检索结果-内蒙古大学图书馆

63rd IEEE Conference on Decision and control, CDC 2024

作者： Liu, Xinhui Cheng, Meiqi Shi, Dawei Shi, Ling Beijing Institute of Technology Miit Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing100081 China Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Kowloon Hong Kong

ISBN: (纸本)9798350316339

In this paper, we investigate the issues of real-time sensor scheduling and state estimator design within large-scale sensor network systems. Specifically, data redundancy sometimes occurs in large-scale sensor arrays due to the excessive proximity of sensing units in the spatial domain, leading to high similarity in their measurement data. Currently, it is difficult to account for such redundancy in sensor scheduling algorithms found in existing literature, where the optimal subset of sensors is generally selected by optimizing objective functions formulated from certain performance criteria. To tackle this problem, we introduce an event-based sensor scheduling strategy, the triggering condition of which is designed founded on the similarity of sensor data, so as to identify the most informative subset of sensors for state estimation. To evaluate the impact of the sensor scheduling protocol on system observability, we propose a new notion of E(varepsilon)-observability, based on which an observability criterion is derived. In addition, we have designed a set-valued state estimation algorithm, which takes into account the intricate measurement information structure inherent within the sensor selection mechanism. The performance enhancement of the proposed estimator is also investigated. Finally, numerical experiments are conducted to validate the effectiveness of the proposed estimation algorithm and to verify the performance improvement. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Attention-enhanced Relation Network for Few-shot Image Classification 23

Attention-enhanced Relation Network for Few-shot Image Class...

引用

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Li, Jinyang Tong, Jiahui Gao, Guangyu Xu, Wenbin School of Computer Science and Technology Beijing Institute of Technology China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Optical Radiation Laboratory Beijing Institute of Environmental Characteristics Beijing100854 China

ISBN: (纸本)9781450398572

Traditional deep learning models firmly rely on a large amount of labeled data during pre-training. Whereas it lacks generalization in the face of unfamiliar categories. Recently, few-shot learning is a hot topic in computer vision to classify unseen classes with limited labels. A representative approach is to extract features from the support and query sets, respectively, and compare similarities via metric learning. However, convolutional neural networks often focus only on a local region and ignore the global region, which severely reduces the accuracy of the matching. Specifically, in this paper, we pile lightweight attention-based blocks in the embedding module, which combines an adaptive kernel size 2D convolutional network with a cross-channel attention mechanism to encode multi-scale features and implicitly increase the receptive field. The SE-relation module chooses to construct learnable non-linear comparators to compare the relationship utilizing channel information. Finally, we show experimental results on standard few-shot testing benchmarks such as mini-ImageNet and tiered-ImageNet to demonstrate effectiveness. © 2023 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

The Development and Industry Risks of New Energy Vehicles in China

The Development and Industry Risks of New Energy Vehicles in...

引用

2022 International Conference on Statistics, Data science, and Computational Intelligence, CSDSCI 2022

作者： Tang, Xi-Ru Wang, Bin Institute of Urban System Engineering Beijing Academy of Science and Technology Beijing100035 China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing100192 China

ISBN: (纸本)9781510661325

The development of the new energy automobile industry is an important direction to accelerate the construction of a powerful automobile country, and it is also an effective means to break the constraints of energy and environment, which is of great strategic significance to China. In this article, based on the perspective of the development of the overall new energy vehicle industry, we analyze the market size and development stage of China's new energy vehicle industry, and explore the characteristics of the industry's development. Further, this paper analyzes the industry risks of the future development of new energy vehicles under the background of the imminent withdrawal of government financial subsidies and the transition of the new energy vehicle industry from policy-driven to market-driven, and provides theoretical support for the healthy and sustainable development of Chinese new energy vehicle industry. © 2023 SPIE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

A Shakedown Strength Based Parametric Optimization Technique and Its Application on an Airtight Module

引用

Chinese Journal of Mechanical engineering 2022年第4期35卷 139-151页

作者： Songhua Huang Yugong Xu Lele Zhang Geng Chen Feng Liu School of Mechanical Electronic and Control EngineeringBeijing Jiaotong UniversityBeijing 100044China National International Science and Technology Cooperation Base on Railway Vehicle Operation Beijing Jiaotong UniversityBeijing 100044China Beijing Institute of Spacecraft System Engineering Academy of Space TechnologyBeijing 100094China

In aerospace engineering,design and optimization of mechanical structures are usually performed with respect to elastic *** causing insufcient use of the material,such design concept fails to meet the ever growing needs of the light weight *** remedy this problem,in the present study,a shakedown theory based numerical approach for performing parametric optimization is *** this approach,strength of the structure is measured by its shakedown limit calculated from the direct *** numerical method developed for the structural optimization consists of nested loops:the inner loop adopts the interior point method to solve shakedown problems pertained to fxed design parameters,while the outer loop employs the genetic algorithm to fnd optimal design parameters leading to the greatest shakedown *** method established is frst verifed by the classic plate-with-a-circular-hole example,and after that it is applied to an airtight module for determining few key design *** carefully analyzing results generated during the optimization process,it is convinced that the approach can become a viable means for designing similar aerospace structures.

