检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Liu, Yongchao Wang, Bo Zheng, Wei Wang, Zibo Li, Tong Cheng, Jiahao Niu, Zhenfeng Ke, Zhiwu Tan, Sichao Li, Jiangkuan Gao, Puzhen Tian, Ruifeng Zhu, Qidan Heilongjiang Provincial Key Laboratory of Nuclear Power System & Equipment Harbin Engineering University Harbin150001 China Key Laboratory of Nuclear Safety and Advanced Nuclear Energy Technology Ministry of Industry and Information Technology Harbin Engineering University Harbin150001 China Science and Technology Thermal Energy and Power Laboratory Wuhan430205 China Wuhan Second Ship Design and Research Institute Wuhan430205 China College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150001 China

As one of the most important subsystem types in the nuclear power system, the closed-loop cooling system is used for the heat transfer of the system. The control quality of its operating temperature is important for the safe operation of the entire nuclear power system. This paper proposes an intelligent temperature control method based on deep reinforcement learning (DRL). First, the closed-loop cooling system simulator is built and expanded to provide an experimental platform for the implementation of DRL. Secondly, a DRL interaction system is designed based on prior knowledge such as system thermal control characteristics and temperature control targets. Finally, the improved deep Q-network (DQN) algorithm is used to train the deep neural network agent, and the optimal temperature control strategy is approached and saved through self-learning interaction. The experimental results demonstrate that the DRL controller can realize automatic control operation and has good target tracking ability and robustness. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learnable Operational design Condition Monitor for Failure Prediction in Autonomous Driving

SSRN

引用

SSRN 2025年

作者： Xu, Haowei Bian, Yougang Li, Yang Qin, Hongmao Zhou, Hanchu Chang, Fangrong Wang, Shaofei Ye, Qing State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle College of Mechanical and Vehicle Engineering Hunan University Changsha410082 China Research and Development Center of Transport Industry of Self-driving Technology China Merchants Chongqing Communications Technology Research and Design Institute Co. Ltd. Chongqing China School of Traffic and Transportation Engineering Central South University Changsha China Department of Data and System Engineering The University of Hong Kong Hong Kong School of Resources and Safety Engineering Central South University Changsha China School of Data Science China

Ensuring the safety of Autonomous Driving systems (ADS) across diverse and unpredictable operational scenarios remains a significant challenge for accident prevention. Central to this effort is the continuous monitoring of Operational design Conditions (ODC), which encompass both in-vehicle factors and external Operational design Domain (ODD). However, the absence of robust methodologies to precisely identify ODC boundaries hinders the deployment and adoption of high-level ADS. This paper introduces a learnable ODC monitor designed to identify implicit operational design condition boundaries to prevent ADS failures. By integrating a state-space duality encoder and a Bayesian neural network decoder, we propose an efficient learnable ODC monitor, termed ODCNet. Furthermore, to further enhance prediction reliability, residual error analysis with linear discrimination is applied for calibrating prediction. Experimental results demonstrate ODCNet's superiority in failure prediction compared to baseline models, achieving a balance between safety and coverage. These findings contribute to advancing data-driven accident prediction and prevention strategies, ensuring safer deployments of ADS in complex environments. © 2025, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Optimization of Task Allocation and Path Planning Using Mixed-Integer Programming for Time and Capacity Constrained Multi-Agent Pickup and Delivery

Simultaneous Optimization of Task Allocation and Path Planni...

引用

International Conference on Control, Automation and systems ( ICCAS)

作者： Takuma Okubo Masaki Takahashi Graduate School of Science and Technology Keio University 3-14-1 Hiyoshi Kohoku-ku Yokohama Japan Department of System Design Engineering Faculty of Science and Technology Keio University 3-14-1 Hiyoshi Kohoku-ku Yokohama Japan

