particularly for internal forces,while pre-training accelerates convergence and enhances stability.Combined with an improved multi-swarm particle swarm optimization(MPSO)algorithm,the framework enables efficient optimization of multi-story frame structures under internal force and multiple other constraints.The application to a six-story frame structure validates its effectiveness:compared with a DNN-based model,the PINN-based model improves the coefficient of determination for internal force prediction from 0.8874 to 0.9937.These results demonstrate that the proposed method offers a promising approach for efficient optimization of multi-story frame structures. 展开更多
关键词 Structural optimization intelligent algorithms physics-informed neural networks(PINN) neural networks
暂未订购 下载PDF
Automated nondestructive evaluation of compressive strength of underground lining structure using hyperspectral imaging and deep neural networks 认领 引用
4
作者 Changsong Wang Mingliang Zhou +1 位作者 Le Zhang Hongwei Huang 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2026年第5期3623-3639,共17页
Evaluation of compressive strength in underground lining structures is critical for ensuring structural integrity and safety.Traditional assessment methods are often destructive,time-consuming,and impractical in confi... Evaluation of compressive strength in underground lining structures is critical for ensuring structural integrity and safety.Traditional assessment methods are often destructive,time-consuming,and impractical in confined environments such as tunnels and utility corridors.This study introduces an automated,nondestructive approach to visualize and estimate the compressive strength of underground concrete lining using hyperspectral imaging(HSI)combined with deep neural network(DNN)models.High-dimensional spectral data of concrete lining are assembled and trained to develop two DNN-based regression models,namely the Mono-Spectrum Deep Neural Regressor(MS-DNR)and the Segmented-Spectrum Deep Neural Regressor(SegS_DNR).Utilizing the SegS_DNR model,two-dimensional(2D)compressive strength distribution heatmaps were generated for visualization and assessment of strength variations.The SegS_DNR model demonstrated excellent predictive performance,achieving a coefficient of determination(Rp²)of 0.925 and a Residual Prediction Deviation(RPD)of 5.28 on the testing set for compressive strength estimation.The idea is further validated in site by investigating the capability of identifying the defect regions of the tunnel concrete lining,namely the cracked,spalling,and leaking areas,and demonstrated promising performance in comparison with experienced inspectors on site.This approach offers a contact-free technique for automated structural health monitoring,contributing to safer and more sustainable underground maintenance practices. 展开更多
关键词 Hyperspectral imaging Underground concrete structure Compressive strength Nondestructive detection Deep neural networks(DNN)
暂未订购 下载PDF
Network Structure-function Decoupling Underlying the Cognitive Impairment in Ischemic Leukoaraiosis 认领 引用
5
作者 Mengxue Wang Wenjuan Huang +5 位作者 Yixin Zhu Tong Lu Zhengsheng Zhang Chunming Xie Zan Wang Qingguo Ren 《Biomedical and Environmental Sciences》 SCIE CAS CSCD 2026年第6期717-722,共6页
Cerebral small vessel disease(CSVD)encompasses a spectrum of pathological processes that affect the small arteries,capillaries,and venules of the brain.The neuroimaging features include white matter hyperintensities(W... Cerebral small vessel disease(CSVD)encompasses a spectrum of pathological processes that affect the small arteries,capillaries,and venules of the brain.The neuroimaging features include white matter hyperintensities(WMH),lacunar infarcts,cerebral microbleeds,and enlarged perivascular spaces. 展开更多
关键词 cognitive impairment network structure function decoupling white matter hyperintensities wmh lacunar infarctscerebral microbleedsand pathological processes neuroimaging features cerebral small vessel disease csvd encompasses enlarged perivascular spaces cerebral small vessel disease
暂未订购 下载PDF
Weakly coordinated TGDE regulating hydrogen bond network and solvated structure for high-rate Zn anodes 认领 引用
6
作者 Ao Zeng Dishu Zeng +7 位作者 Yuzhe Luo Xiaowen Qv He Zhao Xiaojun Feng Peng Chen Zhaohui Wang Yuping Wu Kunkun Guo 《Journal of Energy Chemistry》 SCIE EI CAS CSCD 2026年第2期811-820,I0017,共10页
