检索结果-内蒙古大学图书馆

Knowledge As Not Only Justified True Beliefs in Vision

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 297-299页

作者： Wenbo Zheng Fei-Yue Wang IEEE School of Computer Science and Artificial Intelligence Wuhan University of Technology Sanya Science and Education Innovation Park of Wuhan University of Technology the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences

COMPUTATIONAL knowledge vision [1] is emphasized as a novel perspective or field in this paper. It first proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief. To further the previous research, we concisely summarize our recent works and suggest a new direction that knowledge is also a thought framework in vision.

关键词： Computational modeling Visualization Artificial intelligence Data models Visual perception Visual databases Training data

来源：评论

学校读者我要写书评

暂无评论

Detail Enhancement for Free Surface LBM Using Adaptive Sizing of Coupled Particles 1st

Detail Enhancement for Free Surface LBM Using Adaptive Sizi...

引用

1st International Conference on Extended Reality, ICXR 2024

作者： Qu, Qingyue Liu, Huiwen Zhu, Shaonan Hao, Aimin Yu, Peng Gao, Yang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Hubei Key Laboratory of Intelligent Yangtze and Hydroelectric Science Yangtze Power Co. Ltd. Hubei Yichang443000 China

ISBN: (纸本)9789819636785

Physically based fluid simulation plays an important role in the immersion and realistic of VR and AR applications. However, efficiency is the bottleneck problem that restricts physical applications. Among those physics-related fluid models, the Lattice Boltzmann Method (LBM), with its localized algorithm, offers high efficiency. However, as a purely Eulerian grid-based approach, achieving rich detail necessitates high resolution. Conversely, Lagrange-based methods can capture intricate details but require substantial computational time to solve large-scale linear systems and manage numerous particle operations. To address these challenges, we propose a hybrid solver that couples the efficient LBM solver with an adaptive particle interpolation method for detail enhancement. Our innovative adaptive particle strategy further reduces particle count while preserving surface detail and improving temporal efficiency by dynamically adjusting particle size based on particle position, distance, and velocity. Experiments demonstrate that our method can display more surface details than LBM alone, delivering visual effects comparable to direct particle interpolation but with higher efficiency. Moreover, our method yields superior visual results compared to adaptive particle methods based on the FLIP approach. This approach is particularly well-suited for large-scale simulations, enhancing both visual quality and time efficiency, and shows great potential for real-time fluid simulations in VR applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Experimental study on egress capacity of key facilities in pressurized oxygen-supplement compartments

引用

Chinese Physics B 2025年第1期34卷 536-546页

作者： Kai-Qiang Wang Xue-Hua Song Wei-Jun Liu Kang Wen Zhi-Gang Shi Jun Zhang Bin Yao Wei-Guo Song China Construction Institute of Advanced Technology Wuhan 450000China State Key Laboratory of Fire Science University of Science and Technology of ChinaHefei 230026China Business School University of Shanghai for Science and TechnologyShanghai 200093China School of Intelligent Emergency Management University of Shanghai for Science and TechnologyShanghai 200093China

Pressurized buildings have emerged as a novel architectural solution to alleviate altitude illness in high-altitude *** conventional buildings,evacuation from this kind of building has to experience a depressurization time,which results in air expansion and heat absorption,creating a dense fog and impairing sight within the *** experiments were performed in a pressurized oxygen-supplement compartment to investigate the pedestrian motion *** on the questionnaires,participants reported varying degrees of symptoms such as ear blockage,reduced environmental noise,and dizziness,which had a measurable impact on their *** focus on the evacuation parameters through three basic building components:staircases,pressure transition cabins,and escape *** the visibility in the compartment decreases from high to low,the movement patterns of pedestrian shift from triangular to single-file with a significant decline in evacuation *** is found that there is a linear relationship between evacuation time and the number of evacuees through escape *** pressure transition cabin is a crucial evacuation route in emergencies,and evacuation time is recommended as the key metric for assessing its *** findings offer valuable insights for emergency evacuation strategies in pressurized buildings.