Lately, there has been a need to improve the efficiency of material movements within factories and multi-agents are required to perform these tasks. In this study, graphical representation and mixed-integer programming have been adopted for simultaneous optimization of task allocation and path planning for each agent to achieve the following three goals. First, this study realizes time and capacity constrained multi-agent pickup and delivery (TCMAPD) that simultaneously considers time constraints, capacity constraints, and collision avoidance. Previous studies have not considered these constraints simultaneously. Thus, we can solve the problems associated with using multi-agents in actual factories. Second, we achieved TCMAPD that optimizes the collision avoidance between multi-agents. In conventional research, only a single collision avoidance method can be used. However, an appropriate route was selected from a variety of avoidance methods in this study. Hence, we could achieve a more efficient task allocation and path planning with collision avoidance. Third, the proposed method simultaneously optimizes task allocation and path planning for each agent. Previous studies have separately considered the approach of optimizing task allocation and path planning or used the cost of path planning after task allocation to again perform task allocation and path planning. To simultaneously optimize them in a single plan, we have developed a solution-derivable formulation using mixed-integer programming to derive a globally optimal solution. This enables efficient planning with a reduced total time traveled by the agents.

关键词： Costs Programming Path planning Production facilities Planning Resource management Time factors

来源：评论

学校读者我要写书评

暂无评论

STD: Stable Triangle Descriptor for 3D place recognition

STD: Stable Triangle Descriptor for 3D place recognition

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Chongjian Yuan Jiarong Lin Zuhao Zou Xiaoping Hong Fu Zhang Department of Mechanical Engineering The University of Hong Kong Hong Kong Special Administrative Region People's Republic of China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen People's Republic of China

In this work, we present a novel global descriptor termed stable triangle descriptor (STD) for 3D place recognition. For a triangle, its shape is uniquely determined by the length of the sides or included angles. Moreover, the shape of triangles is completely invariant to rigid transformations. Based on this property, we first design an algorithm to efficiently extract local key points from the 3D point cloud and encode these key points into triangular descriptors. Then, place recognition is achieved by matching the side lengths (and some other information) of the descriptors between point clouds. The point correspondence obtained from the descriptor matching pair can be further used in geometric verification, which greatly improves the accuracy of place recognition. In our experiments, we extensively compare our proposed system against other state-of-the-art systems (i.e., M2DP, Scan Context) on public datasets (i.e., KITTI, NCLT, and Complex-Urban) and our self-collected dataset (with a non-repetitive scanning solid-state LiDAR). All the quantitative results show that STD has stronger adaptability and a great improvement in precision over its counterparts. To share our findings and make contributions to the community, we open source our code on our GitHub: ***/hku-mars/STD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Event-Triggered Adaptive Dynamic Programming Method for Large-Scale HVAC systems*

引用

IFAC-PapersOnLine 2023年第2期56卷 5281-5286页

作者： Shan Xue Zhiwen Chen Derong Liu Chao Shangt Hongtian Chen School of Computer Science and Engineering South China University of Technology Guangzhou 510006 China School of Automation Central South University Changsha 410083 China Peng Cheng Laboratory Shenzhen 518000 China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen 518005 China Department of Automation BNRist Tsinghua University Beijing 100084 China Department of Automation Shanghai Jiao Tong University Shanghai 200240 China

In this paper, an event-triggered adaptive dynamic programming (ADP) algorithm is developed for the temperature control of large-scale heating, ventilation, and air conditioning (HVAC) systems. First, the dynamic model of the system is established by using the conservation of mass and energy, which involves the dynamics of the fan and the cooling coil. Second, the multi-zone temperature control problem is treated as a non-zero-sum game, which requires solving the coupled Hamilton-Jacobian (HJ) equations. Then, the ADP algorithm is employed to solve the HJ equation. Importantly, in order to reduce the network transmission burden of large-scale HVAC systems, the ADP algorithm developed in this paper is based on event-triggering mechanism. Theoretical analysis proves that the tracking error and the neural network weight estimation error are uniformly ultimately bounded. Simulation results verify the effectiveness of the algorithm.