With the rapid growth of technologies requiring high-power energy storage,achieving long-term cyclic stability under ultra-high current density is a key challenge.Aqueous zinc-ion batteries(AZIBs)are promising candida... With the rapid growth of technologies requiring high-power energy storage,achieving long-term cyclic stability under ultra-high current density is a key challenge.Aqueous zinc-ion batteries(AZIBs)are promising candidates due to their intrinsic safety and low cost,but they suffer from severe interfacial instability at rates exceeding 10 mA cm-2,which drastically shortens their cycle life.Inspired by theoretical calculations,triglyme(TGDE)additive with strong electron-donating groups into Zn(OTf)2 electrolytes effectively disrupts the hydrogen-bond network among free water molecules,while the weak coordination of TGDE with Zn2+promotes the entry of OTf-into the primary Zn2+solvated sheath,thus decreasing the coordination number of water with Zn2+.As such,the hydrogen-bond network and the bulk solvated structure are reconstructed with better stability.Moreover,the strong adsorption of TGDE lying on the Zn(002)surface would induce Zn depositions along(002)together with the reduced exposed surface,further effectively inhibiting side reactions.Likewise,TGDE electrolyte induces the formation of such ZnF2-ZnS dual-layer solid electrolyte interface(SEI)with superior chemical stability and ionic conductivity,thereby regulating Zn2+flux with dendrite-free depositions.Based on this electrolyte,Zn‖Zn cells can be stably cycled for 1300 h at a limit of 10 mA cm-2 and 10 mAh cm-2.The assembled Zn‖V2O5 full cells still maintain 99.9%capacity retention after 1000 cycles at 10 A g-1.This work provides a feasible approach for designing aqueous electrolytes to reconstruct the hydrogen-bond network and solvated structure,which can be extended to the applications of high-rate and high-temperature scenarios. 展开更多
关键词 Solvated structure Theoretical calculations Hydrogen-bond network High-rate AZIBs
暂未订购 下载PDF
Multifunctional CNT/cellulose-BN/PVA Composites Integrating Dual-continuous Network Structure with Gradient Conductivity for Electromagnetic Interference Shielding and Joule Heating 认领 引用
7
作者 Xiao-Rui Wang Ting-Ting Liu +2 位作者 Cheng-Hua Cui Xin Xu Liang-Qing Zhang 《Chinese Journal of Polymer Science》 SCIE EI CAS CSCD 2026年第3期803-812,I0015,共10页
In this study,an architecture featuring a gradient conductive network structure and three-dimensional dual-continuous network structure is constructed in a carbon nanotubes/cellulose-boron nitride/poly(vinyl alcohol)(... In this study,an architecture featuring a gradient conductive network structure and three-dimensional dual-continuous network structure is constructed in a carbon nanotubes/cellulose-boron nitride/poly(vinyl alcohol)(CNT/cellulose-BN/PVA)composite.Using cellulose aerogel as a template,CNT were incorporated into the cellulose template by vertically impregnating the CNT suspension.Following the impregnation of BN/PVA and high-pressure compression,three-dimensional dual-continuous network structure was successfully constructed in the CNT/cellulose-BN/PVA composite.The comprehensive performance of the composite,including electromagnetic interference(EMI)shielding and Joule heating performance,was investigated.The results indicate that the total EMI shielding effectiveness(SE)for the CNT/cellulose-BN/PVA composite reveals similar values for electromagnetic waves incident from different directions,but totally different shielding mechanisms.For the CNT/cellulose-BN/PVA composite with three impregnation cycles of CNT,the EMI SE values exceeded 39 dB for electromagnetic waves incident from both the high-and low-CNT-content sides.93%of the microwaves were reflected when electromagnetic waves were incident from the high-CNT-content side,while the reflection coefficient decreased to 0.44 for the transverse direction.In addition,the construction of the dual-continuous network structure enabled the composite to exhibit both excellent electrical conductivity and good thermal conductivity simultaneously,endowing the material with good Joule heating performance.CNT/cellulose-BN/PVA composite films have significant potential for application as EMI shielding materials in extremely cold weather. 展开更多
关键词 Cellulose Dual-continuous network structure Gradient conductivity Electromagnetic interference shielding Joule heating
暂未订购 下载PDF
Training Robust Graph Completion Networks With Extremely Weak Supervision on Graphs With Incomplete Features and Structure 认领 引用
