检索结果-南通市图书馆

A Two-Layer Encoding Learning Swarm Optimizer Based on Frequent Itemsets for Sparse Large-Scale Multi-Objective Optimization

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1342-1357页

作者： Sheng Qi rui wang Tao Zhang xu Yang ruiqing Sun Ling wang College of systems Engineering National University of Defense TechnologyChangsha 410073China Xiangjiang Laboratory Changsha 410205China College of Computer National University of Defense TechnologyChangsha 410073China Department of Automation Tsinghua UniversityBeijing 100084China IEEE

Traditional large-scale multi-objective optimization algorithms(LSMOEAs)encounter difficulties when dealing with sparse large-scale multi-objective optimization problems(SLM-OPs)where most decision variables are *** a result,many algorithms use a two-layer encoding approach to optimize binary variable Mask and real variable Dec ***,existing optimizers often focus on locating non-zero variable posi-tions to optimize the binary variables ***,approxi-mating the sparse distribution of real Pareto optimal solutions does not necessarily mean that the objective function is *** data mining,it is common to mine frequent itemsets appear-ing together in a dataset to reveal the correlation between *** by this,we propose a novel two-layer encoding learning swarm optimizer based on frequent itemsets(TELSO)to address these *** mined the frequent terms of multiple particles with better target values to find mask combinations that can obtain better objective values for fast ***-mental results on five real-world problems and eight benchmark sets demonstrate that TELSO outperforms existing state-of-the-art sparse large-scale multi-objective evolutionary algorithms(SLMOEAs)in terms of performance and convergence speed.

关键词： Evolutionary algorithms learning swarm optimiza-tion sparse large-scale optimization sparse large-scale multi-objec-tive problems two-layer encoding.

Learning to Branch in Combinatorial Optimization With Graph Pointer Networks

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 157-169页

作者： rui wang Zhiming Zhou Kaiwen Li Tao Zhang Ling wang Xin xu Xiangke Liao IEEE the Xiangjiang Laboratory and the College of systems Engineering National University of Defense TechnologyChangsha 410073China the Institute of Automation Chinese Academy of SciencesBeijing 100190China the College of systems Engineering National University of Defense TechnologyChangsha 410073 the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha 410073China the Department of Automation Tsinghua UniversityBeijing 100084China the College of Intelligence science and Technology National University of Defense TechnologyChangsha 410073China the College of Computer science and Technology National University of Defense TechnologyChangsha 410073China

Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex *** the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

关键词： Branch-and-bound(B&B) combinatorial optimization deep learning graph neural network imitation learning

Decohesion of graphene from a uniaxially-stretched substrate:Failure analysis of a frictional adhesive interface

在线全文

学校读者我要写书评

暂无评论

Friction 2024年第3期12卷 510-521页

作者： bo PENG Chaochen xu Qingao wang Pei ZHAO Xiqiao FENG Qunyang LI AML Department of Engineering MechanicsTsinghua UniversityBeijing 100084China State Key Laboratory of Tribology in Advanced Equipment Tsinghua UniversityBeijing 100084China Center for X-Mechanics and Institute of Applied Mechanics Zhejiang UniversityHangzhou 310027China State Key Laboratory of Fluid Power and M

Composite structures consisting of two-dimensional(2D)materials deposited on elastic substrates have a wide range of potential applications in flexible *** such devices,robust 2D film/substrate interfacial adhesion is essential for their reliable performance when subjected to external thermal and mechanical *** better understand the strength and failure behavior of the 2D film/substrate interfaces,two types of graphene/polymer samples with distinct interfacial adhesion properties are fabricated and tested by uniaxially stretching the *** on the interfacial adhesion,two drastically different debonding rates are observed,i.e.,rapid snap-through debonding and more progressive crack *** by the experimental observation,we propose an improved shear-lag model with a trapezoidal-shaped cohesive zone to derive an analytical solution for the decohesion *** theoretical model reveals that the decohesion behavior of the frictional adhesive interface is governed by three dimensionless ***,the dimensionless length of the film essentially determines the decohesion rate;while the other two parameters affect the critical substrate strain to initiate *** fitting the experimental data with the theoretical model,the intrinsic adhesion properties of the two samples are obtained with physically meaningful *** work offers an analytical solution to describing the decohesion behavior of general thin film/substrate systems with a frictional adhesive interface,which is beneficial for characterizing and optimizing the mechanical properties of various thin film/polymer devices.

