检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Xiaoyu Li, Peidong Zhao, Lijun Liu, Dedong Gao, Jinghan Wu, Xian Wu, Yitao Cui, Dixiao State Key Laboratory of Robotics and Systems Harbin Institute of Technology China Zhijia Technology China

3D Multi-Object Tracking (MOT) obtains significant performance improvements with the rapid advancements in 3D object detection, particularly in cost-effective multi-camera setups. However, the prevalent end-to-end training approach for multi-camera trackers results in detector-specific models, limiting their versatility. Moreover, current generic trackers overlook the unique features of multi-camera detectors, i.e., the unreliability of motion observations and the feasibility of visual information. To address these challenges, we propose RockTrack, a 3D MOT method for multi-camera detectors. Following the Tracking-By-Detection framework, RockTrack is compatible with various off-the-shelf detectors. RockTrack incorporates a confidence-guided preprocessing module to extract reliable motion and image observations from distinct representation spaces from a single detector. These observations are then fused in an association module that leverages geometric and appearance cues to minimize mismatches. The resulting matches are propagated through a staged estimation process, forming the basis for heuristic noise modeling. Additionally, we introduce a novel appearance similarity metric for explicitly characterizing object affinities in multi-camera settings. RockTrack achieves state-of-the-art performance on the nuScenes vision-only tracking leaderboard with 59.1% AMOTA while demonstrating impressive computational efficiency. © 2024, CC BY-NC-SA.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Distributed Deep Reinforcement Learning-based Approach for Fast Preventive Control Considering Transient Stability Constraints

引用

CSEE Journal of Power and Energy systems 2023年第1期9卷 197-208页

作者： Hongtai Zeng Yanzhen Zhou Qinglai Guo Zhongmin Cai Hongbin Sun State Key Laboratory of Power Systems Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Automation Science and Technology Xi’an Jiaotong UniversityXi’an 710000China

Preventive transient stability control is an effective measure for the power system to withstand high-probability severe *** is mathematically an optimal power flow problem with transient stability *** to the constraints involved for differential algebraic equations of transient stability,it is difficult and time-consuming to solve this *** address these issues,this paper presents a novel deep reinforcement learning(DRL)framework for preventive transient stability control of power systems.A distributed deep deterministic policy gradient is utilized to train a DRL agent that can learn its control policy through massive interactions with a grid *** properly trained,the DRL agent can instantaneously provide effective strategies to adjust the system to a safe operating position with a near-optimal operational *** effectiveness of the proposed method is verified through numerical experiments conducted on a New England 39-bus system and NPCC 140-bus system.

关键词： Deep reinforcement learning preventive Control transient stability

来源：评论

学校读者我要写书评

暂无评论

Numerical and experimental study of the effects of wind turbine operation on sand-dust transport characteristics

引用

Science China(Physics,Mechanics & Astronomy) 2024年第4期67卷 97-113页

作者： Gaosheng Ma Hong Han Ye Li Deshun Li Yan Wang Ning Fu Quan Zheng Rennian Li School of Energy and Power Engineering Lanzhou University of TechnologyLanzhou 730050China Gansu Provincial Technology Center for Wind Turbines Lanzhou 730050China Key Laboratory of Fluid Machinery and Systems Lanzhou 730050China Multiple Function Towing Tank Laboratory State Key Laboratory of Ocean EngineeringSchool of Naval ArchitectureOcean and Civil EngineeringShanghai Jiao Tong UniversityShanghai 200240China