8
作者 Chengxiang Lei Sichao Fu +4 位作者 Qinmu Peng Yiyang Zhang Bin Zou Xiao-Yuan Jing Xinge You 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第7期1707-1720,共14页
Graph neural networks(GNNs)often suffer from performance degradation due to the incompleteness of node features and structure relationships in the real world.Recently emerged graph completion learning(GCL)enhances the... Graph neural networks(GNNs)often suffer from performance degradation due to the incompleteness of node features and structure relationships in the real world.Recently emerged graph completion learning(GCL)enhances the generalization of GNNs by reconstructing the missing node features or structure relationships.Nevertheless,these proposed GCL methods are supervised by a large number of labeled nodes,which limits their applications in extremely limited labeled nodes.Moreover,the existing GCL methods either focus on feature missing or structure missing tasks,and little effort was paid to more challenging scenarios where both node features and structure relationships are simultaneously missing.In this paper,a general GCL framework with the aid of multi-level contrast graph mask autoencoders(EWS-RGCN)is proposed to improve the generalization of GNNs guided by extremely weak supervision on graphs with features and structure missing.Specifically,to alleviate the mutual interference between missing node features and structure relationships caused by message passing of GNNs,we separate the feature and structure completion into two channels.Then,a multi-level contrastive loss is introduced to simultaneously maximize the mutual information between nodes from the encoding and decoding stage,which can discover more effective supervision information from the data itself for EWS-RGCN optimization,apart from label information.To further enhance the space consistency between reconstructed node features and structure relationships,the inter-channel information cooperation module is introduced to enhance the mutual learning of feature and structure completion channels.Extensive experiments on six benchmarks demonstrate the effectiveness of our EWS-RGCN. 展开更多
关键词 Extremely weak supervision features missing graph neural networks(GNNs) node classification structure missing
暂未订购 下载PDF
Spectral-Integrated Neural Networks for Transient Heat Conduction in Thin-Walled Structures 认领 引用
9
作者 Ting Gao Chengze Shang +1 位作者 Juan Wang Yan Gu 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第2期253-268,共16页
An efficient data-driven numerical framework is developed for transient heat conduction analysis in thin-walled structures.The proposed approach integrates spectral time discretization with neural network approximatio... An efficient data-driven numerical framework is developed for transient heat conduction analysis in thin-walled structures.The proposed approach integrates spectral time discretization with neural network approximation,forming a spectral-integrated neural network(SINN)scheme tailored for problems characterized by long-time evolution.Temporal derivatives are treated through a spectral integration strategy based on orthogonal polynomial expansions,which significantly alleviates stability constraints associated with conventional time-marching schemes.A fully connected neural network is employed to approximate the temperature-related variables,while governing equa-tions and boundary conditions are enforced through a physics-informed loss formulation.Numerical investigations demonstrate that the proposed method maintains high accuracy even when large time steps are adopted,where standard numerical solvers often suffer from instability or excessive computational cost.Moreover,the framework exhibits strong robustness for ultrathin configurations with extreme aspect ratios,achieving relative errors on the order of 10−5 or lower.These results indicate that the SINN framework provides a reliable and efficient alternative for transient thermal analysis of thin-walled structures under challenging computational conditions. 展开更多
关键词 Physics-informed neural networks spectral time integration transient heat conduction thin-walled structures
暂未订购 下载PDF
Intralayer structure reconstruction of general weighted output-coupling multilayer complex networks 认领 引用
10
作者 Xinwei Wang Yayong Wu +1 位作者 Ying Zheng Guo-Ping Jiang 《Chinese Physics B》 SCIE EI CAS CSCD 2026年第2期287-299,共13页
