检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Li, Xudong Hu, Yang Zheng, Jianhua Li, Mingtao National Space Science Center. CAS University of Chinese Academy of Sciences Beijing China Science and Technology on Complex Aviation System Simulation Laboratory 9236 mailbox Beijing China

Data-driven methods has made great progress in fault diagnosis, especially deep learning method. Deep learning is suitable for processing big data, and has a strong feature extraction ability to realize end-to-end fault diagnosis systems. Due to the complexity and variability of experimental data, some deep learning models are designed to be complex. However, designing neural network architecture requires rich professional knowledge and debugging experience, and a lot of experiments are needed to screen models and hyperparameters, increasing the difficulty of developing deep learning models. Fortunately, neural architecture search (NAS) is developing rapidly, and is becoming one of the next directions for deep learning. Given a search space, NAS can automatically search for the optimal network architecture. In this paper, we proposed a NAS method for fault diagnosis using reinforcement learning. A recurrent neural network is used as an agent to generate the network architecture. The accuracy of the generated network on the validation dataset is fed back to the agent as a reward, and the parameters of the agent are updated through the strategy gradient algorithm. In order to speed up the search process, parameters sharing method is adopted in this paper. We use PHM 2009 Data Challeng gearbox dataset to prove the effectiveness of propsed method, and obtain state-of-the-art results compared with other artificial designed network structures. To authors best knowledge, its the first time that NAS has been applied in fault diagnosis. Copyright © 2020, 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

Research on Internet of Things Vulnerability Based on Complex Network Attack Model 3rd

Research on Internet of Things Vulnerability Based on Comple...

引用

3rd International Conference on Space Information Networks, SINC 2018

作者： Liu, Chengxiang Xiong, Wei Company of Postgraduate Management Space Engineering University Beijing China Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing China

ISBN: (纸本)9789811359361

The Internet of Things brings convenience to people’s lives and it is also vulnerable to external attacks due to its own vulnerability. For this reason, analyzing the vulnerability of the Internet of Things is very necessary and meaningful. The paper starts with the characteristics of the Internet of Things and firstly constructs its network attack model. And then we simulate the attack on the model according to the attack rules. Furthermore, an experimental analysis of the nodes vulnerability is conducted by the theory of complex networks, and indicators of network characteristics are quantified based on the removal of vulnerable nodes. The experimental results show that the vulnerability of the system will show different patterns of attenuation as the proportion of node deletion increases. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Research on Integration Framework and Service Adaptation technology of Space system simulation Test-bed

引用

Journal of Physics: Conference Series 2021年第1期2133卷

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

Aiming at the requirements of space system simulation test-bed in heterogeneous integration and co-simulation, the support capability of test-bed integration framework is analysed. A space system simulation test-bed integration framework based on bridging adaptation service is constructed, and adaptation services such as protocol adaptation, information publication, information subscription and service control for service oriented architecture are designed and implemented, which provide integration capability and co-simulation management capability for heterogeneous systems, models and components of space system simulation test-bed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conditional Adversarial Domain Adaption based on Self-attention

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第1期7卷 175-188页

作者： Zhao, Li-Quan Zhang, Yu-Peng Teng, Zi-Ming Jiang, Zi-Cong Cui, Ying Kan, Zhong-Feng Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China College of information and communication Jilin University Changchun130012 China Graduate school of Information Science and Electrical Engineering Kyushu University Fukuoka819-0395 Japan Zhuhai Power Supply Bureau Guangdong Electric Power Corporation Zhuhai519000 China Jilin Power Supply Bureau Jilin Electric Power Corporation Jilin132012 China