关键词： adaptive dynamic programming optimal control event-triggering mechanism neural networks heating, ventilation, and air conditioning

来源：评论

学校读者我要写书评

暂无评论

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection 39

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Dist...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Dai, Tao Lin, Yang Guo, Hang Wang, Jinbao Zhu, Zexuan College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen City Key Laboratory of Embedded System Design Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (纸本)157735897X

Knowledge distillation (KD) has recently gained great success in the field of object detection. By transferring the knowledge of the spatial or channel domain from the teacher model to the student model, it allows for a more compact representation with minimal performance loss. Despite this progress, existing KD methods typically treat knowledge from spatial or channel domains independently, ignoring the exploitation of the mutual relationship between these domains. In this work, we first explore the connection between spatial and channel domains and find there exists a strong correlation between them, i.e. the salient channels tend to contain significant object regions in the spatial domain. Motivated by this observation, we propose DCSF-KD, a novel Dynamic Channel-wise Spatial Feature Knowledge Distillation framework for object detection by fully exploiting both spatial and channel knowledge. Specifically, we introduce channel-wise spatial feature distillation and global channel attention distillation, using information from both domains to improve the accuracy of the student network. Experiments demonstrate that our DCSF-KD outperforms existing detection methods on both homogeneous and heterogeneous teacher-student network pairs. For example, when using the MaskRCNN-Swin detector as the teacher, and based on RetinaNet and FCOS with ResNet-50 on MS COCO, our DCSF-KD can achieve 41.9% and 44.1% mAP, respectively. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A combined reactivity control pattern on a floating nuclear power plant 27

A combined reactivity control pattern on a floating nuclear ...

引用

27th International Conference on Nuclear Engineering: Nuclear Power Saves the World!, ICONE 2019

作者： Zhou, Bingyan Song, Danrong Chen, Zhang Chai, Xiaoming Xiang, Hongzhi Hu, Yuying Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu Sichuan China

ISBN: (纸本)9784888983051

In this study, a new combined reactivity control pattern is presented to lower the power peaking factor on a floating nuclear power plant. In the pattern the whole cycle length is divided into several boron-adjusting periods. During one boron-adjusting period, the soluble boron concentration remains unchanged and the core reactivity change is controlled by control rods. Boron concentration would only be changed at the end of a boron-adjusting period. In the whole cycle the boron concentration would be changed for two to four times, which is acceptable for a floating nuclear power plant. To get an optimized solution, a model of the combined reactivity control pattern was established, which contained boron concentration and control rod pattern (CRP) as coupled variables. A particle swarm optimization with novel mutation operator (PSONM) was applied to optimize the solution. The model was practiced based on a small modular reactor ACP100 core. The solution was optimized separately for equal division of two, three, four and five boron-adjusting periods. The results show that the combined reactivity control pattern can get a lower power peak factor than the original rod-controlled-only pattern without shortening the cycle length. Therefore, the safety of the floating nuclear power plant can be improved. Copyright © 2018-2019 by JSME

关键词： Nuclear power plants

来源：评论

学校读者我要写书评

暂无评论

Parametric Structural Optimization of 2D Complex Shape Based on Isogeometric Analysis

引用

Computer Modeling in Engineering & sciences 2020年第7期124卷 203-225页

作者： Long Chen Li Xu Kai Wang Baotong Li Jun Hong School of Mechanical Engineering University of Shanghai for Science and TechnologyShanghai200093China Key Laboratory of Education Ministry for Modern Design&Rotor-Bearing System Xi’an Jiaotong UniversityXi’an710049China

The geometric model and the analysis model can be unified together through the isogeometric analysis method,which has potential to achieve seamless integration of CAD and *** design is a mainstream and successful method in CAD *** method is not continued in simulation and optimization stage because of the model conversion in conventional optimization method based on the finite element *** integration of the parametric modeling and the structural optimization by using isogeometric analysis is a natural and interesting *** paper proposed a method to realize a structural optimization of parametric complex shapes by using isogeometric *** the given feature curves and the constraints,a feature frame model is *** on the feature frame model,a parametric representation of complex shape is *** adding some auxiliary curves,the feature frame model is divided into many box-like patches in three dimension or four-sided patches in two *** patches are built into parametric patches by using volume interpolation methods such as Coons *** on the parametric patches,isogeometic analysis is ***,the relationships are constructed among the size parameters,the control points and the physical performance *** the sensitivity matrix could be derived based on the *** size optimization is carried out in the first stage by taking the size parameters as *** on the result of size optimization,shape optimization with the constraints of stress is carried out in the second stage by taking the control points as *** planar complex shapes are taken as example to verify our *** results verify that the parametric modeling and structural optimization can be united together without model *** from this,the optimization design can be executed as a dark box operation without considering the concrete modeling and analysis by input of the sizes,constra

