检索结果-南通市图书馆

Social Robot Detection Method with Improved Graph Neural Networks

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2期78卷 1773-1795页

作者： Zhenhua Yu Liangxue bai Ou Ye Xuya Cong Institute of Systems Security and Control College of Computer Science and TechnologyXi’an University of Science and TechnologyXi’an710054China

Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social *** social robot detection methods based on graph neural networks suffer from the problem of many social network nodes and complex relationships,which makes it difficult to accurately describe the difference between the topological relations of nodes,resulting in low detection accuracy of social *** paper proposes a social robot detection method with the use of an improved neural ***,social relationship subgraphs are constructed by leveraging the user’s social network to disentangle intricate social relationships ***,a linear modulated graph attention residual network model is devised to extract the node and network topology features of the social relation subgraph,thereby generating comprehensive social relation subgraph features,and the feature-wise linear modulation module of the model can better learn the differences between the ***,user text content and behavioral gene sequences are extracted to construct social behavioral features combined with the social relationship subgraph ***,social robots can be more accurately identified by combining user behavioral and relationship *** carrying out experimental studies based on the publicly available datasets TwiBot-20 and Cresci-15,the suggested method’s detection accuracies can achieve 86.73%and 97.86%,*** with the existing mainstream approaches,the accuracy of the proposed method is 2.2%and 1.35%higher on the two *** results show that the method proposed in this paper can effectively detect social robots and maintain a healthy ecological environment of social networks.

关键词： Social robot detection social relationship subgraph graph attention network feature linear modulation behavioral gene sequences

Dynamic Multi-Physics Behaviors and Performance Loss of Cylindrical Batteries Upon Low-Velocity Impact Loading

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy & Environmental Materials 2024年第6期7卷 184-192页

作者： Qingdan Huang Yang bai Han Luo Yikai Jia Chao Zhang School of Civil Aviation Northwestern Polytechnical UniversityXi’an 710072China Key Laboratory on the Impact Protection and Safety Assessment of Civil Aviation Vehicle Taicang 215400China School of Aeronautics Northwestern Polytechnical UniversityXi’an 710072China EVE Energy Co. Ltd.Huizhou 516006C

In challenging operational environments,Lithium-ion batteries(LIBs)inevitably experience mechanical stresses,including impacts and extrusion,which can lead to battery damage,failure,and even the occurrence of fire and explosion ***,it is imperative to investigate the safety performance of LIBs under mechanical *** study is grounded in a more realistic coupling scenario consisting of electrochemical cycling and low-velocity *** systematically and experimentally uncovered the mechanical,electrochemical,and thermal responses,damage behavior,and corresponding mechanisms under various *** study demonstrates that higher impact energy results in increased structural stiffness,maximum temperature,and maximum voltage ***,heightened impact energy significantly influences the electrical resistance parameters within the internal *** also examined the effects of State of Charge(SOC)and *** methodology and experimental findings will offer insights for enhancing the safety design,conducting risk assessments,and enabling the cascading utilization of energy storage systems based on LIBs.

关键词： cycling performance damaged battery lithium-ion battery low-velocity impact mechanical safety

Gravity Change Caused by Heavy Rainfall Detected by A gPhone Gravimeter in Zhengzhou,China

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 Earth Science 2024年第4期35卷 1273-1276页

作者： Lelin Xing Yufei Han Xiaowei Niu Lei bai Innovation Academy for Precision Measurement Science and Technology Chinese Academy of SciencesWuhan430077China Wuhan Geodesy National Observation and Research Station Wuhan430077China China Earthquake Networks Center Beijing100045China

The short-term effect of heavy rainfall on gPhone gravimeter observation at Zhengzhou Seismic Station is *** to the observation data during Jul.17–20,2021,the corrected gravity residual reflects the gravimetric response caused by heavy *** observed gravity change is dominated by the local effect considering topographic effect on *** deduced water depth near the observation station is about 300 mm.

