检索结果-内蒙古大学图书馆

Towards understanding structure–property relations in materials with interpretable deep learning

npj Computational Materials 2023年第1期9卷 157-168页

作者： Tien-Sinh Vu Minh-Quyet Ha Duong-Nguyen Nguyen Viet-Cuong Nguyen Yukihiro Abe Truyen Tran Huan Tran Hiori Kino Takashi Miyake Koji Tsuda Hieu-Chi Dam Japan Advanced Institute of Science and Technology NomiIshikawaJapan HPC SYSTEMS Inc. MinatoTokyoJapan Applied Artificial Intelligence Institute Deakin UniversityGeelongVICAustralia School of Materials Science and Engineering Georgia Institute of TechnologyAtlantaGAUSA Research and Services Division of Materials Data and Integrated System National Institute for Materials ScienceTsukubaIbarakiJapan Research Center for Computational Design of Advanced Functional Materials National Institute of Advanced Industrial Science and TechnologyTsukubaIbarakiJapan Department of Computational Biology and Medical Sciences Graduate School of Frontier SciencesUniversity of TokyoKashiwa-shiChiba-kenJapan International Center for Synchrotron Radiation Innovation Smart(SRIS) Tohoku UniversityAoba-kuSendaiJapan

Deep learning(DL)models currently employed in materials research exhibit certain limitations in delivering meaningful information for interpreting predictions and comprehending the relationships between structure and material *** address these limitations,we propose an interpretable DL architecture that incorporates the attention mechanism to predict material properties and gain insights into their structure–property *** proposed architecture is evaluated using two well-known datasets(the QM9 and the Materials Project datasets),and three in-house-developed computational materials ***–test–split validations confirm that the models derived using the proposed DL architecture exhibit strong predictive capabilities,which are comparable to those of current state-of-the-art ***,comparative validations,based on first-principles calculations,indicate that the degree of attention of the atoms’local structures to the representation of the material structure is critical when interpreting structure–property relationships with respect to physical *** properties encompass molecular orbital energies and the formation energies of *** proposed architecture shows great potential in accelerating material design by predicting material properties and explicitly identifying crucial features within the corresponding structures.

关键词： properties property structure

来源：评论

学校读者我要写书评

暂无评论

Hybrid Atom Search-Heap Energy Optimization Algorithm for Dynamic Topology in Underwater Acoustic Sensor Network 6

Hybrid Atom Search-Heap Energy Optimization Algorithm for Dy...

引用

6th International Conference on Devices, Circuits and systems, ICDCS 2022

作者： Ayyadurai, M. Vasanth Raj, P.T. Vijayaraj, A. Dhanagopal, R. Suresh Kumar, R. SRM Institute of Science and Technology Ramapuram Campus Department of Ece Chennai India Center for System Design Chennai Institute of Technology Department of Ece Chennai India Vignan's Foundation for Science Technology & Research Dept. of Information Technology Andhra Pradesh India

ISBN: (纸本)9781665480949

Benefits obtained from the water resources are many in terms of renewable energy, food, materials, communication and security. Monitoring, sensing, routing and analysis of underwater happenings is the challenging task in a sparse environment. Due to the dynamic nature of underwater topology, routing among the nodes is a complex task, hence optimal node identification is mandatory for enhancing network performance. The environment and vast area of ocean makes it highly unlikely for humans to explore and monitor as a challenging task and more cost then manual labour. Hence, economical solutions for monitoring and exploration applications in the ocean are possible with Underwater Acoustic Sensor Network (UWASN). This work proposes a meta-heuristic novel hybrid Atom searchHeap optimization (NHASHO) algorithm to enhance the network performance in terms of energy, end-to-end delay and throughput. The NS2 simulation results show that the proposed work outperforms with existing Cat Optimization algorithm (CAO) for dynamically varying underwater topology condition. © 2022 IEEE.