关键词： film/substrate systems adhesion frictional sliding interface decohesion cohesive-zone model

Enhancing Multi-agent Coordination via Dual-channel Consensus

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第2期21卷 349-368页

作者： Qingyang Zhang Kaishen wang Jingqing Ruan Yiming Yang Dengpeng Xing bo xu Institute of Automation Chinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China

Successful coordination in multi-agent systems requires agents to achieve *** works propose methods through information sharing,such as explicit information sharing via communication protocols or exchanging information implicitly via behavior ***,these methods may fail in the absence of communication channels or due to biased *** this work,we propose to develop dual-channel consensus(DuCC)via contrastive representation learning for fully cooperative multi-agent systems,which does not need explicit communication and avoids biased *** comprises two types of consensus:temporally extended consensus within each agent(inner-agent consensus)and mutual consensus across agents(inter-agent consensus).To achieve DuCC,we design two objectives to learn representations of slow environmental features for inner-agent consensus and to realize cognitive consistency as inter-agent *** DuCC is highly general and can be flexibly combined with various MARL *** extensive experiments on StarCraft multi-agent challenge and Google research football demonstrate that our method efficiently reaches consensus and performs superiorly to state-of-the-art MARL algorithms.

关键词： Multi-agent reinforcement learning contrastive representation learning consensus multi-agent cooperation cognitive consistency

Large-aperture Telescope Tracking Control Based on Time-synchronization Strategy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2024年第3期24卷 34-46页

作者： Yun Li Yu Ye Shi-Hai Yang Ling-Zhe xu Jin xu Hai wang Zhuang-Zhuang Deng rui-Qiang Liu Xiao-Jie Gu bo-Zhong Gu Nanjing Institute of Astronomical Optics&Technology Chinese Academy of SciencesNanjing 210042China CAS Key Laboratory of Astronomical Optics&Technology Nanjing Institute of Astronomical Optics&TechnologyNanjing 210042China University of chinese academy of sciences Beijing 100049China

A time-synchronization strategy for packetized transmission of target position about a large-aperture telescope observation control system has been proposed in this *** with the existing telescope tracking strategy,the target position packing and sending strategy based on the time synchronization method proposed in this paper has the advantages of high stability and ***,the telescope tracking observation control method was elaborated in this paper,including the motion pattern during telescope ***,the strategy for packetizes transmission of target positions based on time-synchronization is established and lists the detailed ***,the performance of the tracking strategy is verified using the 2.5 m telescope for the simulated uniform speed star and the blind-tracking fixed star HIP 31216,*** test results show that the accuracy root mean square of the tracking strategy proposed in this paper is less than 0".02 at 30 minutes,and the performance is much better than the design requirement of 0".*** most important advantage of this tracking strategy is that the telescope can guarantee normal tracking for a certain period of time even if the hardware or software of the host computer is abnormal.

关键词： miscellaneous-telescopes-methods observational-methods analytical

Impact Analysis of Microscopic Defect Types on the Macroscopic Crack Propagation in Sintered Silver Nanoparticles

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4期139卷 441-458页

作者： Zhongqing Zhang bo Wan Guicui Fu Yutai Su Zhaoxi Wu Xiangfen wang xu Long School of Reliability and systems Engineering Beihang UniversityBeijing100191China School of Mechanics Civil Engineering and ArchitectureNorthwestern Polytechnical UniversityXi’an710072China china Aerospace Components Engineering Center Beijing100098China

Sintered silver nanoparticles(AgNPs)arewidely used in high-power electronics due to their exceptional ***,the material reliability is significantly affected by various microscopic *** this work,the three primary micro-defect types at potential stress concentrations in sintered AgNPs are identified,categorized,and *** dynamics(MD)simulations are employed to observe the failure evolution of different microscopic *** dominant mechanisms responsible for this evolution are dislocation nucleation and dislocation *** the same time,this paper clarifies the quantitative relationship between the tensile strain amount and the failure mechanism transitions of the three defect types by defining key strain *** impact of defect types on the failure process is also ***,traction-separation curves extracted from microscopic defect evolutions serve as a bridge to connect the macro-scale *** validity of the crack propagation model is confirmed through tensile ***,we thoroughly analyze how micro-defect types influence macro-crack propagation and attempt to find supporting evidence from the MD *** findings provide a multi-perspective reference for the reliability analysis of sintered AgNPs.