关键词： Isogeometric analysis parametric design structural optimization

来源：评论

学校读者我要写书评

暂无评论

Dual-clamped one-pot SERS-based biosensors for rapid and sensitive detection of SARS-CoV-2 using portable Raman spectrometer

引用

Sensors and Actuators B: Chemical 2023年第1期393卷 134172页

作者： Kaladharan, Kiran Chen, Kuan-Hung Chen, Pin-Han Goudar, Venkanagouda S. Ishdorj, Tseren-Onolt Santra, Tuhin Subhra Tseng, Fan-Gang Department of Engineering and System Science National Tsing Hua University Taiwan School of Information and Communication Technology Mongolian University of Science and Technology Mongolia Department of Engineering Design Indian Institute of Technology Madras India Institute of Nano Engineering and Microsystems National Tsing Hua University Taiwan Department of Chemistry National Tsing Hua University Taiwan Frontier Research Centre on Fundamental and Applied Sciences of Matters National Tsing Hua University Taiwan Research Centre for Applied Sciences Academia Sinica Taipei Taiwan

Rapid and sensitive diagnostics of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is of utmost importance to control the widespread coronavirus disease 2019 (COVID-19) upsurge. This study demonstrated a novel one-pot surface-enhanced Raman scattering (SERS) based immunoassay to detect SARS-CoV-2, without any washing process using a portable Raman spectrometer. The SERS-immune assay was designed using a regular digital versatile disk (DVD) substrate integrated with Raman reporter labeled silver nanoparticles for double clamping effects. The disks were molded to form nanopillar arrays and coated with silver film to enhance the sensitivity of immunoassay. The SERS platform demonstrated a limit of detection (LoD) up to 50 pg mL−1 for SARS-CoV-2 spike protein and virus-like-particle (VLP) protein in phosphate buffer saline within a turnaround time of 20 mins. Moreover, VLP protein spiked in untreated saliva achieved an LoD of 400 pg mL−1, providing a cycle threshold (Ct) value range of 30–32, closer to reverse transcription-polymerase chain reaction (RT-PCR) results (35−40) and higher than the commercial rapid antigen tests, ranging from 25 to 28. Therefore, the developed one-pot SERS based biosensor exhibited highly sensitive and rapid detection of SARS-CoV-2, which could be a potential point-of-care platform for early and cost-effective diagnosis of the COVID-19 virus. © 2023 Elsevier B.V.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Boosting weather forecast via generative superensemble

arXiv

引用

arXiv 2024年

作者： Nai, Congyi Chen, Xi Yang, Shangshang Liang, Yuan Xiao, Ziniu Pan, Baoxiang Key Laboratory of Earth System Numerical Modeling and Application Institute of Atmospheric Physics Chinese Academy of Science Beijing China Institute of Atmospheric Physics Chinese Academy of Science Beijing China School of Engineering and Design Technical University of Munich Munich Germany Potsdam Institute for Climate Impact Research Potsdam Germany TianJi Weather Science and Technology Company Beijing China

Accurate weather forecasting is essential for socioeconomic activities. While data-driven forecasting demonstrates superior predictive capabilities over traditional Numerical Weather Prediction (NWP) with reduced computational demands, its deterministic nature and limited advantages over physics-based ensemble predictions restrict operational applications. We introduce the generative ensemble prediction system (GenEPS) framework to address these limitations by randomizing and mitigating both random errors and systematic biases. GenEPS provides a plug-and-play ensemble forecasting capability for deterministic models to eliminate random errors, while incorporating cross-model integration for cross-model ensembles to address systematic biases. The framework culminates in a superensemble approach utilizing all available data-driven models to further minimize systematic biases. GenEPS achieves an Anomaly Correlation Coefficient (ACC) of 0.679 for 500hPa geopotential (Z500), exceeding the ECMWF Ensemble Prediction system’s (ENS) ACC of 0.646. Integration of the ECMWF ensemble mean further improves the ACC to 0.683. The framework also enhances extreme event representation and produces energy spectra more consistent with ERA5 reanalysis. GenEPS establishes a new paradigm in ensemble forecasting by enabling the integration of multiple data-driven models into a high-performing super-ensemble system. © 2024, CC BY-NC-SA.

关键词： Prediction models

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：