Transfer learning is a deep learning method. It transforms knowledge in the source domain and feeds it to the target domain to improve the performance of the target domain model. The conditional adversarial domain adaption method is one of a number of transfer learning methods. It uses Resnet as the feature extraction network;however, Resnet can only determine the relationship between local features, and so its feature extraction accuracy is limited. To overcome this problem, a self-attention layer has been designed in order to determine the relationship among all features. This layer is added between the fourth layer and fifth layer of Resnet. Besides, a cross-entropy function is introduced into loss function, and a sigmoid layer is designed and used as the out layer in conditional adversarial domain adaption. These produce gradient disappearance in the deep network, and influence the discriminator training effect. To solve that problem, a least squares function is used as to design the loss function. The new type of loss function does not require the sigmoid function. Using theoretical analysis, we explain how this new loss function can be used to solve the gradient disappearance problem, thus rendering the network structure more stable. We compare our proposed method with other datasets, including Joint Adaptation Networks, adversarial domain adaptation, conditional adversarial domain adaption, Resnet-50, domain-adversarial neural network on imageCLEF-DA, Office-Home, and Office-31. Our simulation results show that the proposed conditional adversarial domain adaption based on self-attention method has the fastest convergence speed and highest accuracy the among different datasets. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

First Principles Calculations of Charge Shift Photocurrent in Vdws Slide Double Layered 2d H-Bn and Β-Ges Homostructures

SSRN

引用

SSRN 2022年

作者： Kaner, Ngeywo Tolbert Wei, Yadong Raza, Ali Yang, Jianqun Li, Xingji Li, Weiqi Jiang, YongYuan Wei Quan, Tian School of Physics Harbin Institute of Technology Harbin150001 China School of Materials Science and Engineering Harbin Institute of Technology Harbin150001 China Technology Innovation Center of Materials and Devices at Extreme Environment Harbin Institute of Technology Harbin150001 China 1-Km Main Daska Road Punjab Sialkot51040 Pakistan State Key Laboratory of Intense Pulsed Radiation Simulation and Effect Xi’an710024 China Key Lab of Micro-Optics and Photonic Technology of Heilongjiang Province Harbin150001 China Key Laboratory of Micro-Nano Optoelectronic Information System Ministry of Industry and Information Technology Harbin150001 China Collaborative Innovation Center of Extreme Optics Shanxi University Taiyuan030006 China Chongqing Key Laboratory of Theoretical and Computational Chemistry College of Chemistry and Chemical Engineering Chongqing University Chongqing401331 China

Shift photovoltaic current (SPC) in polar non-centrosymmetric materials has recently emerged as a promising candidate for the next generation photovoltaic devices in which Shockley-Queisser limits are fully overcome. Here, we apply first principles calculations to predict colossal SPC in the slide bilayers of 2D h -BN and β-GeS vdW homostructures. The large SPC in slide bilayers h -BN and β-GeS reaches 49.3 µAV-2 and 130µ µAV-2 , respectively, in the ultra-violet (UV) region. Increasing the number of layers is further implemented to tune the band structure of the two homostructures. Consequently, giant SPC peaks about 3 times larger than those of the 2-layers is predicted at photon energies 7.40 eV and 5.95 eV in the 5-layers of h -BN and β-GeS, respectively. The two homostructures may thus be promising building blocks for next-generation shift current devices. These findings also suggest layering as a possible convenient approach of enhancing and also tuning the SPC output in thin layered materials. © 2022, The Authors. All rights reserved.

关键词： Van der Waals forces

来源：评论

学校读者我要写书评

暂无评论

α [email protected] carrier modulated platinum single atoms for high-efficient solar cells

引用

Applied Surface science 2023年 611卷

作者： Jixin Yao Jie Wang Wen Wang Ying Meng Haibo Wang Shibin Lu Feng Du Li Yang Xueqin Zuo Guang Li Anhui Province Key Laboratory of simulation and design for Electronic information system Universities Joint Key Laboratory of photoelectric detection Science and Technology in Anhui Province Hefei Normal University Hefei 230601 China School of Materials Science and Engineering Anhui Key Laboratory of Information Materials and Devices Key Laboratory of Structure and Functional Regulation of Hybrid Materials of Ministry of Education Institute of Physical Science and Information Technology Anhui University Hefei 230601 China Institute of Materials Science and Devices School of Materials Science and Engineering Suzhou University of Science and Technology Suzhou 215011 China