关键词： gravity gravity change gravimeter heavy rain Zhengzhou

Deformation characteristics of ultra-deep circular shaft in soft soil:A case study

在线全文

学校读者我要写书评

暂无评论

Underground Space 2024年第3期16卷 239-260页

作者： Yafei Qiao Feng Xie Zhanwei bai Jiafeng Lu Wenqi Ding Department of Geotechnical Engineering College of Civil EngineeringTongji UniversityShanghai 200092China Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education Tongji UniversityShanghai 200092China Engineering Project Management Company Shanghai Chengtou Water GroupShanghai 200002China SGIDI Engineering Consulting(Group)Co. Ltd.Shanghai 200093China

A circular shaft is often used to access a working well for deep underground space *** the depth of underground space increases,the excavation depth of the shaft *** this study,the deformation characteristics of a circular shaft with a depth of 56.3 m were presented and *** main monitoring contents included:(1)wall deflection;(2)vertical wall movement;(3)horizontal soil movement;(4)vertical surface movement;and(5)basal ***,the maximum wall deflection was only 7.7 *** with the wall deflection data collected for another 29 circular excavations,the ratio of maximum wall deflection to excavation depth of this shaft was smaller due to a smaller ratio of diameter to excavation *** wall deflection underwent two stages of deformation:the first stage was mainly circumferential compression caused by the mutual extrusion of joints between walls,and the second stage was typical vertical deflection *** horizontal soil movement outside the shaft was greater than the wall deflection and the deep soil caused great horizontal movement because of dewatering at confined water ***,a basal heave of 203.8 mm occurred in the pit centre near the ***,the shaft was uplifted over time and showed 3 stages of vertical *** surface outside the shaft exhibited settlement and uplift deformation at different locations due to different *** basal heave caused by excavation was the dominant factor,driving the vertical movement of the shaft as well as the surrounding *** correlation between the wall deflection and the surface settlement outside the shaft was weak.

关键词： Circular shaft Site monitoring Deflection Vertical deformation Soft soil

Voltage rise rate-related generalised probabilistic lifetime model of turn-to-turn insulation in inverter-fed motors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Voltage 2024年第1期9卷 46-55页

作者： Yan Yang Xueyang bai Yuxing Lei Kai Liu Guangning Wu School of Electrical Engineering Southwest Jiaotong UniversityChengduChina

The lifetime model of turn-to-turn insulation in inverter-fed motors is studied.A lifetime model has been built by considering the effect of inverter-generated high voltage rise rate(dv/dt up to 20 V/ns).This model is followed by the generalised probabilistic model,in which the lifetime is proportional to the nth power of the voltage rise ***,by investigating the effect of voltage rise rate on the partial discharge characteristics,it is found that the effect of voltage rise rate on the charge transport process in a voltage cycle is similar to that of the voltage *** enhanced partial discharge activity and induced charges are responsible for accelerated ageing and thus determine the final lifetime of turn-to-turn *** this case,the generalised probabilistic electric lifetime model is applicable to the voltage rise rate as well as the voltage amplitude.

关键词： lifetime inverter insulation

Solvation strategies in various electrolytes for advanced zinc metal anode

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7期94卷 740-757页

作者： Zhenxu Wang Lichong bai Hongguang Fan Yanpeng Wang Wei Liu School of Materials Science and Engineering Ocean University of ChinaQingdao 266100ShandongChina

Aqueous zinc-ion batteries(AZIBs),known for their high safety,low cost,and environmental friendliness,have a wide range of potential applications in large-scale energy storage ***,the notorious dendrite growth and severe side reactions on the anode have significantly hindered their further practical *** studies have shown that the solvation chemistry in the electrolyte is not only closely related to the barriers to the commercialization of AZIBs,but have also sparked a number of valuable ideas to address the challenges of ***,we systematically summarize and discuss the regulatory mechanisms of solvation chemistry in various types of electrolytes and the influence of the solvation environment on battery *** challenges and future directions for solvation strategies based on the electrolyte environment are proposed to improve their performance and expand their application in AZIBs.