Given factors such as reduced land availability for onshore wind farms,wind resource enrichment levels,and costs,there is a growing trend of establishing wind farms in deserts,the Gobi,and other arid ***,the relationship between sanddust weather environments and wind turbine operations has garnered significant *** investigate the impact of wind turbine wakes on sand-dust transportation,this study employs large eddy simulation to model flow fields,coupled with an actuator line model for simulating rotating blades and a multiphase particle in cell model for simulating sand *** research focuses on a horizontal axis wind turbine model and examines the motion and spatiotemporal distribution characteristics of four typical sizes of sand particles in the turbine *** findings reveal that sand particles of varying sizes exhibit a spiral settling pattern after traversing the rotating plane of wind turbine blades,influenced by blade shedding vortex and *** particles tend to cluster in the peripheries of the vortex cores of low vorticity in the wind turbine *** rotation of wind turbines generates a wake vortex structure that causes a significant clustering of sand particles at the tip *** the wake distance increases,the particles that cluster at the turbine's tip gradually spread outward to approximately twice the rotor diameter and then begin to mix with the incoming flow *** turbines have a noticeable impact on sand-dust transportation,hindering their movement to a significant *** average sand-blocking rate exhibits a trend of initially increasing and then decreasing as the wake distance *** its peak,the sand-blocking rate reaches an impressive 67.55%.The presence of wind turbines induces the advanced settling of sand particles,resulting in a“triangular”distribution of the deposition within the ground projection area of the wake.

关键词： wind turbine particle transportation actuator line model dry deposition particle clustering

来源：评论

学校读者我要写书评

暂无评论

High accuracy target point classification through dark-field detection of large-aperture optics surface based on machine vision

High accuracy target point classification through dark-field...

引用

2024 Applied Optics and Photonics China: Optical Sensing, Imaging technology, and Applications, AOPC 2024

作者： Zhou, Shicheng Yin, Zhaoyang Wang, Bei Zhao, Linjie Cheng, Jian Chen, Mingjun School of Mechatronics Engineering Harbin Institute of Technology Harbin150001 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

ISBN: (数字)9781510687820

ISBN: (纸本)9781510687813

Surface defects on optics seriously affect their service life in high-power laser system. To address this issue, repair technologies for large-aperture optics are extensively employed. However, the operation of high-power laser system generates a large number of optics requiring repair. Currently, microscopic inspection is widely used for target points classification due to its high accuracy, but it has limitations such as small field of view and low efficiency. Utilizing the OTSU algorithm and Convolutional Neural Networks (CNN), a dark-field classification model for optical surface target points has been developed. Upon conducting experiments with several network models, the ResNet model, a probability threshold of 0.998 were determined. In conclusion, the classification accuracy for defects was 99.18% and for contaminants was 90.34%. The outcomes show that target points on the surfaces of optics can be accurately classified using this method. © 2024 SPIE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

A brief review of preparation and applications of monolithic aerogels in atmospheric environmental purification

引用

Journal of Environmental Sciences 2025年第3期149卷 209-220页

作者： Linfeng Nie Shuangde Li Mengjie Cao Ning Han Yunfa Chen State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China Key Laboratory of Science&Technology on Particle Materials Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China

Monolithic aerogels are promising candidates for use in atmospheric environmental purification due to their structural advantages,such as fine building block size together with high specific surface area,abundant pore structure,***,monolithic aerogels possess a unique monolithic macrostructure that sets them apart from aerogel powders and nanoparticles in practical environmental clean-up *** review delves into the available synthesis strategies and atmospheric environmental applications of monolithic aerogels,covering types of monolithic aerogels including SiO_(2),graphene,metal oxides and their combinations,along with their preparation *** particular,recent developments for VOC adsorption,CO_(2)capture,catalytic oxidation of VOCs and catalytic reduction of CO_(2)are ***,challenges and future opportunities for monolithic aerogels in the atmospheric environmental purification field are *** reviewprovides valuable insights for designing and utilizing monolithic aerogel-based functional materials.