Multilayer complex dynamical networks,characterized by the intricate topological connections and diverse hierarchical structures,present significant challenges in determining complete structural configurations due to ... Multilayer complex dynamical networks,characterized by the intricate topological connections and diverse hierarchical structures,present significant challenges in determining complete structural configurations due to the unique functional attributes and interaction patterns inherent to different layers.This paper addresses the critical question of whether structural information from a known layer can be used to reconstruct the unknown intralayer structure of a target layer within general weighted output-coupling multilayer networks.Building upon the generalized synchronization principle,we propose an innovative reconstruction method that incorporates two essential components in the design of structure observers,the cross-layer coupling modulator and the structural divergence term.A key advantage of the proposed reconstruction method lies in its flexibility to freely designate both the unknown target layer and the known reference layer from the general weighted output-coupling multilayer network.The reduced dependency on full-state observability enables more deployment in engineering applications with partial measurements.Numerical simulations are conducted to validate the effectiveness of the proposed structure reconstruction method. 展开更多
关键词 multilayer network structure reconstruction cross-layer coupling modulator output coupling
暂未订购 下载PDF
Energy‑Based Physics‑Informed Neural Network for Linear Elastic Analysis of Multi‑patch Plate and Shell Structures 认领 引用
11
作者 GUO Boyu CHEN Yuhang +2 位作者 QIU Hao XU Xianhua GUO Yujie 《Transactions of Nanjing University of Aeronautics and Astronautics》 EI CSCD 2026年第3期463-474,共12页
Machine learning provides a fast and accurate tool for the prediction of a physical model.In this paper,a machine learning framework based on the physics-informed neural network(PINN)was established to predict the lin... Machine learning provides a fast and accurate tool for the prediction of a physical model.In this paper,a machine learning framework based on the physics-informed neural network(PINN)was established to predict the linear elastic static deformation of plate and shell structures.In contrast to the purely data-driven neural network,PINN incorporates the physical laws into the training process,thus reducing the required amount of data.The loss functions of the PINN are constructed based on the total potential energy functions of the thin-walled structure.Besides,the proposed PINN can be easily extended to shell structures with multiple patches by adding interface compatibility constraints into the loss function.The performance of the PINNs with the energy-based loss functions was evaluated with different shell structures and compared with the finite element results.Numerical examples show that the highly accurate results can be achieved based on the proposed framework which significantly reduces the amount of required training data compared to the data-driven neural network. 展开更多
关键词 physics-informed neural network(PINN) machine learning plate and shell structures total potential energy partial differential equations
暂未订购 下载PDF
Spatial morphology optimization for reconciling urban expansion with ecological integrity based on a multi-level ecological network framework 认领 引用 被引量：2
12
作者 LU Jie JIAO Sheng CHEN Xingli 《Journal of Geographical Sciences》 SCIE CSCD 2026年第2期399-420,共22页
Urban spatial morphology(USM)optimization is critical to balancing biodiversity conservation and sustainable urbanization.However,previous studies predominantly focused on the socio-economic efficiency and static ecol... Urban spatial morphology(USM)optimization is critical to balancing biodiversity conservation and sustainable urbanization.However,previous studies predominantly focused on the socio-economic efficiency and static ecological metrics and rarely addressed the dynamic USM optimization across spatial scales.Here,we developed a multi-level ecological network(MEN)framework to resolve the tension between urban expansion and ecological integrity.By integrating the cost-weighted distance analysis with a hierarchical network transmission mechanism,we established a cross-scale spatial optimization system,which coordinated the regional ecological corridors and local habitat patches.Comparative