关键词： altitude visibility architectural

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Assisted Robust Cubature Kalman Filter for Power System Dynamic state Estimation With Multi-Rate Measurements

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 14346-14357页

作者： Gu, Haoli Liu, Shichao Chen, Bo Wang, Rusheng Yu, Li Kaynak, Okyay Zhejiang University of Technology Department of Automation Hangzhou310023 China Zhejiang Key Laboratory of Intelligent Perception and Control for Complex Systems Hangzhou310023 China Ningbo University of Technology Ningbo315201 China Bogazici University Istanbul34342 Turkey

The coexistence of high-frequency phasor measurement units (PMUs) and conventional SCADA systems raises the challenge of heterogenous-source and multi-rate measurements which significantly degrades the performance of power system dynamic state estimation. In this work, a deep reinforcement learning (DRL) assisted robust cubature Kalman filtering (CKF) scheme is proposed to handle measurements from hybrid sources and with different time scales. In specific, a multi-rate measurement function reconstruction approach is designed with an independent discretization mechanism to lift the present limitation of requiring an integer multiple relationship of the sampling rates from multiple sources in most of existing works. Embedded with this discretization mechanism, a deep reinforcement learning assisted two-parameter linear exponential smoothing method is proposed to reconstruct the slow measurement model with online adjustable estimation parameters. A generalized correntropy loss criterion is also included in the robust CKF to counter the non-Gaussian noise and the noise distribution variation caused by the reconstruction. Comparisons results demonstrate that the proposed DRL-based robust CKF method can achieve better accuracy and robustness under various operating scenarios. © 2004-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Over 200 times current enhancement via buckling triboelectric nanogenerator at ultra-low speed for monitoring the swelling of lithium ion batteries

引用

Science Bulletin 2025年第2期70卷 148-152页

作者： Maoyi Zhang Chaosheng Hu Tongtong Zhang Chris R.Bowen Rui Li YongAn Huang Yewang Su Zhong Lin Wang Ya Yang Beijing Key Laboratory of Micro-Nano Energy and Sensor Center for High-Entropy Energy and SystemsBeijing Institute of Nanoenergy and NanosystemsChinese Academy of SciencesBeijing 101400China State Key Laboratory of Nonlinear Mechanics Institute of MechanicsChinese Academy of SciencesBeijing 100190China School of Engineering Science University of Chinese Academy of SciencesBeijing 100049China School of Nanoscience and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Mechanical Engineering University of BathBath BA27AKUK State Key Laboratory of Structural Analysis for Industrial Equipment Dalian University of TechnologyDalian 116024China State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China School of Material Science and Engineering Georgia Institute of TechnologyAtlantaGA 30332-0245USA

Sensors deployed within the Internet of Things(Io T)require a stable and continuous electrical energy supply[1].The traditional approach to provide an energy supply relies primarily on battery power,which has specific shortcomings;these include integration difficulties,the need for frequent charging or replacement,and environmental pollution associated with battery production and *** solve the challenge of delivering an energy supply to sensors,researchers have designed self-powered sensors or have produced power for sensors by scavenging mechanical energy from the surrounding *** generators[2],piezoelectric generators[3]and triboelectric nanogenerators(TENGs)[4,5]are common approaches to scavenge mechanical *** have been widely used in the development of self-powered sensors and the supply of electrical energy to sensors due to their high performance,low cost,and wide range of potential materials[6].

关键词： battery buckling swelling

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Enabled Digital Twin Synchronization for AIGC Services in Space–Air–Ground-Integrated Networks

引用

IEEE Internet of Things Journal 2025年第9期12卷 12989-13004页

作者： Li, Ya Jin, Kebing Tang, Jianhang Zhang, Yang Feng, Yixiong Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Hangzhou310027 China

