检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

Numerical investigation of the critical heat flux in a 5 × 5 rod bundle with multi-grid

引用

Nuclear engineering and Technology 2022年第5期54卷 1914-1928页

作者： Liu, Wei Shang, Zemin Yang, Shihao Yang, Lixin Tian, Zihao Liu, Yu Chen, Xi Peng, Qian State Key Laboratory of Reactor System Design Technology Nuclear Power Institute of China Chengdu 610213 China School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing 100044 China

To improve the heat transfer efficiency of the reactor fuel assembly, it is necessary to accurately calculate the two-phase flow boiling characteristics and the critical heat flux (CHF) in the fuel assembly. In this paper, a Eulerian two-fluid model combined with the extended wall boiling model was used to numerically simulate the 5 × 5 fuel rod bundle with spacer grids (four sets of mixing vane grids and four sets of simple support grids without mixing vanes). We calculated and analyzed 11 experimental conditions under different pressure, inlet temperature, and mass flux. After comparing the CHF and the location of departure from the nucleate boiling obtained by the numerical simulation with the experimental results, we confirmed the reliability of computational fluid dynamic analysis for the prediction of the CHF of the rod bundle and the boiling characteristics of the two-phase flow. Subsequently, we analyzed the influence of the spacer grid and mixing vanes on the void fraction, liquid temperature, and secondary flow distribution. The research in this article provides theoretical support for the design of fuel assemblies. © 2021 Korean Nuclear Society

关键词： 5 × 5 rod bundle Critical heat flux Eulerian two-fluid model Flow boiling

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Integrated Energy system for Cchp Based on Improved Cuckoo Search Algorithm

SSRN

引用

SSRN 2024年

作者： Zheng, KaiYue Zhao, ChuanZhen School of Control Science and Engineering Key Laboratory of Intelligent Control of Electrical Equipment Tiangong University Tianjin300387 China School of Electronics & Information Engineering Tianjin Key Laboratory of Optoelectronic Detection Technology and System Tiangong University Tianjin300387 China

This paper discusses the optimization and scheduling of an integrated energy system for combined cooling, heating and power (CCHP). It seeks to provide better scheduling of device outputs in the system and to decrease the daily economic and environmental operating costs of the system. We build an integrated energy system with wind turbine, micro gas turbine, electric cooling unit and so on, and establish a multi-objective optimization model with the goal of minimizing economic and environmental costs. In addition, we propose a novel optimal scheduling method. It combines chaotic mapping and cuckoo search algorithm to address issues such as slow convergence speed and high iteration counts in traditional optimization algorithms. Finally, the improved cuckoo search algorithm is used to solve the system optimization problem. The optimization solution is implemented in the case of satisfying the constraints of equipment output and power balance. The simulation results show that the CCHP system can effectively improve the economic efficiency and reduce the pollutant emissions compared with the common micro-grid system. Furthermore, compared with other algorithms, the improved cuckoo algorithm shows much better performance in solving the model and can decrease the whole system's total cost. © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

State-of-Charge Balancing control for Battery Energy Storage systems of Near-Space Vehicles with An Electric-Thermal-Aging Coupling Model

State-of-Charge Balancing Control for Battery Energy Storage...

引用

第42届中国控制会议

作者： Zhiqiang Zuo Yunhao Du Yijing Wang Zhicheng Zhang Peng Li Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University Key Laboratory of System Control and Information Processing Ministry of Education

State-of-charge(SoC) balancing is crucial for improving the efficiency and lifetime of the battery energy storage system in near-space vehicles. In this paper, the So C balancing control problem is investigated by a coupling battery model with electric-thermal-aging dynamics. Firstly, a system identification experiment is carried out to obtain the internal parameters of the battery. Secondly, a weight optimization index is designed by integrating the balancing speed and battery state-of-health(SoH). Then, a receding horizon control algorithm is proposed to realize multi-unit battery SoC balancing with partial swarm optimization(PSO). Finally, the effectiveness of the proposed strategy is verified by simulation results.

关键词：

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

Classification of Dunhuang Mural Image Based on Small-sample and Semi-supervised Learning 6

Classification of Dunhuang Mural Image Based on Small-sample...

引用

6th IEEE Information Technology, Networking, Electronic and Automation control Conference, ITNEC 2023

作者： Cui, Hui Su, Zhibin Zhang, Luyue Bai, Liyang Communication University of China School of Information and Engineering China Key Laboratory of Acoustic Visual Technology and Intelligent Control System China Ministry of Culture and Tourism P.R.C. Center for Ethnic and Folk Literature and Art Development China

ISBN: (纸本)9781665460033

Dunhuang mural images classification belongs to the research task in the field of image recognition. In this paper, the semi-supervised model is established with multidimensional features extracted by transfer learning. A small number of labeled samples were used to obtain a large number of unlabeled data, combined with Active Learning and iterative strategy for multiple rounds of label transfer of selected samples. After several rounds of iterations, we can get a more powerful classification learner. Experiments on the self-built Dunhuang mural dataset have shown that the results can approach or even exceed some supervised learning methods when the number of known label samples is less than 4%. Our research implements the cultural resource image classification algorithm based on small samples, which is conductive to improving the accuracy when label samples are scarce. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization and Termination of Sequential Prediction Maintenance and Spare Parts Ordering under Dynamic Remaining Useful Time Prediction 5

Joint Optimization and Termination of Sequential Prediction ...