experiments with conventional single-scale approaches and scenario simulations using the PLUS model show that the MEN framework had superior performance in three dimensions:(1)spatial governance:the primary-level network(peri-urban natural reserves)effectively contained urban sprawl,and the secondary-level network(intra-urban green corridors)mitigated habitat fragmentation and improved the built-environment;(2)scenario robustness:the model maintained an optimal compactness-loose balance in multiple development pathways;(3)landscape metrics:patch fragmentation decreased by 18.25%,and the internal landscape richness improved by 10.66%compared to the scenario without USM optimization.The findings provide new insight to establish a hierarchical ecological optimization framework as a nature-based spatial protocol to reconcile metropolitan growth with landscape sustainability. 展开更多
关键词 urban spatial morphology ecological network multi-level coupling scenarios simulation urban expansion
暂未订购 下载PDF
Revealing the dominant influenceof joints:Soil-structurecomponent-joint adaptivity for prefabricated underground structures 认领 引用
13
作者 Tong Qiu Kaibin Ye +3 位作者 Xiangsheng Chen Tianjun Wu Wei Rao Xiaohua Bao 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2026年第7期5468-5488,共21页
Compared to the traditional cast-in-situ technique,the novel prefabricated underground structure(PUS)employs machinery excavation and assembly.Notably,the PUS assembly system undergoes multi-level force transmission t... Compared to the traditional cast-in-situ technique,the novel prefabricated underground structure(PUS)employs machinery excavation and assembly.Notably,the PUS assembly system undergoes multi-level force transmission through soil,structure,component,and joint interactions.This transmission mechanism remains inadequately understood,consequently posing frequent instability risks during PUS construction.Hereby,this study foremost addresses this problem for multi-level information modeling and planning for PUS under joint principal control.Three modules of numerical modeling,design theory and adaptive planning were constructed and integrated into the Soil-structure-component-joint Adaptive Planning Model(SAPM).Through a real-project application of SAPM,key insights are as follows:(1)SAPM achieves multi-level information adaptivity by planning the joint properties,which mitigates the soil-structure interaction effect of main and secondary structures by 18% and 63%,respectively.(2)Different joints and components may not achieve optimum solutions with uniform joint properties.Top,bottom and midslab joints achieve multi-level information adaptivity only when their respective joint stiffness factors are 0.90,0.61 and 0.65.(3)The use of semi-rigid joints in PUS has multiple advantages over the common cast-in-situ rigid joints.The semi-rigid scheme reduces ring assembly time and cost by approximately 40%and 20%,respectively,compared to hinged and rigid joint schemes.The research results provide a theoretical and instrumental basis for the safe construction of PUS in complex urban and geotechnical environments. 展开更多
关键词 Prefabricated underground structures Soil-structure-component-joint adaptivity Multi-level information planning Automatic modeling Semi-rigid joint
暂未订购 下载PDF
An enhanced ecological network for spatial planning considering spatial conflicts and structural resilience 认领 引用
14
作者 Haowei Mu Shanchuan Guo +6 位作者 Xingang Zhang Bo Yuan Xiaoquan Pan Zilong Xia Xin Pan Shangwu Zhang Peijun Du 《Geography and Sustainability》 CSCD 2026年第2期116-128,共13页
The digital transformation of territorial spatial planning has underscored the urgent need to integrate ecological network into spatial planning practices.In response,we developed two innovative new tools,the Ecologic... The digital transformation of territorial spatial planning has underscored the urgent need to integrate ecological network into spatial planning practices.In response,we developed two innovative new tools,the Ecological Linkage Tool(ELT)and the Relative Spatial Conflict Index(RSCI),to enhance ecological networks applications by addressing spatial conflicts and structural resilience.The ELT identified ecological corridors within and outside irregular ecological sources,activation points,and stepping stones in parallel,and then constructed an intact ecological network.By integrating the RSCI and complex network metrics,the spatial conflicts and