Artificial intelligence-generated content (AIGC) is increasingly featuring a key to extract intent information from external instructions and generate required content in digital twin (DT)-enabled application scenarios. To construct DT contexts as the input of generative artificial intelligence (GenAI) algorithms, space–air–ground integrated networks (SAGINs) with hierarchical structures can facilitate object cloning from the physical world to a virtual space within vast geographical regions. In this work, we propose a novel DT synchronization framework residing in SAGINs to provide AIGC services. Autonomous aerial vehicles (AAVs) are in charge of gathering real-time information from the external environment and transmitting synchronization data to the core cloud via a communication relay, i.e., base station (BS) or satellite. In the proposed framework, we develop a resource allocation problem for DT synchronization, aiming to minimize the time-average energy costs of AAVs under the constraints on resource provision and long-term transmission queue stability. To address the complexity and dynamics of SAGINs, we first transform the original resource allocation problem into several deterministic problems based on the Lyapunov optimization. Then, a diffusion model-based resource allocation (DRA) algorithm is developed to solve the deterministic problem in each time slot, where a novel diffusion model is proposed to generate integer relay selection decisions with the aid of auxiliary gradients provided by conventional model-based optimization. Finally, we provide theoretical and simulation evaluations to demonstrate that the DRA algorithm can reduce energy consumption and improve resource utilization by comparing it with deep reinforcement learning (DRL) and heuristic algorithms. © 2014 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Cyclic shear responses of rough-walled rock joints subjected to dynamic normal loads

引用

Journal of Rock Mechanics and Geotechnical Engineering 2025年第5期17卷 3289-3297页

作者： Zhu, Qiang Yin, Qian Tao, Zhigang He, Manchao State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering China University of Mining and Technology Xuzhou 221116 China State Key Laboratory for Geomechanics and Deep Underground Engineering China University of Mining and Technology Beijing 100083 China

In rock engineering, the cyclic shear characteristics of rough joints under dynamic disturbances are still insufficiently studied. This study conducted cyclic shear experiments on rough joints under dynamic normal loads to assess the impact of shear frequency (f_h) and shear displacement amplitude (u_d) on the frictional properties of the joint. The results reveal that within a single shearing cycle, the normal displacement negatively correlates with the dynamic normal force. As the shear cycle number increases, the joint surface undergoes progressive wear, resulting in an exponential decrease in the peak normal displacement. In the cyclic shearing procedure, the forward peak values of shear force and friction coefficient display larger fluctuations at either lower or higher shear frequencies. However, under moderate shear frequency conditions, the changes in the shear strength of the joint surface are smaller, and the degree of degradation post-shearing is relatively limited. As the shear displacement amplitude increases, the range of normal deformation within the joint widens. Furthermore, after shearing, the corresponding joint roughness coefficient trend shows a gradual decrease with an increasing shear displacement amplitude, while varying with the shearing frequency in a pattern that initially rises and then falls, with a turning point at 0.05 Hz. The findings of this research contribute to a profound comprehension of the cyclic frictional properties of rock joints under dynamic disturbances. © 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences

关键词： Dynamic normal load Dynamic shear load Friction mechanisms Rough joints

来源：评论

学校读者我要写书评

暂无评论

Reinforcement-Learning-Based Finite Time Fault Tolerant Control for a Manipulator With Actuator Faults

引用

IEEE Transactions on Cybernetics 2025年第6期55卷 2621-2632页

作者： Yang, Pengxin Zhang, Shuang Yu, Xinbo He, Wei University of Science and Technology Beijing Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education Institute of Artificial Intelligence School of Intelligence Science and Technology Beijing100083 China University of Science and Technology Beijing School of Intelligence Science and Technology Beijing Advanced Innovation Center for Materials Genome Engineering Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education Beijing100083 China Liaoning Academy of Materials Institute of Materials Intelligent Technology Shenyang110004 China Beijing Information Science and Technology University School of Automation Institute of Artificial Intelligence Beijing102206 China University of Science and Technology Beijing School of Intelligence Science and Technology Institute of Artificial Intelligence Beijing100083 China

This study introduces a novel finite time fault tolerant controller integrating nonsingular terminal sliding mode (NTSM) and reinforcement learning (RL) strategies for manipulator systems with actuator faults. Leveraging an actor–critic network architecture, the RL algorithm facilitates the computation of the cost function and the approximation of unknown nonlinear dynamics. The inherent properties of NTSM mitigate the effects of parameter uncertainties, thereby enhancing system robustness. Furthermore, an adaptive law is crafted to counteract the deleterious effects of actuator faults. Through the direct Lyapunov function approach, it is demonstrated that the closed-loop system achieves semi-global practical finite-time stability. This control strategy diminishes the dependence on precise model accuracy and augments the system’s fault tolerance. The viability of the proposed algorithm is corroborated by simulation results, and its efficacy is further validated through experiments conducted on the 6-DOF Kinova Jaco 2 platform. © 2013 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Integrating Friction Noise for In Situ Monitoring of Polymer Wear Performance: A Machine Learning Approach in Tribology