关键词： Parametric optimal design Shakedown analysis Direct method(DM) Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Robust Optimization Under Decision Dependent Uncertainty

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1295-1306页

作者： Yunfan Zhang Feng Liu Yifan Su Yue Chen Zhaojian Wang João P.S.Catalão State Key Laboratory of Power System and Generation Equipment the Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Mechanical and Automation Engineering the Chinese University of Hong KongHong Kong SARChina Ministry of Education Key Laboratory of System Control and Information Processing the Department of AutomationShanghai Jiao Tong Universityand also with Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240China Faculty of Engineering of the University of Porto and Institute for Systems and Computer Engineering Technology and Science(INESC TEC)Porto 4200-465Portugal IEEE

In the conventional robust optimization(RO)context,the uncertainty is regarded as residing in a predetermined and fixed uncertainty *** many applications,however,uncertainties are affected by decisions,making the current RO framework *** paper investigates a class of two-stage RO problems that involve decision-dependent *** introduce a class of polyhedral uncertainty sets whose right-hand-side vector has a dependency on the here-and-now decisions and seek to derive the exact optimal wait-and-see decisions for the second-stage problem.A novel iterative algorithm based on the Benders dual decomposition is proposed where advanced optimality cuts and feasibility cuts are designed to incorporate the uncertainty-decision *** computational tractability,robust feasibility and optimality,and convergence performance of the proposed algorithm are guaranteed with theoretical *** motivating application examples that feature the decision-dependent uncertainties are ***,the proposed solution methodology is verified by conducting case studies on the pre-disaster highway investment problem.

关键词： Benders decomposition decision-dependent uncertainty endogenous uncertainty robust optimization(RO)

来源：评论

学校读者我要写书评

暂无评论

Barrier Construction of the Homicidal Chauffeur Game Considering Speed Descent of the Car

Barrier Construction of the Homicidal Chauffeur Game Conside...

引用

IEEE International Conference on control science and systems engineering (CCSSE)

作者： Ziyi Zhan Yiqun Zhang Pengfei Zhang Control Science and Engineering Beijing Institute of Electronic System Engineering Beijing China Institute of Mechanics Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331517199

ISBN: (纸本)9798331517205

The Homicidal Chauffeur game is a classic pursuit-evasion problem for its significant application in aerospace, robot control, and military. Different from the well-known Isaacs' Homicidal Chauffeur game in which the car's speed is constant, we assume that the car's speed decreases during turns, reflecting the energy limitations in real-world applications. The paper aims to derive the optimal strategies and construct a barrier separating the capture and evasion zones. Initially, we simplify the six- dimensional problem to a three-dimensional one. Subsequently, we deduce the optimal strategy and construct the barrier using the Hamilton-Jacobi-Isaacs equation and backward induction method. A new barrier appears where the optimal strategy of the pursuer is different from the traditional one. That is, when the pursuer's speed is greater than a critical value, the optimal strategy is to apply maximum control; when the pursuer's speed is less than the critical speed, the optimal strategy is to apply zero control.

关键词： Shape Robot control Games Differential equations systems engineering and theory Automobiles Aerospace control

来源：评论

学校读者我要写书评

暂无评论

Hydrochars as slow-release phosphorus fertilizers for enhancing corn and soybean growth in an agricultural soil

引用

Carbon Research 2024年第1期3卷 1-19页

作者： Khosravi, Anahita Yuan, Yanfei Liu, Qiang Zheng, Hao Hashemi, Masoud Tang, Yuanzhi Xing, Baoshan Stockbridge School of Agriculture University of Massachusetts AmherstMA01003 United States Institute of Coastal Environmental Pollution Control College of Environmental Science and Engineering Ministry of Education Key Laboratory of Marine Environment and Ecology Frontiers Science Center for Deep Ocean Multispheres and Earth System Ocean University of China Qingdao266100 China Laboratory for Marine Ecology and Environmental Science Qingdao National Laboratory for Marine Science and Technology Qingdao266237 China School of Earth and Atmospheric Sciences Georgia Institute of Technology AtlantaGA30332–0340 United States

