检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Liu, Yumeng Li, Xudong Hu, Yang Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Jingdong Industry Beijing China Science and Technology on Complex Aviation System Simulation Laboratory 9236 mailbox Beijing China

In recent years, deep transfer learning has been widely applied in fault diagnosis. In particular, domain adaptation method to solve unsupervised transfer learning problem has become a research hotspot. However, these researches mainly focus on the construction of loss function, and the design of network structure still depends on manual work. A differentiable neural architecture search method is proposed to automatically search for network structures suitable for domain adaptation in fault diagnosis to solve this problem. The proposed method search for two components in the Inception search space: structures of Inception blocks and feature mask. Inception blocks are stacked to form a complete network, and the feature mask selects the features for domain adaptation. Besides, to improve the search efficiency, we search and adapt multiple target domains at the same time, expanding the application scenarios of domain adaptation. The proposed method is evaluated on two datasets, and experiments show that this method can generate networks with excellent performance. © 2023, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis and Braking system Design of Icebreaker Propulsion system Based on 3L-NPC Inverter

Stability Analysis and Braking System Design of Icebreaker P...

引用

Smart Power & Internet Energy systems (SPIES), International Conference on

作者： Nianzhou Liu Nan Fu Pengfei Xie Wenfeng Long Kui Wang Yongdong Li Science and Technology on Ship Integrated Power System Technology Laboratory Wuhan Institute of Marine Electrical Propulsion Wuhan China State Key Lab of Control and Simulation of Power System and Generation Equipment Tsinghua University Beijing China

The icebreaker is important in the polar scientific investigation and resource exploration. There will be pulse and periodic load during the continuous icebreaking process, which may affect the propulsion system of the icebreaker. This paper mainly analyzes the effect of the impact load on the three-level neutral point clamped (3L-NPC) inverter with diode front-end, and demonstrates the relationship between the impact load and the feedback energy. Moreover, the choice of the resistance of the braking resistor is briefly discussed. The simulation results are given at last, which verify the rationality and correctness of the theoretical analysis.

关键词： Resistors Resistance simulation Energy Propulsion Inverters Stability analysis

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective optimization model for simulation-based acquisition 7

A Multi-objective optimization model for simulation-based ac...

引用

7th IEEE International Conference on Progress in Informatics and Computing, PIC 2020

作者： Zhang, Xue Xue, Junjie Zhou, Junhua Shi, Guoqiang Yu, Yan Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China Beijing Simulation Center Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing China

ISBN: (纸本)9781728170862

Large-scale equipment presents the characteristics of technology-intensive, knowledge-intensive and complex, which brings high investment and high risk to equipment acquisition. This paper analyzes the various components of equipment acquisition to fully apply modeling and simulation technology to each stage of it. On the basis of multi-objective optimization theory, the objective function of the lowest risk and lowest cost of simulation-based acquisition (SBA) is proposed. Then establishing a multi-objective optimization model for simulation-based acquisition according to the corresponding constraints. The nondominated sorting genetic algorithm II (NSGA II) and multi-objective particle swarm optimization (MOPSO) algorithms are used to optimize the model, and the majority voting method is used for integration. The comparison of simulation examples proves that the multi-objective optimization model oriented to SBA designed in this paper can effectively realize the optimization of each objective of SBA under cost constraints. And the feasibility and efficiency of optimization solution are guaranteed. © 2020 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Analysis on the Complex Characteristics of the Space-ground Integrated Network Structure

Analysis on the Complex Characteristics of the Space-ground ...

引用

Artificial Intelligence, Networking and Information technology (AINIT), International Seminar on

作者： Shenhao An Ronghuan Yu Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781665412971

The space-ground integrated network is one of the important information infrastructures of the country in the future. In order to further promote its visualization research, the structural characteristics of the space-ground integrated network are analyzed from the perspective of network complexity. Firstly, it introduces the development status of the space-ground integrated network, and then describes its overall structure and composition, focusing on the analysis of the complex characteristics of the space-ground integrated network structure from four aspects: heterogeneity, multi-layeredness, dynamics and distribution. Finally, Prospects for the next research direction.