关键词： Solvation strategy Electrolyte Aqueous zinc-ion batteries Zinc dendrite

From atomistic modeling to materials design:computation-driven material development in lithium-ion batteries

在线全文

学校读者我要写书评

暂无评论

Science China Chemistry 2024年第1期67卷 276-290页

作者： Xiangrong Li Xiang Chen Qiang bai Yifei Mo Yizhou Zhu Research Center for Industries of the Future and School of Engineering Westlake UniversityHangzhou 310030China Department of Chemical Engineering Tsinghua UniversityBeijing 100084China College of Materials Science and Engineering Taiyuan University of TechnologyTaiyuan 030024China Department of Materials Science and Engineering University of MarylandCollege Park 20742United States

As an advanced energy storage system,lithium-ion batteries play an essential role in modern *** their ubiquitous success,there is a great demand for continuous improvements of the battery performance,including higher energy density,lower safety risk,longer cycling life,and lower *** performance improvement requires the design and development of novel electrode and electrolyte materials that exhibit desirable properties and satisfy strict *** modeling can provide a unique perspective to fundamentally understand and rationally design battery *** this paper,we review a few recent successful examples of computation-driven discovery and design in electrode and electrolyte ***,we highlight how atomistic modeling can reveal the underlying mechanisms,predict the important properties,and guide the design and engineering of electrode and electrolyte *** have a conclusion with a discussion of the unique capability of atomistic modeling in battery material development and provide a perspective on future challenges and directions for computation-driven battery material developments.

关键词： materials design computation modeling batteries electrolyte electrode

Digitalizing river aquatic ecosystems

在线全文

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2024年第3期137卷 677-680页

作者： Yaohui bai Hui Lin Chenchen Wang Qiaojuan Wang Jiuhui Qu Key Laboratory of Drinking Water Science and Technology Research Center for Eco-Environmental SciencesChinese Academy of SciencesBeijing 100085China University of Chinese Academy of Sciences Beijing 100049China School of Environmental and Municipal Engineering Tianjin Chengjian UniversityTianjin 300384China Center for Water and Ecology Tsinghua UniversityBeijing 100084China

Traditional river health assessment relies on limited water quality indices and representative organism activity,but does not comprehensively obtain biotic and abiotic information of the ***,we propose a new approach to evaluate the ecological and health risks of river aquatic ***,detailed physicochemical and biological characterization of a river ecosystem can be obtained through pollutant determination(especially emerging pollutants)and DNA/RNA ***,supervised machine learning can be applied to perform classification analysis of characterization data and ascertain river ecosystem ecology and *** proposed methodology transforms river ecosystem health assessment and can be applied in river management.

关键词： Digitalizing River ecosystem health Emerging pollutants High throughput sequencing Machine learning

Ensemble successor representations for task generalization in offline-to-online reinforcement learning

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 240-255页

作者： Changhong WANG Xudong YU Chenjia bai Qiaosheng ZHANG Zhen WANG Space Control and Inertial Technology Research Center Harbin Institute of Technology Shanghai Artificial Intelligence Laboratory Shenzhen Research Institute of Northwestern Polytechnical University School of Cybersecurity Northwestern Polytechnical University

In reinforcement learning(RL), training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration. Recently, offline RL provides a promising solution by giving an initialized offline policy, which can be refined through online interactions. However, existing approaches primarily perform offline and online learning in the same task, without considering the task generalization problem in offline-to-online adaptation. In real-world applications, it is common that we only have an offline dataset from a specific task while aiming for fast online-adaptation for several tasks. To address this problem, our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning. We demonstrate that the conventional paradigm using successor features cannot effectively utilize offline data and improve the performance for the new task by online fine-tuning. To mitigate this, we introduce a novel methodology that leverages offline data to acquire an ensemble of successor representations and subsequently constructs ensemble Q functions. This approach enables robust representation learning from datasets with different coverage and facilitates fast adaption of Q functions towards new tasks during the online fine-tuning *** empirical evaluations provide compelling evidence showcasing the superior performance of our method in generalizing to diverse or even unseen tasks.

关键词： offline reinforcement learning online fine-tuning task generalization successor representations ensembles