引用

5th International Conference on system Reliability and Safety engineering, SRSE 2023

作者： Zhang, Yongfei Zhang, Xiaohong Yang, Tianxiang Li, Yuxin Shen, Juan Sun, Chaoli Taiyuan University of Science & Technology Taiyuan School of Economics & Management Taiyuan China Taiyuan University of Science & Technology Division of Industrial and System Engineering 030024 China Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan030024 China

ISBN: (纸本)9798350305944

In the research of Prognostics and Health Management (PHM), prediction is a dynamic process, and the corresponding maintenance decisions are also dynamic. The problem of updating and termination decisions in dynamic sequential decision-making is a rarely studied but worthy of attention problem. To address these problems, a joint decision-making and termination problem for sequential prediction maintenance and spare parts ordering under dynamic remaining life prediction was studied. The Bayesian update and EM algorithm were used in combination to achieve dynamic remaining life and reliability prediction. An adaptive detection and sequential prediction maintenance strategy based on dynamic prediction results was developed, and a judgment criterion for decision termination was given. At the adaptive detection moment, the system balanced the cost of spare parts storage and stockout, preventive maintenance cost, and post-failure maintenance cost, and determined the optimal maintenance and spare parts ordering time. Based on the termination criterion, the truly executed maintenance and spare parts ordering time were selected from the dynamic redundant decision results. Finally, the effectiveness of the proposed strategy and method were verified through experiments. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Integrated Energy system for Cchp Based on Improved Cuckoo Search Algorithm

SSRN

引用

SSRN 2024年

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Capacity Planning of Distributed Photovoltaic Generation and Energy Storage systems for the Traction Power Supply system of Electric Railway 8

Capacity Planning of Distributed Photovoltaic Generation and...

引用

8th IEEE International Conference on Energy Internet, ICEI 2024

作者： Huang, Li Wang, Ying Liu, Weizhi Ma, Yingtao Li, Shenglin Beijing Jiaotong University School of Electrical Engineering Beijing China State Key Laboratory for Traction and Control System of EMU and Locomotive China Academy Railway Sciences Corporation Limited Beijing Zongheng Electromechanical Technology Co.Ltd. Beijing China Shanghai Jiaotong University School of Electronic Information and Electrical Engineering Shanghai China

ISBN: (纸本)9798331523558

Although the current power industry distributed photovoltaic development for many years, how to integrate photovoltaic into the railway system existing power supply infrastructure is still not a consensus in the industry, how to determine the railway energy system planning of photovoltaic energy storage access needs to be studied. Taking the traction power supply system connected with distributed photovoltaic power generation and energy storage system as the research object, this paper explores the capacity planning method of optical storage system along railway line, which takes into account the whole life cycle cost of photovoltaic and energy storage equipment. On the basis of consulting data, this paper first defines the influence factors of the system required for capacity planning, including access method of PV and ESS, the Solar radiation conditions, the types of photovoltaic and energy storage equipment used, etc. Then, the system is modeled according to the selected parameters and constraints of equipment in planning stage and operation stage. Finally, the necessity is illustrated by comparing the difference of power purchase cost of railway system before and after introducing PV and ESS along the railway line, and the further evaluation of the role of the system is obtained by comparing the effect of different access methods, different electricity tariff policies and different light levels. © 2024 IEEE.

关键词： Power distribution planning

来源：评论

学校读者我要写书评

暂无评论

Improved closed-loop tracking interferometer measurement for a five-axis machine tool with a bi-rotary milling head

引用

Science China(Technological Sciences) 2022年第5期65卷 1127-1136页

作者： TANG XinYu XU Kun BI QingZhen SONG ZhiYong JI YuLei QIAN DeHou State Key Laboratory of Mechanical System and Vibration School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai200240China AVIC Chengdu Aircraft Industrial(Group)Co. Ltd.Chengdu610092China Shanghai TOP Numerical Control Technology Co. Ltd.Shanghai201100China

Tracking interferometer based on bi-rotary milling head is a novel scheme to conduct volumetric accuracy measurement of a five-axis machine *** laser beam direction of the interferometer can be regulated to follow the retroreflector by moving the bi-rotary *** is a low-cost implementation of multilateration measurement,and its measurement accuracy is mainly affected by the error motion of the rotary *** paper proposes an improved multilateration principle to identify the positionindependent geometric errors of rotary axis and laser beam,and minimize their impact on the measurement uncertainty.A closed-loop tracking interferometer system installed on the spindle is developed to perform the measurement with high tracking *** device can be installed on an ordinary five-axis machine tool without modifying the machine tool *** proposed scheme is conducive to improving the accuracy and practical application of the tracking interferometer based on birotary milling *** with the corresponding closed-loop tracking interferometer and uncertainty analysis are conducted to verify the performance of the proposed measurement scheme.

关键词： tracking interferometer multilateration volumetric accuracy five-axis machine tools

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：