关键词： Sintered silver nanoparticles defect types microscopic defect evolution macroscopic crack propagation molecular dynamics simulation cohesive zone model

Tuning electronic properties of cobalt phthalocyanines for oxygen reduction and evolution reactions

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science china Chemistry 2024年第1期67卷 398-407页

作者： Jianlin Jiang Zhen Liu Shuaijun Pan Xinnian Xia Bing Qin Yang Hu xuxu wang Jiamin Lan Yu Gu Encai Ou Weijian xu Joseph J.Richardson rui Guo SINOPEC Research Institute of Petroleum Processing Co. Ltd.Beijing 100083China College of Chemistry and Chemical Engineering Hunan UniversityChangsha 410082China College of Chemistry and Materials science Hunan Agricultural UniversityChangsha 410128China Department of Chemical Engineering The University of MelbourneParkville 3010Australia College of Environmental science and Engineering Hunan UniversityChangsha 410082China School of Engineering RMIT UniversityMelbourneVictoria 3001Australia

Metal–phthalocyanines are a class of catalytically active materials promising in energy conversion and storage fields(e.g.,electrocatalysis).However,understanding and controlling the electrochemical properties in metal-phthalocyanine systems is ***,we elucidate the electrocatalytic origins of a series of cobalt-phthalocyanine molecular catalysts and finetune their electronic properties at the atomic level,both experimentally and *** interactions between the cobalt center and the local coordination environment are regulated by introducing either electron-donating or electron-withdrawing groups on the phthalocyanine ligand,and the spin-orbit splitting of cobalt is increased by~0.15 eV compared with the nonsubstituted ***,the aminated cobalt phthalocyanine-based electrocatalysts exhibit low free energies in the ratedetermining steps of the oxygen reduction(-1.68 eV)and oxygen evolution reactions(0.37 eV).This contributes to the high electrocatalytic activity(e.g.,a halfwave potential of 0.84 V and an overpotential of 0.30 V at 10 mAcm^(-2)),featuring a high selectivity of a four-electron pathway(i.e.,a negligible by-product of hydrogen peroxide).These catalysts also exhibit exceptional kinetic current density(Tafel slope of 100 mV dec^(-1))in oxygen reduction reactions,in addition to a superior power density(158 mWcm^(-2))and a high cycling stability(>1,300 cycles)in Zn-air batteries,outperforming the commercial Pt/C and/or RuO2counterparts.

关键词： interfacial wettability molecular catalysts carbon nanotubes density functional theory electrochemistry

Superhydrophobic melamine sponge prepared by radiation-induced grafting technology for efficient oil-water separation

在线全文

学校读者我要写书评

暂无评论

Nuclear science and Techniques 2024年第9期35卷 103-114页

作者： Ying Sun Wen-rui wang Dan-Yi Li Si-Yi xu Lin Lin Man-Li Lu Kai Fan Chen-Yang Xing Lin-Fan Li Ji-Hao Li Shanghai Institute of Applied Physics Chinese Academy of SciencesShanghai 201800China University of chinese academy of sciences Beijing 100049China School of Architecture and Materials Chongqing College of Electronic EngineeringChongqing 401331China Center for Stretchable Electronics and NanoSensors Key Laboratory of Optoelectronic Devices and Systems of Ministry of EducationCollege of Physics and Optoelectronic EngineeringShenzhen UniversityShenzhen 518060China

This paper presents a superhydrophobic melamine(ME)sponge(ME-g-PLMA)prepared via high-energy radiation-induced in situ covalent grafting of long-alkyl-chain dodecyl methacrylate(LMA)onto an ME sponge for efficient oil–water *** obtained ME-g-PLMA sponge had an excellent pore structure with superhydrophobic(water contact angle of 154°)and superoleophilic *** can absorb various types of oils up to 66–168 times its *** ME-g-PLMA sponge can continuously separate oil slicks in water by connecting a pump or separating oil underwater with a gravity-driven *** addition,it maintained its highly hydrophobic properties even after long-term immersion in different corrosive solutions and repeated oil *** modified ME-g-PLMA sponge exhibited excellent separation properties and potential for oil spill cleanup.