引用

Journal of Tribology 2025年第6期147卷 061701页

作者： Chen, Shengshan Cheng, Ganlin Guo, Fei Jia, Xiaohong Wen, Xiaohao State Key Laboratory of Tribology in Advanced Equipment Tsinghua University Beijing100084 China Macau Institute of Systems Engineering Macau University of Science and Technology 999078 China

Friction and wear between mating surfaces significantly affect the efficiency and performance of mechanical systems. Traditional tribological research relies on post-observation methods, limiting the understanding of dynamic friction behavior. In contrast, in situ monitoring provides real-time insights into evolving friction dynamics. This study employs machine learning to monitor polymer wear performance through friction noise. The predictive accuracy of various machine learning methods, including Extremely Randomized Trees, Gradient-Boosting Decision Trees, AdaBoost, LightGBM, Deep Forest, and Deep Neural Networks, is compared for wear-type classification. Additionally, the LSBoost regression is selected as the optimal method for predicting polymer wear-rates across various temperatures. The results underscore the potential of using friction noise and machine learning for real-time wear monitoring, offering valuable insights for tribological system maintenance and failure prediction. © 2024 by ASME.

关键词： Tribology

来源：评论

学校读者我要写书评

暂无评论

Niobium oxide/MXene heterostructure for simultaneous production of ammonia and energy via rechargeable Zn-N2 battery system

引用

Journal of Energy Chemistry 2025年第4期103卷 448-457页

作者： Xinyu Dai Wei Zhang Ying Sun Zhenyi Du Zhanliang Tao Jingang Wang Wenhui Fang Xuehan Xing Yang Chen Hui Li Hao Zheng Jieshan Qiu Tianyi Ma Institute of Clean Energy Chemistry Key Laboratory for Green Synthesis and Preparative Chemistry of Advanced Materials of Liaoning Province College of ChemistryLiaoning University State Key Laboratory of Clean and Efficient Coal Utilization Taiyuan University of Technology Key Laboratory of Advanced Energy Materials Chemistry (Ministry of Education) Renewable Energy Conversion and Storage Center College of Chemistry Nankai University College of Science Liaoning Petrochemical University College of Chemical Engineering State Key Laboratory of Chemical Resource Engineering Beijing University of Chemical Technology Centre for Atomaterials and Nanomanufacturing (CAN) School of Science RMIT University ARC Industrial Transformation Research Hub for Intelligent Energy Efficiency in Future Protected Cropping (E2Crop) College of Chemical State Key Laboratory of Chemical Resource Engineering Beijing University of Chemical Technology

Aqueous Zn-N2batteries with unique configuration are of potential for simultaneous N2electro reduction and electricity generation,in which the electrocatalysts are critical for improving the NH3yield and the energy ***,a heterostructure Nb2O5/Nb2CTXwith abundant exposed Nb active sites and tuned electron density has been synthesized by in situ formation and anchoring of Nb2O5nanoparticles on the surface of Nb2CTXMXene,which shows an enhanced N2adsorption/activation *** heterostructure Nb2O5/Nb2CTXwas used as the cathode of Zn-N2battery that can deliver a peak power density of 1.25 mW cm-2in 1.0 M KOH and can continuously produce NH3with a yield of3.62 μg *** NH3formed in the battery system can be easily collected as a net product without circulating the ***,the Nb2O5/Nb2CTXhas a long durability,evidenced by 70 h of operation at-0.4 V *** hydrogen electrode,which is the highest among the MXene-based electrocatalysts reported thus *** work may provide a new methodology based on Zn-N2battery for sustainable and large-scale NH3production with minimal energy consumption.

关键词： NH 3 production Zn-N 2 battery N 2 Electroreduction Nb 2 O 5 /Nb 2 CT X heterostructure

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：