structural resilience were evaluated.The framework was implemented in the Hohhot-Baotou-Ordos-Yulin(HBOY)urban agglomeration,identifying a total of 5,814 corridors,of which 67%were classified as intra-patch and 33%as inter-patch.The number and distribution of these corridors were determined by the size and shape of the ecological sources,and the connectivity of intra-patch corridors was 34%higher than inter-patch corridors.According to the RSCI,60%of the corridors experienced spatial conflicts,with 21%involving production spaces or composite production-related conflicts.Moreover,Yulin served as a key hub in the ecological network,and Baotou had the highest network efficiency.Compound conflict corridors(involving production,living,and open spaces)had a greater impact on overall ecological network efficiency compared to those with single or dual conflicts.Meanwhile,the failure of 40%of corridors without spatial conflicts would directly result in a 96.9%decline in network efficiency,highlighting their critical role in maintaining network functionality.This study provides an enhanced ecological network application solution for the China Spatial Planning Observation Network(CSPON),supporting spatial planning practices. 展开更多
关键词 Ecological network Ecological corridor Spatial conflict Structural resilience Spatial planning
暂未订购 下载PDF
Hot-Ham:an Accurate and Efficient E(3)-Equivariant Machine-Learning Electronic Structures Calculation Framework 认领 引用
15
作者 Zhixin Liang Yunlong Wang +4 位作者 Chi Ding Junjie Wang Hui-Tian Wang Dingyu Xing Jian Sun 《Chinese Physics Letters》 SCIE EI CAS CSCD 2026年第2期149-166,共18页
The combinations of machine learning with ab initio methods have attracted much attention for their potential to resolve the accuracy-efficiency dilemma and facilitate calculations for large-scale systems.Recently,equ... The combinations of machine learning with ab initio methods have attracted much attention for their potential to resolve the accuracy-efficiency dilemma and facilitate calculations for large-scale systems.Recently,equivariant message passing neural networks(MPNNs)that explicitly incorporate symmetry constraints have demonstrated promise for interatomic potential and density functional theory(DFT)Hamiltonian predictions.However,the high-order tensors used to represent node and edge information are coupled through the Clebsch–Gordan tensor product,leading to steep increases in computational complexity and seriously hindering the performance of equivariant MPNNs.Here,we develop high-order tensor machine-learning Hamiltonian(Hot-Ham),an E(3)equivariant MPNN framework that combines two advanced technologies:local coordinate transformation and Gaunt tensor product to efficiently model DFT Hamiltonians.These two innovations significantly reduce the complexity of tensor products from O(L6)to O(L3)or O(L2log2L)for the max tensor order L,and enhance the performance of MPNNs.Benchmarks on several public datasets demonstrate its state-of-the-art accuracy with relatively few parameters,and applications to multilayer twisted moire systems,heterostructures,and allotropes showcase its generalization ability and high efficiency.Our Hot-Ham method provides a new perspective for developing efficient equivariant neural networks and would be a promising approach for investigating the electronic properties of large-scale materials systems. 展开更多
关键词 equivariant neural networks symmetry constraints message passing neural networks mpnns high order tensors machine learning ab initio methods density functional electronic structure calculations
暂未订购 下载PDF
Reconstruction of bridge‑sensor data and detection of structural damage based on gradient‑coupled autoencoder and fully connected network 认领 引用
16
作者 DUAN Yuanfeng DING Pengyao +1 位作者 DUAN Zhengteng CHENG J.J.Roger 《Journal of Southeast University(English Edition)》 EI CAS 2026年第1期1-11,共11页