关键词： Monolithic aerogel Environmental purification Catalysis Adsorption

来源：评论

学校读者我要写书评

暂无评论

Investigation of thermal and solidification behaviors to predict dendrite microstructure formation during directed energy deposition of AlSi10Mg

引用

CIRP Journal of Manufacturing Science and technology 2025年 61卷 222-232页

作者： Tingyu Chang Enjie Dong Linjie Zhao Mingjun Chen Jian Cheng State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin Heilongjiang 150001 China State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Hangzhou 310027 China

The characteristics of local high-energy input and rapid cooling of L-DED result in uneven microstructure on the scale of the molten pool. This paper develops a coupled temperature and solid-liquid phase fields model, from which the cooling rate and morphology parameters could be calculated to predict the dendrites size and morphology throughout the entire molten pool. The single-track cladding experiment was carried out to verify the feasibility of the model, showing that the geometrical characteristic (i.e., width and depth of the modelled molten pool match closely with the experimental measurements. It is found that from the bonding zone to the top zone of the molten pool, the microstructure evolution trend from columnar dendrites to fine equiaxed dendrites could be accurately predicted with the decreasing morphology parameters and increasing cooling rate. The morphology parameter drops suddenly at about 0.3 mm away from the bottom boundary, indicating that the dendrite microstructure morphology would show a major change from columnar to equiaxial at this specific location. The dendrite microstructure obtained by the experiment also verified this transformation, and further proofed the DED aluminum alloy suffers from columnar to equiaxial transition in the region with morphology parameters greater than about 2 ×10 8 K∙s/m 2 . This work greatly reduces the time cost in evaluating the dendrites microstructure of DED cladding layers, which is necessary to control the microstructure and to improve properties of L-DED repaired layers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-shot object detection via class encoding and multi-target decoding

引用

IET Cyber-systems and robotics 2023年第2期5卷 1-14页

作者： Xueqiang Guo Hanqing Yang Mohan Wei Xiaotong Ye Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhouChina Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province HangzhouChina

The task of few‐shot object detection is to classify and locate objects through a few annotated *** many studies have tried to solve this problem,the results are still not *** studies have found that the class margin significantly impacts the classification and representation of the targets to be *** methods use the loss function to balance the class margin,but the results show that the loss‐based methods only have a tiny improvement on the few‐shot object detection *** this study,the authors propose a class encoding method based on the transformer to balance the class margin,which can make the model pay more attention to the essential information of the features,thus increasing the recognition ability of the ***,the authors propose a multi‐target decoding method to aggregate RoI vectors generated from multi‐target images with multiple support vectors,which can significantly improve the detection ability of the detector for multi‐target *** on Pascal visual object classes(VOC)and Microsoft Common Objects in Context datasets show that our proposed Few‐Shot Object Detection via Class Encoding and Multi‐Target Decoding significantly improves upon baseline detectors(average accuracy improvement is up to 10.8%on VOC and 2.1%on COCO),achieving competitive *** general,we propose a new way to regulate the class margin between support set vectors and a way of feature aggregation for images containing multiple objects and achieve remarkable *** method is implemented on mmfewshot,and the code will be available later.

关键词： Class Margin Few-Shot Object Detection Multi-Target Transformer

来源：评论

学校读者我要写书评

暂无评论

Characteristics of laser-induced breakdown spectroscopy of liquid slag

引用

Plasma Science and technology 2024年第2期26卷 86-93页

作者：董长言于洪霞孙兰香李洋刘修业周平黄少文 State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016People's Republic of China Key Laboratory of Networked Control Systems Chinese Academy of SciencesShenyang 110016People's RepublicofChina Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169People's Republic of China Shenyang University of Technology Shenyang 110870People's Republic of China Shenyang Ligong University Shenyang 1i0142People's Republic of China Shandong Iron and Steel Company Ltd. Jinan 271105People's Republic of China

