检索结果-南通市图书馆

Cross-Dimension Attentive Feature Fusion Network for Unsupervised Time-Series Anomaly Detection

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第6期139卷 3011-3027页

作者： Rui Wang yao Zhou Guangchun luo Peng Chen Dezhong Peng School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China School of Computer and Software Engineering Xihua UniversityChengdu610039China School of Computer Science Sichuan UniversityChengdu610065China National Innovation Center for UHD Video Technology Chengdu610095China

Time series anomaly detection is crucial in various industrial applications to identify unusual behaviors within the time series *** to the challenges associated with annotating anomaly events,time series reconstruction has become a prevalent approach for unsupervised anomaly ***,effectively learning representations and achieving accurate detection results remain challenging due to the intricate temporal patterns and dependencies in real-world time *** this paper,we propose a cross-dimension attentive feature fusion network for time series anomaly detection,referred to as ***,a series and feature mixing block is introduced to learn representations in 1D ***,a fast Fourier transform is employed to convert the time series into 2D space,providing the capability for 2D feature ***,a cross-dimension attentive feature fusion mechanism is designed that adaptively integrates features across different dimensions for anomaly *** results on real-world time series datasets demonstrate that CAFFN performs better than other competing methods in time series anomaly detection.

关键词： Time series anomaly detection unsupervised feature learning feature fusion

Finite particle method for kinematically indeterminate bar assemblies

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 Zhejiang University-Science A(Applied Physics & Engineering) 2009年第5期10卷 669-676页

作者： Ying YU yao-zhi luo Space Structures Research Center Zhejiang University Hangzhou 310058 China

This study presents a structural analysis algorithm called the finite particle method （FPM） for kinematically indeterminate bar assemblies. Different from the traditional analysis method, FPM is based on the combination of the vector mechanics and numerical calculations. It models the analyzed domain composed of finite particles. Newton＇s second law is adopted to describe the motions of all particles. A convected material flame and explicit time integration for the solution procedure is also adopted in this method. By using the FPM, there is no need to solve any nonlinear equations, to calculate the stiffness matrix or equilibrium matrix, which is very helpful in the analysis of kinematically indeterminate structures. The basic formulations for the space bar are derived, following its solution procedures for bar assemblies. Three numerical examples are analyzed using the FPM. Results obtained from both the straight pretension cable and the suspension cable assembly show that the FPM can produce a more accurate analysis result. The motion simulation of the four-bar space assembly demonstrates the capability of this method in the analysis ofkinematically indeterminate structures.

关键词： Finite particle method (FPM) Vector mechanics Convected material frame Explicit time integrations Kinematicallyindeterminate bar assemblies

Multi-Material Topology Optimization of 2D Structures Using Convolutional Neural Networks

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第8期140卷 1919-1947页

作者： Jiaxiang luo Weien Zhou Bingxiao Du Daokui Li Wen yao College of Aerospace Science and Engineering National University of Defense TechnologyChangsha410073China Defense Innovation Institute Chinese Academy of Military ScienceBeijing100071China Intelligent Game and Decision Laboratory Chinese Academy of Military ScienceBeijing100071China

In recent years,there has been significant research on the application of deep learning(DL)in topology optimization(TO)to accelerate structural ***,these methods have primarily focused on solving binary TO problems,and effective solutions for multi-material topology optimization(MMTO)which requires a lot of computing resources are still ***,this paper proposes the framework of multiphase topology optimization using deep learning to accelerate MMTO *** framework employs convolutional neural network(CNN)to construct a surrogate model for solving MMTO,and the obtained surrogate model can rapidly generate multi-material structure topologies in negligible time without any *** performance evaluation results show that the proposed method not only outputs multi-material topologies with clear material boundary but also reduces the calculation cost with high prediction ***,in order to find a more reasonable modeling method for MMTO,this paper studies the characteristics of surrogate modeling as regression task and classification *** the training of 297 models,our findings show that the regression task yields slightly better results than the classification task in most ***,The results indicate that the prediction accuracy is primarily influenced by factors such as the TO problem,material category,and data ***,factors such as the domain size and the material property have minimal impact on the accuracy.