A dual‑task parallel machine learning framework was developed by integrating a convolutional autoencoder(CAE)and a fully connected neural network(FCNN)via the gradient‑coupled mechanism,enabling simultaneous data comp... A dual‑task parallel machine learning framework was developed by integrating a convolutional autoencoder(CAE)and a fully connected neural network(FCNN)via the gradient‑coupled mechanism,enabling simultaneous data compression‑reconstruction and structural damage identification.Under the condition where 40% of the sensor nodes are missing,the model successfully reconstructs the full sensor network with an R2 of 0.916 and normalized root mean square error(NRMSE)of 0.0288.Even under significant noise contamination with an SNR of 12 dB,the model maintains strong reconstruction performance,achieving a R2 of 0.910 and NRMSE of 0.0253.Forty‑six structural damage scenarios were simulated using the scaled bridge model.The accuracy of spatial localization and quantification of the damage severity using the framework exceeds 99.3%.The proposed framework reduces the training time by 54.4%and iteration counts by 45.5% compared to conventional two‑stage machine learning approaches,demonstrating the efficiency of gradient‑coupled optimization. 展开更多
关键词 structural health monitoring machine learning data compression damage identification convolutional neural network fully connected neural network gradient‑coupled mechanism
暂未订购 下载PDF
Topological Structure Evolution of Polymer Network Based on Star-shaped Multi-armed Precursors 认领 引用 被引量：1
17
作者 Hui Li Zi-Jian Xue +2 位作者 Yao-Hong Xue Yingxiang Li Hong Liu 《Chinese Journal of Polymer Science》 SCIE EI CAS CSCD 2025年第7期1240-1252,共13页
The performance of polymer networks is directly determined by their structure.Understanding the network structure offers insights into optimizing material performance,such as elasticity,toughness,and swelling behavior... The performance of polymer networks is directly determined by their structure.Understanding the network structure offers insights into optimizing material performance,such as elasticity,toughness,and swelling behavior.Herein,in this study we introduce the Dijkstra algorithm from graph theory to characterize polymer networks based on star-shaped multi-armed precursors by employing coarse-grained molecular dynamics simulations coupled with stochastic reaction model.Our research focuses on the structure characteristics of the generated networks,including the number and size of loops,as well as network dispersity characterized by loops.Tracking the number of loops during network generation allows for the identification of the gel point.The size distribution of loops in the network is primarily related to the functionality of the precursors,and the system with fewer precursor arms exhibiting larger average loop sizes.Strain-stress curves indicate that materials with identical functionality and precursor arm lengths generally exhibit superior performance.This method of characterizing network structures helps to refine microscopic structural analysis and contributes to the enhancement and optimization of material properties. 展开更多
关键词 Polymer network Topological structure Dijkstra algorithm Molecular dynamics
暂未订购 下载PDF
Pore structure properties characterization of shale using generative adversarial network:Image augmentation,super-resolution reconstruction,and multi-mineral auto-segmentation 认领 引用 被引量：1
18
作者 LIU Fugui YANG Yongfei +7 位作者 YANG Haiyuan TAO Liu TAO Yunwei ZHANG Kai SUN Hai ZHANG Lei ZHONG Junjie YAO Jun 《Petroleum Exploration and Development》 SCIE 2025年第5期1262-1274,共13页
Existing imaging techniques cannot simultaneously achieve high resolution and a wide field of view,and manual multi-mineral segmentation in shale lacks precision.To address these limitations,we propose a comprehensive... Existing imaging techniques cannot simultaneously achieve high resolution and a wide field of view,and manual multi-mineral segmentation in shale lacks precision.To address these limitations,we propose a comprehensive framework based on generative adversarial network(GAN)for characterizing pore structure properties of shale,which incorporates image augmentation,super-resolution reconstruction,and multi-mineral auto-segmentation.Using real 2D and 3D shale images,the framework was assessed through correlation function,entropy,porosity,pore size distribution,and permeability.The application results show that this framework enables the enhancement of 3D low-resolution digital cores by a scale factor of 8,without paired shale images,effectively reconstructing the unresolved fine-scale pores under a low resolution,rather than merely denoising,deblurring,and edge clarification.The trained GAN-based segmentation model effectively improves manual multi-mineral segmentation results,resulting in a strong resemblance to real samples in terms of pore size distribution and permeability.This framework significantly improves the characterization of complex shale microstructures and can be expanded to other heterogeneous porous media,such as carbonate,coal,and tight sandstone reservoirs. 展开更多