关键词： Seminars Visualization Focusing Complexity theory Security Information technology Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

ETM fusion algorithm based on log classification

ETM fusion algorithm based on log classification

引用

Information technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Wenxiang Lin Desheng Liu Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781665428781

With the improvement of computer computing power, the shortcomings of the computational inefficiency of the genetic mining algorithm are compensated, and the genetic mining become a research hotspot. In this paper, for the Evolutionary Tree Miner (ETM) algorithm in noise processing can not find the low-frequency effective path and remove the shortage of noise, an ETM fusion algorithm based on log classification is proposed. The algorithm performs process model mining for high-frequency and low-frequency logs separately, and get model fusion based on alignment ideas, Eventually mining the complete process model. Through the simulation of event log data verification, the improved algorithm achieves more complete process model mining than the original ETM algorithm.

关键词： Solid modeling Analytical models Machine learning algorithms Heuristic algorithms Petri nets Genetics Mathematical models

来源：评论

学校读者我要写书评

暂无评论

WebGL-based Network Multi-view Visualization Interactive Analysis Method

WebGL-based Network Multi-view Visualization Interactive Ana...

引用

Computer Information science and Artificial Intelligence (CISAI), International Conference on

作者： Ronghuan Yu Shenhao An Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781665406932

The space-ground integrated network is one of the important information infrastructures of the country in the future. In order to display its network structure in all directions and from multiple angles, a multi-view visualization interactive analysis method is proposed. First introduces the relevant basic technology, and then constructs the network dynamic model, which is mainly divided into three parts: link visibility analysis, relative motion analysis and visualization model construction. Finally, the digital earth technology is based on a unified coordinate system and data source. Establish a multi-dimensional view on it and provide a variety of interactive operations. Experimental results show that this method can more comprehensively show the structure of the space-ground integrated network, and help users understand its evolutionary law.

关键词： Earth Solid modeling Analytical models Visualization Information science Three-dimensional displays Soft sensors

来源：评论

学校读者我要写书评

暂无评论

Twin Delayed Multi-Agent Deep Deterministic Policy Gradient

Twin Delayed Multi-Agent Deep Deterministic Policy Gradient

引用

Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)

作者： Mengying Zhan Jinchao Chen Chenglie Du Yuxin Duan Northwestern Polytechnical University Xi’an China Beijing Simulation Center Science and Technology on Special System Simulation Laboratory Beijing China

ISBN: (纸本)9781665426565

Recently, reinforcement learning has made remarkable achievements in the fields of natural science, engineering, medicine and operational research. Reinforcement learning addresses sequence problems and considers long-term returns. This long-term view of reinforcement learning is critical to find the optimal solution of many problems. The existing multi- agent reinforcement learning algorithms have the problem of overestimation in estimating the Q value. Unfortunately, there have not been many studies on overestimation of agent reinforcement learning, which will affect the learning efficiency of reinforcement learning. Based on the traditional multi-agent reinforcement learning algorithm, this paper improves the actor network and critic network, optimizes the overestimation of Q value and adopts the update delayed method to make the actor training more stable. In order to test the effectiveness of the algorithm structure, the modified method is compared with the traditional MADDPG, DDPG and DQN methods in the simulation environment.

关键词： Training Conferences Reinforcement learning Delays Informatics Convergence

来源：评论

学校读者我要写书评

暂无评论

A DQN-based hyperheuristic algorithm for emergency scheduling of Earth observation satellites

A DQN-based hyperheuristic algorithm for emergency schedulin...

引用

International Conference on Electronics, Communications and Information technology (CECIT)

作者： Zheng Liu Wei Xiong Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781665437585

With the surge of emergency task demand, large-scale Earth observation satellite emergency scheduling has become a practical problem which is urgent to be solved. In view of this situation, this paper analyzes the constrains and conflict relationship in this problem, and proposes a DQN-based hyperheuristic algorithm. The algorithm includes encoding and decoding, deep Q-network and several low-level heuristic operators. A Markov decision model of this problem is established and 7 low-level heuristic operators are designed according the feature of this problem. After training, DQN behaves well when selecting operators for the scheduling scheme. Finally, several groups of comparative experiments verify the algorithm's ability in solving large-scale satellite emergency scheduling problems.

关键词： Training Earth Satellites Heuristic algorithms Markov processes Scheduling Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

A Rapid Evaluation Method of Radar Tracking Accuracy 20

A Rapid Evaluation Method of Radar Tracking Accuracy

引用

Proceedings of the 2020 4th International Conference on Electronic Information technology and Computer Engineering

作者： Zhongwen Zhao Xu Zhang Guodong Li Science and Technology on Complex Electronics System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9781450387811

In order to solve the problem that the accuracy evaluation method based on error grouping is complex and can only be applied to post-processing, a fast judgment analysis method of radar tracking accuracy is proposed. This method decouples the two main processes of accuracy evaluation, namely error estimation and error statistics, and achieves fast analysis of radar tracking accuracy through real-time estimation of local accuracy and fast statistics of average accuracy of whole track. At the same time, this method avoids the discrimination of abnormal errors by applying robust median and median absolute difference estimation, further simplifies the error estimation process, so that it is more suitable for real-time data analysis.