关键词： Network topology Heuristic algorithms Oceans Throughput Routing Topology Task analysis

来源：评论

学校读者我要写书评

暂无评论

Coupled Carbon Fiber Structural Battery Composites with Reinforced Interfaces to Improve Multifunctional Performance

SSRN

引用

SSRN 2024年

作者： Liu, Xu Peng, Yilin Zhou, Limin School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shen Zhen518055 China

Carbon fiber structured batteries are multifunctional composites that can simultaneously serve as power sources and structural load-bearing components of vehicles. By reducing system weight to increase the cruising range, the structural batteries have potential applications in electric vehicles, drones, and airplanes, etc. Herein, an interfacial engineering is adopted to increase the multifunctional performance of structural batteries composites. The carbon fiber structural electrodes are reinforced with an epoxy-based binder, strengthening the interfacial bonding between active materials and carbon fiber. The solid-state electrolyte is assembled with the continuous phase, delivering high mechanical strength to support load and ionic conductivity at the interface between electrode and electrolyte. A coupled Zn-ions structural battery is fabricated with the optimized structural electrode and solid-state electrolyte, which demonstrates both high mechanical properties (flexural strength: 206.1±5 MPa, flexural modulus: 9.8 GPa) and high energy density of 7.8Wh kg-1 with a power density of 1.6 W kg-1 based on the total mass of the device. Furthermore, the in situ electrochemical-mechanical and extreme environmental testing confirm the device's electrochemical durability and structural stability. Therefore, this study will provide a guideline for designing and fabricating safe, high-energy density, and mechanically robust carbon fiber structural energy storage composites. © 2024, The Authors. All rights reserved.

关键词： Environmental testing

来源：评论

学校读者我要写书评

暂无评论

Corrosion Mechanisms and Differences of Inconel 617 and Incoloy 800h Under High-Temperature Air Ingress Accident

SSRN

引用

SSRN 2024年

作者： Li, Haoxiang Yan, Dapeng Li, Guodong Tian, Changqing An, Jiayi Tan, Jiaqi Zheng, Wei Du, Bin Yin, Huaqiang Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China State Key Laboratory of Advanced Nuclear Energy Technology Nuclear Power Institute of China Chengdu China Institute of Nuclear and New Energy Technology Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education Tsinghua University Beijing China Tsinghua University China

In the high-temperature operation of very high-temperature gas-cooled reactors (VHTRs), "microclimate reaction" are one of the key corrosion reactions of concern. This study investigates the corrosion behavior and mechanisms of the two mainstream high-temperature alloys, Incoloy 800H and Inconel 617, under minor air ingress accidents. The main focus is on comparing and analyzing the "microclimate reaction" corrosion behavior and mechanisms of the two alloys, as well as exploring changes in their mechanical properties. The results show that during the experiment, both alloys primarily underwent oxidation and "microclimate reaction". The double-layer oxide of Cr2 O3 -MnCr2 O4 /MnFe2 O4 and the SiO2 layer on the surface of Incoloy 800H provide good resistance to "microclimate reaction," whereas the single-layer Cr2 O3 oxide on Inconel 617 is not effective in preventing "microclimate reaction". The mechanical property test results indicate that the decarburization caused by "microclimate reaction" does not significantly affect the basic mechanical properties of the alloy. Research on "microclimate reactions" should primarily focus on preventing the oxidation layer from cracking and reducing the time during which the alloy matrix is unprotected by a protective oxide layer. © 2024, The Authors. All rights reserved.

关键词： Gas cooled reactors

来源：评论

学校读者我要写书评

暂无评论

Application Research of Computational design Aesthetics 4

Application Research of Computational Design Aesthetics

引用

4th International Conference on Intelligent design, ICID 2023

作者： Zhou, Ding Huang, Jiawei Zhang, Yukun Liu, Bingjian Southern University of Science and Technology School of System Design and Intelligent Manufacturing Shenzhen518055 China University of Nottingham Ningbo China Department of Mechanical Materials and Manufacturing Engineering Ningbo315000 China