关键词： Radiation-induced graft polymerization Oil–water separation Sponge Superhydrophobic

Genome assembly of autotetraploid Actinidia arguta highlights adaptive evolution and enables dissection of important economic traits

在线全文

学校读者我要写书评

暂无评论

Plant Communications 2024年第6期5卷 173-192页

作者： xue-Mei Lu Xiao-Fen Yu Guo-Qiang Li Ming-Hao Qu Huan wang Chuang Liu Yu-Ping Man Xiao-Han Jiang Mu-Zi Li Jian wang Qi-Qi Chen rui Lei Cheng-Cheng Zhao Yun-Qiu Zhou Zheng-wang Jiang Zuo-Zhou Li Shang Zheng Chang Dong Bai-Lin wang Yan-Xiang Sun Hui-Qin Zhang Jie-Wei Li Quan-Hui Mo Ying Zhang Xin Lou Hai-xu Peng Ya-Ting Yi He-Xin wang Xiu-Jun Zhang Yi-bo wang Dan wang Li Li Qiong Zhang Wen-Xia wang Yongbo Liu Lei Gao Jin-Hu Wu Yan-Chang wang CAS Key Laboratory of Plant Germplasm Enhancement and Specialty Agriculture Wuhan Botanical GardenChinese Academy of SciencesWuhanHubeiChina Key Laboratory of Western china’s Environmental systems(Ministry of Education) College of Earth and Environmental SciencesLanzhou UniversityLanzhouGansuChina College of Life sciences University of Chinese Academy of SciencesBeijingChina Wuhan Frasergen Bioinformatics Co. LtdWuhanHubeiChina Institute of Soil and Fertilizer Anhui Academy of Agricultural SciencesHefeiChina College of Agricultural sciences Xichang UniversityXichangSichuanChina Department of Horticulture Heilongjiang Academy of Agricultural SciencesHarbinHeilongjiangChina College of Life sciences Langfang Normal UniversityLangfangHebeiChina Institute of Horticulture Zhejiang Academy of Agricultural SciencesHangzhouZhejiangChina Guangxi Institute of botany Chinese Academy of SciencesGuilinGuangxiChina Xi’an botanical Garden of Shaanxi Province Institute of Botany of Shaanxi ProvinceXi’anShaanxiChina Institute of Modern Agricultural Research Dalian UniversityDalianLiaoningChina Bioinformatics Center College of Plant Science and TechnologyBeijing University of AgricultureBeijingChina College of Agriculture Eastern Liaoning UniversityDandongLiaoningChina Dalian Institute of Chemical Physics Chinese Academy of SciencesDalianLiaoningChina State Environmental Protection Key Laboratory of Regional Eco-process and Function Assessment Chinese Research Academy of Environmental SciencesBeijingChina Hubei Hongshan Laboratory WuhanHubeiChina The New Zealand Institute for Plant and Food Research Limited AucklandNew Zealand

Actinidia arguta,the most widely distributed Actinidia species and the second cultivated species in the genus,can be distinguished from the currently cultivated Actinidia chinensis on the basis of its small and smooth fruit,rapid softening,and excellent cold *** evolution of tetraploid Actinidia species and the genetic basis of their important agronomic traits are still ***,we generated a chromosome-scale genome assembly of an autotetraploid male *** *** genome assembly was 2.77 Gb in length with a contig N50 of 9.97 Mb and was anchored onto 116 *** and clustering of 101 geographically representative accessions showed that they could be divided into two geographic groups,Southern and Northern,which first diverged 12.9 million years *** underwent two prominent expansions and one demographic bottleneck from the midPleistocene climate transition to the late *** genomics studies using paleoclimate data enabled us to discern the evolution of the species’adaptation to different historical *** genes(AaCEL1,AaPME1,and AaDOF1)related to flesh softening were identified by multi-omics analysis,and their ability to accelerate flesh softening was verified through transient expression assays.A set of genes that characteristically regulate sexual dimorphism located on the sex chromosome(Chr3)or autosomal chromosomes showed biased expression during stamen or carpel *** chromosome-level assembly of the autotetraploid *** genome and the genes related to important agronomic traits will facilitate future functional genomics research and improvement of ***.

关键词： kiwiberry dioecism adaptive evolution paleoclimate GEA rapid softening