Rapid online analysis of liquid slag is essential for optimizing the quality and energy efficiency of steel production. To investigate the key factors that affect the online measurement of refined slag using laser-induced breakdown spectroscopy(LIBS), this study examined the effects of slag composition and temperature on the intensity and stability of the LIBS spectra. The experimental temperature was controlled at three levels: 1350℃, 1400℃, and 1450℃. The results showed that slag composition and temperature significantly affected the intensity and stability of the LIBS spectra. Increasing the Fe content and temperature in the slag reduces its viscosity, resulting in an enhanced intensity and stability of the LIBS spectra. Additionally, 42 refined slag samples were quantitatively analyzed for Fe, Si, Ca, Mg, Al, and Mn at 1350℃, 1400℃, and 1450℃.The normalized full spectrum combined with partial least squares(PLS) quantification modeling was used, using the Ca Ⅱ 317.91 nm spectral line as an internal standard. The results show that using the internal standard normalization method can significantly reduce the influence of spectral fluctuations. Meanwhile, a temperature of 1450℃ has been found to yield superior results compared to both 1350℃ and 1400℃, and it is advantageous to conduct a quantitative analysis of the slag when it is in a “water-like” state with low viscosity.

关键词： laser-induced breakdown spectroscopy(LIBS) slag temperature composition viscosity internal standard normalization partial least squares(PLS)

来源：评论

学校读者我要写书评

暂无评论

Reconstructing and editing fluids using the adaptive multilayer external force guiding model

引用

Science China(Information Sciences) 2022年第11期65卷 107-122页

作者： Xiaoying NIE Yong HU Xukun SHEN Zhiyuan SU State Key Laboratory of Virtual Reality Technology and Systems Beihang University School of New Media Art and Design Beihang University

Reconstructing monocular fluids usually involves a tedious trial-and-error process, and editing desired fluid behaviors is notoriously difficult to predict and control. To address these problems, we propose an adaptive multilayer external force guiding model that alleviates the challenging parameter tuning and satisfies user-defined requirements. External forces cause the effect of target particles on fluid *** adaptive multilayer scheme makes the whole 3D fluid volume subject to the shape and motion of the water captured by the input video or designed by users. Therefore, we can avoid the tedious and laborious parameter tuning and easily balance the smoothness of fluid volume and the details of the water ***, to vividly reproduce the inflow and outflow of the video scene, we construct a generation and extinction model to add or delete fluid particles according to the three-dimensional velocity field of target particles calculated using a hybrid model coupling shape-from-shading with optical flow. Besides, we edit fluids by subtly extracting features selected by users using the off-screen rendering method and seamlessly integrating them using the dynamic weight approach. Experiments show that our approach is comparable to the state-of-the-art reconstruction quality and is remarkably convenient in authoring flows by editing ***, our results can be effectively applied to any desired new scenario.

关键词： reconstructing fluids editing fluids monocular videos adaptive multilayer external force guiding model generation and extinction model

来源：评论

学校读者我要写书评

暂无评论

Learning Rat-Like Behavioral Interaction Using a Small-Scale Robotic Rat

引用

Cyborg and Bionic systems 2023年第1期4卷 225-232页

作者： Hongzhao Xie Zihang Gao Guanglu Jia Shingo Shimoda Qing Shi Intelligent Robotics Institute School of Mechatronical EngineeringBeijing Institute of TechnologyBeijing 100081China Key Laboratory of Biomimetic Robots and Systems(Beijing Institute of Technology) Ministry of EducationBeijing 100081China Nagoya University Graduate School of Medicine NagoyaJapan

In this paper,we propose a novel method for emulating rat-like behavioral interactions in robots using reinforcement ***,we develop a state decision method to optimize the interaction process among 6 known behavior types that have been identified in previous research on rat *** novelty of our method lies in using the temporal difference(TD)algorithm to optimize the state decision process,which enables the robots to make informed decisions about their behavior *** assess the similarity between robot and rat behavior,we use Pearson *** then use TD-λto update the state value function and make state decisions based on *** robots execute these decisions using our dynamics-based *** results demonstrate that our method can generate rat-like behaviors on both short-and long-term timescales,with interaction information entropy comparable to that between real ***,our approach shows promise for controlling robots in robot-rat interactions and highlights the potential of using reinforcement learning to develop more sophisticated robotic systems.

关键词： robot enable similarity

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：