ISBN: (纸本)9798350342574

This study explores the application of computational design aesthetics to conform to Chinese aesthetic standards in customized glasses frames. Through quantitative analysis, it examines the impact of key design variables (upper frame position, middle beam height, and lower frame position) on the aesthetics of wearing. The results indicate that achieving a better aesthetic feeling can be attained when the upper frame of the glasses is approximately 20% above the vertical distance between the eyebrow and eye, the middle beam is about 20% above the height of the frame, or the lower frame is roughly 40% above the vertical distance between the lower eyelid and the angle of the mouth. These findings hold significant value for the eyewear industry and cultural confidence. They empower enterprises to leverage computational design tools, enhancing the harmony and attractiveness of individual facial frames, catering to the preferences of the Chinese market, and deepening the understanding of cultural factors in aesthetic perception. Furthermore, it contributes to realizing the goal of socialist cultural confidence with Chinese characteristics. In conclusion, this study is a valuable reference for creating eyewear frames that exude individual and cultural confidence, fostering innovation in the eyewear industry and the principles of harmonious design aesthetics. © 2023 IEEE.

关键词： Glass

来源：评论

学校读者我要写书评

暂无评论

Network-Transparent Load Balancing and Migration for Edge Computing

Network-Transparent Load Balancing and Migration for Edge Co...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Yohei Namba Ryo Morishima Hiroaki Nishi Graduate School of Science and Technology Keio University Yokohama Kanagawa Japan Department of System Design Faculty of Science and Technology Keio University Yokohama Kanagawa Japan

The network infrastructure in a smart community uses the cloud and compute servers, and the edge and fog areas to perform processing in the optimal place. Nodes in the edge and fog areas have various processing capacities, and there must be load-balancing mechanisms to meet the requirements of applications. However, Internet of Things (IoT) devices are generally small, computationally constrained, and numerous, so reconfiguration and functionality updates for the network must be kept to a minimum. In addition, if nodes establish connections with other nodes to exchange their information, the number of connections will be large, and communication costs will be high. In this study, we use nodes called “Distributor” that can monitor data flow through the network without changing the existing infrastructure. Piggyback technique is used to add information onto the packets flowing in the network. Distributors add the information to the packets and exchange information to each other without establishing connections with other nodes, and they perform load balancing based on the information. By changing and migrating the processing locations among Distributors, IoT devices can continue to communicate with other nodes even during load balancing. Experiments confirmed that load balancing could be performed to prepare for sudden load increases and that the impact of piggybacking on occupied bandwidth and processing delay was 0.177% and 0.06%, respectively. We also confirmed that sensor data can be sent without reconnecting communications, even during load balancing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simple Method to Measure the Contact Angle of Metal Droplets on Graphite

引用

Nanomanufacturing and Metrology 2023年第4期6卷 35-45页

作者： Bozhao Wu Yongping Kang Cai Lu Langquan Shui Wengen Ouyang Qi Peng Qiankun He Ze Liu Department of Engineering Mechanics School of Civil EngineeringWuhan UniversityWuhan 430072HubeiChina School of Civil Engineering Architecture and Environment Hubei University of TechnologyWuhan 430068HubeiChina System Design Institute of Hubei Areospace Technology Academy Wuhan 430040China State Key Laboratory of Water Resources and Hydropower Engineering Science Wuhan UniversityWuhan 430072China

The determination of solid–liquid interfacial tension plays an important role in science and ***,we propose a simple method to directly measure the contact angle between metal droplets and a graphite substrate for the determination of metal–graphite interfacial *** proposed method involves the synthesis of micro-and nanosized metal droplets on graphite by arc *** to its small volume,the rapid cooling of the prepared metal droplets on the graphite substrate leads to the freezing of equilibrium contact confguration after *** observe that the measured contact angle between micro-and nanosized Au(or Ag)particles and the graphite substrate is almost size independent,even though the size of the particles synthesized herein is 1–3 orders of magnitude smaller than that studied in previous *** addition,the interfacial tensions of Au and Ag on the step edges(edge plane)of graphite are found to be larger than that on the(0001)plane(basal plane).The proposed method provides a simple approach to determine the solid–liquid interfacial tension and may be efective in the study of interface related science and technology.