关键词： Accuracy Evaluation Error Grouping Radar Robust Rapid Evaluation

来源：评论

学校读者我要写书评

暂无评论

An overview for monitoring and prediction of pathogenic microorganisms in the atmosphere

引用

Fundamental Research 2024年第3期4卷 430-441页

作者： Jianping Huang Danfeng Wang Yongguan Zhu Zifeng Yang Maosheng Yao Xiaoming Shi Taicheng An Qiang Zhang Cunrui Huang Xinhui Bi Jiang Li Zifa Wang Yongqin Liu Guibing Zhu Siyu Chen Jian Hang Xinghua Qiu Weiwei Deng Huaiyu Tian Tengfei Zhang Tianmu Chen Sijin Liu Xinbo Lian Bin Chen Beidou Zhang Yingjie Zhao Rui Wang Han Li Collaborative Innovation Center for Western Ecological Safety College of Atmospheric SciencesLanzhou UniversityLanzhou 730000China Research Center for Eco-Environmental Sciences Chinese Academy of SciencesBeijing 100085China National Clinical Research Center for Respiratory Disease Guangzhou Institute of Respiratory HealthFirst Affiliated Hospital of Guangzhou Medical UniversityState Key Laboratory of Respiratory Disease(Guangzhou Medical University)Guangzhou 510230China College of Environmental Sciences and Engineering Peking UniversityBeijing 100871China China CDC Key Laboratory of Environment and Population Health National Institute of Environmental HealthChinese Center for Disease Control and PreventionBeijing 100021China Guangdong-Hong Kong-Macao Joint Laboratory for Contaminants Exposure and Health School of Environmental Science and EngineeringInstitute of Environmental Health and Pollution ControlGuangdong University of TechnologyGuangzhou 510006China Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System ScienceTsinghua UniversityBeijing 100084China Vanke School of Public Health Tsinghua UniversityBeijing 100084China State Key Laboratory of Organic Geochemistry and Guangdong Key Laboratory of Environmental Protection and Resources Utilization Guangzhou Institute of GeochemistryChinese Academy of SciencesGuangzhou 510640China National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100021China State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China Center for Pan-third Pole Environment Lanzhou UniversityLanzhou 730000China College of Atmospheric Sciences Lanzhou UniversityLanzhou 730000China School of Atmospheric Sciences Sun Yat-sen Universityand Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)Zhuhai 510640

Corona virus disease 2019(COVID-19)has exerted a profound adverse impact on human *** have demonstrated that aerosol transmission is one of the major transmission routes of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2).Pathogenic microorganisms such as SARS-CoV-2 can survive in the air and cause widespread infection among *** monitoring of pathogenic microorganism transmission in the atmosphere and accurate epidemic prediction are the frontier guarantee for preventing large-scale epidemic *** of pathogenic microorganisms in the air,especially in densely populated areas,may raise the possibility to detect viruses before people are widely infected and contain the epidemic at an earlier *** multi-scale coupled accurate epidemic prediction system can provide support for governments to analyze the epidemic situation,allocate health resources,and formulate epidemic response *** review first elaborates on the effects of the atmospheric environment on pathogenic microorganism transmission,which lays a theoretical foundation for the monitoring and prediction of epidemic ***,the monitoring technique development and the necessity of monitoring pathogenic microorganisms in the atmosphere are summarized and ***,this review introduces the major epidemic prediction methods and highlights the significance to realize a multi-scale coupled epidemic prediction system by strengthening the multidisciplinary cooperation of epidemiology,atmospheric sciences,environmental sciences,sociology,demography,*** summarizing the achievements and challenges in monitoring and prediction of pathogenic microorganism transmission in the atmosphere,this review proposes suggestions for epidemic response,namely,the establishment of an integrated monitoring and prediction platform for pathogenic microorganism transmission in the atmosphere.

关键词： Aerosol transmission Epidemic monitoring methods Epidemic prediction modelsEpidemic response Multidisciplinary cooperation

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：