关键词： Multi-material topology optimization convolutional neural networks deep learning finite element analysis

“La relación del Perú con China la considero como un modelo”

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

今日中国（西文版） 2023年第9期 48-50页

作者： luo yao

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Lost in the Stars

今日中国（西文版） 2023年第8期 70-71页

作者： luo yao

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Moscow Mission

今日中国（西文版） 2023年第11期 70-71页

作者： luo yao

La trascendencia del pop hongkones

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

今日中国（西文版） 2022年第7期 38-39页

作者： luo yao 不详

Impact of Initial Soil Conditions on Soil Hydrothermal and Surface Energy Fluxes in the Permafrost Region of the Tibetan Plateau

维普期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2024年第4期41卷 717-736页

作者： Siqiong luo Zihang CHEN Jingyuan WANG Tonghua WU yao XIAO Yongping QIAO Key Laboratory of Land Surface Process and Climate Change in Cold and Arid Regions Northwest Institute of Eco-Environment and ResourcesChinese Academy of SciencesLanzhou 730000China University of Chinese Academy of Sciences Beijing 100049China Cryosphere Research Station on the Qinghai-Tibet Plateau State Key Laboratory of Cryospheric ScienceNorthwest Institute of Eco-Environment and ResourcesChinese Academy of SciencesLanzhou 730000China

Accurate initial soil conditions play a crucial role in simulating soil hydrothermal and surface energy fluxes in land surface process *** study emphasized the influence of the initial soil temperature(ST)and soil moisture(SM)conditions on a land surface energy and water simulation in the permafrost region in the Tibetan Plateau(TP)using the Community Land Model version 5.0(CLM5.0).The results indicate that the default initial schemes for ST and SM in CLM5.0 were simplistic,and inaccurately represented the soil characteristics of permafrost in the TP which led to underestimating ST during the freezing period while overestimating ST and underestimating SLW during the thawing period at the XDT *** the long-term spin-up method to obtain initial soil conditions has only led to limited improvement in simulating soil hydrothermal and surface energy *** modified initial soil schemes proposed in this study comprehensively incorporate the characteristics of permafrost,which coexists with soil liquid water(SLW),and soil ice(SI)when the ST is below freezing temperature,effectively enhancing the accuracy of the simulated soil hydrothermal and surface energy ***,the modified initial soil schemes greatly improved upon the results achieved through the long-term spin-up *** modified initial soil schemes experiments resulted in a 64%,88%,and 77%reduction in the average mean bias error(MBE)of ST,and a 13%,21%,and 19%reduction in the average root-mean-square error(RMSE)of SLW compared to the default simulation ***,the average MBE of net radiation was reduced by 7%,22%,and 21%.

关键词： initial soil conditions soil temperature soil liquid water soil ice surface energy fluxes permafrost

Experimental study on temperature fluctuations on plate surface induced by coaxial-jet flow

在线全文

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第5期35卷 139-153页

作者： Xue-yao Xiong Zun-Quan Liu Guo-Yan Zhou Xing luo Shan-Tung Tu Key Laboratory of Pressure Systems and Safety(MOE) East China University of Science and TechnologyShanghai 200237China Institute of Thermodynamics Gottfried Wilhelm Leibniz University Hannover30823 GarbsenGermany

In nuclear reactors,temperature fluctuations of fluids may cause fatigue damage to adjacent structures;this is referred to as thermal *** on thermal striping in the upper plenum has mainly focused on fluid *** experimental studies have been reported on solid structures in a fluid field with a coaxial *** study entailed an experimental study of the temperature fluctuations in the fluid and on a plate surface caused by a coaxial *** temperature fluctuations of the fluid and plate surfaces located at different heights were *** cause of the temperature fluctuation was analyzed using a transient temperature *** results show that the mixing of the hot and cold fluids gradually becomes uniform in the positive axial *** average surface temperatures tended to be *** the jet reaches the plate surface,the swing of the jet center,contraction and expansion of the cold jet,and changes in the jet shape result in temperature *** intensity of the temperature fluctuation was affected by the *** attention should be paid when the plate is located at a lower height,and between the hot and cold-fluid nozzles.

关键词： Temperature fluctuation Thermal striping Coaxial jet Thermal mixing The upper plenum of nuclear reactor