Hydrochars as carbonaceous amendments rich in porous structures and nutrients can be used as promising slow-release fertilizers and soil health amendments. Yet, the performance of hydrochars derived from different feedstocks in improving crop plant growth and soil phosphorus (P) availability is not well understood. Here, a batch of sewage sludge (SS) and chicken manure (CM) derived hydrochars (SSCs and CMCs) were produced at 125 and 225 °C (SS125/225 and CM125/225) to investigate their characteristics and performances in improving the seedling growth of two representative crops, soybean (Glycine max) and corn (Zea mays), as well as the P availability in an acidic agricultural soil in comparison with triple super phosphate (TSP), a conventional P fertilizer. Compared with CMCs, SSCs with more porous and rougher surfaces contained relatively lower contents of carbon (C;32.3–33.3%), hydrogen (H;3.9–4.69%), and potassium (K;29.2–51 mg g−1), but higher contents of P (37.4–85.4%) and nitrogen (N;2.26–4.9%), as well as more O-containing and N-containing functional groups. The impacts of hydrochars on soybean and corn growth showed distinct variations. The application of SSCs showed little effect on soybean growth (i.e., biomass, chlorophyl contents, and number of leaves), while CMCs significantly increased its total dry biomass by 23.2–66.2%. For corn, both SSCs and CMCs increased the total dry biomass by 32.8–92.4% and 21.8–69.7%, respectively, compared to those in the un-amended soils. In addition, compared with the higher temperature hydrochars (SS225 and CM225), the lower temperature ones (SS125 and CM125) increased the total dry biomass by 24.6% and 34.9% for soybean and 44.8% and 39.3% for corn, respectively. The significant improvement in crop growth by hydrochars was mainly due to the direct nutrient supply (particularly P) by the hydrochars, which was supported by the increased soil and shoot P concentrations. Moreover, hydrochar application led to a rise in soil

关键词： Manures

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning 27

Video2Reward: Generating Reward Function from Videos for Leg...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781643685489

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. © 2024 The Authors.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Thermal performance of a 3D printed lattice-structure heat sink packaging phase change material

引用

Chinese Journal of Aeronautics 2021年第5期34卷 373-385页

作者： Yuandong GUO Huning YANG Guiping LIN Haichuan JIN Xiaobin SHEN Jiang HE Jianyin MIAO Laboratory of Fundamental Science on Ergonomics and Environmental Control School of Aeronautic Science and EngineeringBeihang UniversityBeijing 100083China Beijing Key Laboratory of Space Thermal Control Technology Beijing Institute of Spacecraft System EngineeringChina Academy of Space TechnologyBeijing 100094China

Thermal storage technology is becoming more and more significant with the increase of high-power equipment in space *** this paper,3 D printing technology and Phase Change Material(PCM)were combined into a Thermal Energy Storage(TES)system,which could fulfill the requirements of light weight and high thermal conductivity.A 3 D-printed lattice-structure TES plate with N-tetradecane as the PCM and aluminum alloy as the thermal conductivity enhancer was manufactured,and experimentally tested in a thermal vacuum *** addition,a simplified simulation model of the lattice cell was established to clearly analyze the heat transfer process of the TES *** effects of initial temperature distribution and heat load gradient on the thermal storage performances were investigated experimentally and *** equivalent thermal conductivity of the 3 D-printed lattice-structure TES plate turns out to be 13 times of the pure PCM thanks to the aluminum *** heat transfer enhancement appears at the end of the phase change stage due to the sudden mixture of the PCM with different *** simulation results agree well with the experimental *** equivalent thermal conductivity obtained by the phase change simulations are a little higher than those of the experiments,which is mainly caused by the initial uneven temperature distribution in the ***,the effects of non-uniform heat load and the presence of the PCM in the TES plate are *** work successfully validates the feasibility and effectiveness of 3 D printing technology and TES technology for the temperature control in space applications.

关键词： 3D printing Experiment Lattice-cell structure Phase change material Simulation Thermal energy storage

来源：评论

学校读者我要写书评

暂无评论

Nodes2STRNet for structural dense displacement recognition by deformable mesh model and motion representation

引用

International Journal of Mechanical system Dynamics 2023年第3期3卷 229-250页

作者： Jin Zhao Hui Li Yang Xu Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology Harbin Institute of TechnologyHarbinChina Key Lab of Structures Dynamics Behavior and Control of the Ministry of Education Harbin Institute of TechnologyHarbinChina School of Civil Engineering Harbin Institute of TechnologyHarbinChina Department of System Design and Simulation Goldwind Science and Technology Co.Ltd.BeijingChina

Displacement is a critical indicator for mechanical systems and civil *** vision-based displacement recognition methods mainly focus on the sparse identification of limited measurement points,and the motion representation of an entire structure is very *** study proposes a novel Nodes2STRNet for structural dense displacement recognition using a handful of structural control nodes based on a deformable structural three-dimensional mesh model,which consists of control node estimation subnetwork(NodesEstimate)and pose parameter recognition subnetwork(Nodes2PoseNet).NodesEstimate calculates the dense optical flow field based on FlowNet 2.0 and generates structural control node ***2PoseNet uses structural control node coordinates as input and regresses structural pose parameters by a multilayer perceptron.A self-supervised learning strategy is designed with a mean square error loss and L2 regularization to train *** effectiveness and accuracy of dense displacement recognition and robustness to light condition variations are validated by seismic shaking table tests of a four-story-building *** studies with image-segmentation-based Structure-PoseNet show that the proposed Nodes2STRNet can achieve higher accuracy and better robustness against light condition *** addition,NodesEstimate does not require retraining when faced with new scenarios,and Nodes2PoseNet has high self-supervised training efficiency with only a few control nodes instead of fully supervised pixel-level segmentation.

关键词： structural dense displacement recognition deformable structural mesh model deep-learning-based monocular vision self-supervised learning

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：