关键词： Metal droplets Graphite/graphenes Contact angle Interfacial tension

来源：评论

学校读者我要写书评

暂无评论

Attention-PVS for Domestic Hot Water Consumption Forecasting in Individual Household 49

Attention-PVS for Domestic Hot Water Consumption Forecasting...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Sonoda, Ayu Compagnon, Paul Reyboz, Marina Nishi, Hiroaki Graduate School of Science and Technology Keio University Yokohama Japan Univ. Grenoble Alpes CEA List GrenobleF-38000 France Univ. Grenoble Alpes CEA List Grenoble France Keio University Faculty of Science and Technology Department of System Design Yokohama Japan

ISBN: (纸本)9798350331820

Short-term hot water consumption forecasting in an individual household is important to realize energy-efficient hot water management while meeting users' comfort. However, consumption traits in an individual household contain much irregularity, and that gives additional challenges to accurate forecasting. This paper proposes an Attention-PVS model to tackle this issue, which focuses on consumption values with similar past consumption trends. In this study, verification experiments were conducted on a real-household hot water consumption dataset collected by Electricity of France. The model was evaluated with its consumption forecasting error with MAE, MSE, and RMSE metrics and computational costs. As for the computational cost, experiments were conducted on NVIDIA Jetson Nano (Jetson) to validate the applicability to embedded systems. The results revealed that the proposed model performs consumption forecasting with comparable accuracy to other state-of-the-art models. Additionally, while LSTM scored lower error than the proposed model, Attention-PVS performed training and inference on Jetson in shorter times than LSTM. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Generative design for Buffer Layer Structures 4

Generative Design for Buffer Layer Structures

引用

4th International Conference on Intelligent design, ICID 2023

作者： Zhou, Ding Huang, Jiawei Zhang, Zhengxiang Liu, Bingjian Southern University of Science and Technology School of System Design and Intelligent Manufacturing Shenzhen518055 China University of Nottingham Ningbo China Department of Mechanical Materials and Manufacturing Engineering Ningbo315000 China

ISBN: (纸本)9798350342574

Discarded used tires, commonly referred to as 'black pollution', are a significant environmental issue. Airless tires have been considered as a potential solution, but their adoption is impeded by their stiff ride quality. This study leverages generative design methods to optimize the structure and form of the buffer layer in airless bicycle tires, striving to create a safe, durable, and high-performance tire with characteristics akin to those of pneumatic tires. The research delves into thousands of design possibilities using parametric model generation, finite element analysis, and genetic algorithms, with the aim of generating designs that fulfill all requirements effectively. The proposed method could significantly reduce waste and improve the cycling experience by offering a reliable alternative to conventional tires. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Few-Shot Relation Extraction via Representation Learning and Domain Adaptation

Cross-Domain Few-Shot Relation Extraction via Representation...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhongju Yuan Zhenkun Wang Genghui Li School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the few labeled sentences embedding with the embeddings of the query sentences using a trained metric function. However, as these domains always have considerable differences from those in the training dataset, the generalization ability of these approaches on unseen relations in many domains is limited. Since the prototype is necessary for obtaining relationships between entities in the latent space, we suggest learning more interpretable and efficient prototypes from prior knowledge and the intrinsic semantics of relations to extract new relations in various domains more effectively. By exploring the relationships between relations using prior information, we effectively improve the prototype representation of relations. By using contrastive learning to make the classification margins between sentence embedding more distinct, the prototype's geometric interpretability is enhanced. Additionally, utilizing a transfer learning approach for the cross-domain problem allows the generation process of the prototype to account for the gap between other domains, making the prototype more robust and enabling the better extraction of associations across multiple domains. The experiment results on the benchmark FewRel dataset demonstrate the advantages of the suggested method over some state-of-the-art approaches.

关键词：

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：