Single-atom electrocatalysts have been proven to be the great promising catalysts for energy-related fields yet their active site structure remains elusive, especially in dye-sensitized solar cell (DSSC). Herein, atomically dispersed Pt is anchored into α [email protected] carrier (Pt/α [email protected] ), which vigorously stimulates the activity of Pt single atoms under the strong metal interaction. As expected, the Pt/α [email protected] as the cathode in DSSC exhibits high power conversion efficiency (PCE) of 9.67%, exceeding Pt electrode (7.61%). X-ray photoelectron spectroscopy combined with density functional theory calculations reveals that the high activity is mainly derived from charge re-distribution of Pt/α [email protected] caused by the interaction between Pt atoms and α-MoC. This interaction not only achieves the optimized adsorption/desorption energy of reactants but also brings synergic advantages to expedite the reaction kinetics of the overall system. This work paves further research prospects for charge re-distribution, stimulating electrocatalysts to effectively enhance their catalytic properties by an atomic-level engineering strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boron concentration field measurement and mixing analysis in the annular downcomer of reactor pressure vessel 27

Boron concentration field measurement and mixing analysis in...

引用

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

作者： Zhang, Qi Tan, Sichao Zhao, Hangbin Wang, Peng Gu, Hanyang Yang, Yunjia School of Nuclear Science and Engineering Shanghai Jiao Tong University Shanghai China Fundamental Science on Nuclear Safety and Simulation Technology Laboratory Harbin Engineer University Harbin Heilongjiang China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China

ISBN: (纸本)9784888983051

In nuclear power plant, the reactor annular downcomer acts as the upstream of the reactor core, and boric distribution inside the downcomer is focused in the ECC situation. The relevant study indicates that the inlet coolant does not flow along annular channel directly, and the current multi primary loops layout makes the fluid mixing of the downcomer far more complex. In this paper, boron transport and mixing phenomenon inside the reactor annular downcomer were analyzed by Laser Induced Fluorescence (LIF) method, a reduziertreduced RPV model was built with transparent material, the boric acid was equivalently simulated by rhodamine B. The single loop and double loops flow mixing tests were respectively performed, the qualitative and quantitative data at cross sections were acquired. For the single loop test, the injected tracer transported along the circumferential position and was constantly diluted by the ambient pure water;meanwhile, a portion of the injection entered the lower space and filled up the annular channel in the same manner. From the time evolution of concentration gradient distribution, the increasement of inlet velocity is favorable to the uniform mixing. For the double loops fluid mixing tests, the tracer solution and pure water were injected into the model simultaneously through two independent entrances. The location of the intersection boundary of the two fluids was affected by the entrance momentum ratio, and the tracer distribution fluctuated remarkably in the lower space of the downcomer. Copyright © 2018-2019 by JSME

关键词： Boric acid

来源：评论

学校读者我要写书评

暂无评论

Drought frequency, intensity, and exposure have increased due to historical land use and land cover changes

Communications Earth & Environment

引用

Communications Earth & Environment 2025年第1期6卷 1-13页

作者： Tao Tang Lin Wang Junji Cao Jun Ge Haiyun Shi Xuhui Lee State Key Laboratory of Earth System Numerical Modeling and Application Institute of Atmospheric Physics Chinese Academy of Sciences Beijing China Science Center for Earth System Numerical Simulation Institute of Atmospheric Physics Chinese Academy of Sciences Beijing China CAS Key Laboratory of Regional Climate-Environment for Temperate East Asia Institute of Atmospheric Physics Chinese Academy of Sciences Beijing China Joint International Research Laboratory of Atmospheric and Earth System Sciences School of Atmospheric Sciences Nanjing University Nanjing China School of Environmental Science and Engineering Southern University of Science and Technology Shenzhen China School of the Environment Yale University New Haven CT USA