关键词 shale pore structure parameter generative adversarial network super-resolution multi-mineral auto-segmentation multiscale fusion
暂未订购 下载PDF
Improved resistance to creep and underlying mechanisms in TiB/(TA15−Si)composites with network structure 认领 引用
19
作者 Shuai WANG Rui ZHANG +5 位作者 Ming JI Feng-bo SUN Zi-shuo MA Qi AN Lu-jun HUANG Lin GENG 《Transactions of Nonferrous Metals Society of China》 SCIE EI CAS CSCD 2025年第10期3357-3367,共11页
To assess the high-temperature creep properties of titanium matrix composites for aircraft skin,the TA15 alloy,TiB/TA15 and TiB/(TA15−Si)composites with network structure were fabricated using low-energy milling and v... To assess the high-temperature creep properties of titanium matrix composites for aircraft skin,the TA15 alloy,TiB/TA15 and TiB/(TA15−Si)composites with network structure were fabricated using low-energy milling and vacuum hot pressing sintering techniques.The results show that introducing TiB and Si can reduce the steady-state creep rate by an order of magnitude at 600℃ compared to the alloy.However,the beneficial effect of Si can be maintained at 700℃ while the positive effect of TiB gradually diminishes due to the pores near TiB and interface debonding.The creep deformation mechanism of the as-sintered TiB/(TA15−Si)composite is primarily governed by dislocation climbing.The high creep resistance at 600℃ can be mainly attributed to the absence of grain boundaryαphases,load transfer by TiB whisker,and the hindrance of dislocation movement by silicides.The low steady-state creep rate at 700℃ is mainly resulted from the elimination of grain boundaryαphases as well as increased dynamic precipitation of silicides andα2. 展开更多
关键词 discontinueously reinforced titanium matrix composite TiB whisker network structure silicides creep properties
暂未订购 下载PDF
Prevalence and network structure of depression and its association with quality of life among older stroke survivors:findings from a national survey in China 认领 引用
20
作者 Mu-Rui Zheng Pan Chen +7 位作者 Ling Zhang Yuan Feng Teris Cheung Nicole Xun Xiang Gabor S Ungvari Qinge Zhang Chee H Ng Yu-Tao Xiang 《General Psychiatry》 CAS CSCD 2025年第2期82-92,共11页
Background Post-stroke depression(PSD)is a common neuropsychiatric problem associated with a high disease burden and reduced quality of life(QoL).To date,few studies have examined the network structure of depressive s... Background Post-stroke depression(PSD)is a common neuropsychiatric problem associated with a high disease burden and reduced quality of life(QoL).To date,few studies have examined the network structure of depressive symptoms and their relationships with QoL in stroke survivors.Aims This study aimed to explore the network structure of depressive symptoms in PSD and investigate the interrelationships between specific depressive symptoms and QoL among older stroke survivors.Methods This study was based on the 2017–2018 collection of data from a large national survey in China.Depressive symptoms were assessed using the 10-item Centre for Epidemiological Studies Depression Scale(CESD),while QoL was measured with the World Health Organization Quality of Life-brief version.Network analysis was employed to explore the structure of PSD,using expected influence(EI)to identify the most central symptoms and the flow function to investigate the association between depressive symptoms and QoL.Results A total of 1123 stroke survivors were included,with an overall prevalence of depression of 34.3%(n=385;95%confidence interval 31.5%to 37.2%).In the network model of depression,the most central symptoms were CESD3(‘feeling blue/depressed’,EI:1.180),CESD6(‘feeling nervous/fearful’,EI:0.864)and CESD8(‘loneliness’,EI:0.843).In addition,CESD5(‘hopelessness’,EI:−0.195),CESD10(‘sleep disturbances’,EI:−0.169)and CESD4(‘everything was an effort’,EI:−0.150)had strong negative associations with QoL.Conclusion This study found that PSD was common among older Chinese stroke survivors.Given its negative impact on QoL,appropriate interventions targeting central symptoms and those associated with QoL should be developed and implemented for stroke survivors with PSD. 展开更多
关键词 prevalence stroke survivors neuropsychiatric problem China depression quality life depressive symptoms network structure depressive symptoms
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