Drought, a marked deficiency of surface water, has a wide adverse impact on the environment, agriculture, and the socio-economy. The global impact of land use changes on drought features and associated exposures to droughts, however, remains largely unknown. In this study, the changes of drought features are estimated by using the model simulations with and without land use change. We show that historical land use changes since 1850, mainly deforestation and crop expansion, has increased the drought frequency, duration, and severity over half of the global land area. Regions with greater activity tend to experience stronger exacerbation of drought events. Owing to their increasing frequency and prolonged duration, populations, croplands and forests are increasingly exposed to drought events, which poses serious potential impacts on human health, agriculture, and forest ecosystems. The enhanced drought events could be substantially alleviated by potential reforestation activity. Our results provide useful information for land-management-related policy-making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stability and energetics of two-dimensional surface crystals in liquid AuSi thin films and nanoscale droplets

引用

Physical Review Materials 2021年第7期5卷 074003-074003页

作者： Hailong Wang Mengyuan Wang Alireza Shahabi Alain Karma Moneesh Upmanyu CAS Key Laboratory of Mechanical Behavior and Design of Materials Department of Modern Mechanics CAS Center for Excellence in Complex System Mechanics University of Science and Technology of China Hefei Anhui 230027 China Group for Simulation and Theory of Atomic-Scale Material Phenomena (stAMP) Department of Mechanical and Industrial Engineering Northeastern University Boston Massachusetts 02115 USA Department of Physics Northeastern University Boston Massachusetts 02115 USA

We employ atomic-scale computational frameworks to study the surface crystallization in AuSi films and droplets as a function of composition, temperature, and size. Above the melting point, the surfaces of both thin films and droplets undergo a first-order transition from a two-dimensional (2D) Au2Si crystalline phase to a laterally disordered yet stratified layer. The thin film surfaces exhibit an effective surface tension that increases with temperature and decreases with Si concentration, while for droplets in the size range 10–30 nm, the bulk Laplace pressure alters the surface segregation as it occurs with respect to a strained bulk. Above the transition, the size effect on the surface tension due to the stratified surface layer is small, while the crystalline surface layer below the transition is strained and composed of 2D crystallites separated by extended grain boundary scars that lead to large fluctuations in its energetics. As a specific application, all-atom simulations of AuSi droplets on Si(111) substrate subject to Si surface flux show that the supersaturation dependent surface tension destabilizes the contact line via formation of a precursor wetting film on the solid-vapor interface and has ramifications for size selection during droplet-catalyzed routes for nanowire growth. Our study sheds light on the interplay between stability and energetics of surfaces in this unique class of binary alloys and offers pathways for exploiting their surface structure for varied applications such as catalytic nanocrystal growth, dealloying, and polymer crystallization.

关键词： Crystal forms Growth Interface & surface thermodynamics Nanocrystals Structural phase transition 2-dimensional systems Surfaces Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Distributed Coordinated Emergency Frequency Control Strategy for Renewables-Rich Power systems Based on Multi-Agent Reinforcement Learning

SSRN

引用

SSRN 2025年

作者： Sun, Zhenglong Han, Junpeng Chen, Weihan Zhang, Rui Liu, Yong Levron, Yoash Belikov, Juri Department of Electrical Engineering Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin China The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering Technion—Israel Institute of Technology Haifa3200003 Israel Department of Software Science Tallinn University of Technology Akadeemia Tee 15a Tallinn12618 Estonia

With the rapid growth of renewable energy in the power system and the implementation of large-capacity LCC-HVDC projects, the frequency support capability of the grid has been reduced. Simultaneously, the renewables-rich grid faces the risk of high-power shocks due to LCC-HVDC blocking. Existing centralized, single-measure approaches and the model-based emergency frequency control (EFC) methods are facing tremendous challenges. To fill this gap, this paper proposes a frequency emergency control method for renewables-rich grids that coordinates LCC-HVDC emergency power support and load shedding. The coordination of the two stabilization measures is modeled as a decentralized partially observable Markov decision process, and a multi-agent reinforcement learning (MADRL) approach is employed to optimize the power of measures for each stabilization control substation. An MADRL algorithm that integrates the system frequency response model is developed to overcome the problem of inaccurate evaluation of centralized action value in the MADRL algorithm used for EFC. This approach allows for the global optimization of the distributed coordination strategy through centralized training. The effectiveness and adaptability of the proposed method are demonstrated through simulations of the modified IEEE 39-bus system. © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement 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：