检索结果-内蒙古大学图书馆

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Cheng, Yubin Song, Zhihuan Jiang, Xiaoyu Yao, Le Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Industrial Process Control College of Control Science and Engineering Hangzhou310027 China School of Mathematics Hangzhou Normal University Hangzhou China

ISBN: (纸本)9798350361674

In recent years, pre-trained foundation models have developed rapidly and have been applied to various downstream tasks through fine-tuning methods. However, due to the existence of data silos, the lack of data for fine-tuning has become a vital issue preventing the application of the foundation model to industry. In addition, the high complexity of the network makes the foundation model prone to overfitting when used for data-constrained industrial tasks. Therefore, a federated tuning approach with adaptive weight shrinking, named FedAWS, is proposed for collaborative fine-tuning between factories. FedAWS adaptively selects the weight-shrinking factor to reduce overfitting and improve the generalization of the global model without relying on additional data sets or human experience. The case study on an industrial dataset demonstrates the effectiveness of FedAWS. This successful validation provides a new way for inter-factory collaboration to apply the foundation model to industry, thus facilitating the efficient utilization of industrial data. © 2024 IEEE.

关键词： Federated Learning Fine-tuning Foundation Model Weight Shrinking

来源：评论

学校读者我要写书评

暂无评论

Use of forestry waste as an alternative raw material for generating metallurgical coke

引用

Journal of Iron and Steel Research International 2025年第1期32卷 25-39页

作者： Lin-bo Qin Wei Qin An-yi Wang Ling Shi Jun Han College of Resources and Environment Engineering Wuhan University of Science and TechnologyWuhan430081HubeiChina Hubei Key Laboratory of Industrial Fume and Dust Pollution Control Jianghan UniversityWuhan430056HubeiChina Hubei Key Laboratory for Efficient Utilization and Agglomeration of Metallurgic Mineral Resources Wuhan University of Science and TechnologyWuhan430081HubeiChina

Forestry waste(FW)is a significant renewable energy source in *** substitution of coal blends(BC)with forestry waste to produce metallurgical coke was investigated aiming at expanding alternative resources and reducing CO_(2)emissions in ironmaking *** BC with different ratios of FW were carbonized in a fixed bed reactor,and the physicochemical structure of the coke derived from FW/BC co-carbonization was characterized by Fourier transform infrared spectroscopy,X-ray photoelectron spectroscopy,solid-state^(13)C nuclear magnetic resonance,optical microscopy,and scanning electron *** results reveal that the suitable incorporation of FW in BC is 10 wt.%,and the index of coke quality exhibits a good correlation with the optical anisotropy index and the aromaticity of the as-obtained *** partial substitution of BC with FW exhibits potential benefits for colloid formation,owing to the higher hydrogen in ***,as the substitution ratio of BC with FW increases,it inhibits coke agglomeration due to more tortuous stacked structures formation during volatile releasing ***,it was identified that the substitution of higher BC ratios with FW results in the partial replacement of aromatic carbons by oxygenlinked carbons and aliphatic *** substitution leads to a reduction in the aromaticity of the as-obtained coke.

关键词： Metallurgical coke Forestry waste Coal blend Co-carbonization Chemical structure

来源：评论

学校读者我要写书评

暂无评论

CDQKL: Consensus-Based Distributed Quantum Kernel Learning 1

CDQKL: Consensus-Based Distributed Quantum Kernel Learning

引用

1st International Conference on Quantum Communications, Networking, and Computing, QCNC 2024

作者： Ma, Wenxuan Liu, Mengxiang Deng, Ruilong State Key Laboratory of Industrial Control Technology The College of Control Science and Engineering Zhejiang University Hangzhou310027 China University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom

ISBN: (纸本)9798350366778

The field of quantum computing has developed rapidly in recent years due to its promising trend of surpassing traditional machine learning in terms of speed and effectiveness. Quantum kernel learning is one of the paradigms of quantum machine learning, but the training of quantum kernel is time consuming. Therefore, this work makes the first attempt to introduce a consensus-based distributed approach to quantum kernel learning - named CDQKL - that only requires to exchange model parameter information between adjacent nodes while avoiding the need of sharing local training data. Through comparative experimental studies, the advantages of CDQKL in classification accuracy and convergence speed are verified. Considering the popularization of quantum computing cloud service and miniaturization of quantum terminals, the CDQKL adapting to this trend is able to play a vital role in data security, which implies the far-reaching significance of this work. Our code is available at https://***/Leisurivan/CDOKL. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Attacks on Data-Driven Process Monitoring Systems: Subspace Transfer Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第3期3卷 470-484页

作者： Jiang, Xiaoyu Ge, Zhiqiang Zhejiang University State Key Laboratory of Industrial Control Technology Institute of Industrial Process Control College of Control Science and Engineering Hangzhou310027 China Peng Cheng Laboratory Shenzhen518000 China

With the rapid development of information technology, intelligent upgrading of the manufacturing industry has broken the closed environment of traditional industrial control systems (ICS);thus, the information security of ICS has been seriously threatened. As part of ICS, the process monitoring system (PMS) is heavily subject to external risks. Data-driven PMSs have been widely used as initial lines of defense to ensure ICS safety. Once the PMS is under attack, the consequences on the whole ICS will be unimaginable. Unfortunately, the safety issues of the PMS have received inadequate attention. This article reveals PMS's vulnerabilities through effective attacks. A novel method called subspace transfer network (STN) is proposed to conduct adversarial and poisoning attacks on the PMS simultaneously. Then the attack task flow is defined and explained to make online adversarial attacks and data poisoning on PMS. Meanwhile, aiming at two poisoning goals, targeted and untargeted attacks of STN are designed, respectively. Finally, the PMS's fragility is verified in two industrial benchmarks. © 2020 IEEE.

关键词： Security of data

来源：评论

学校读者我要写书评

暂无评论

Drift-free localisation using prior cross-source map for indoor low-light environments

引用

IET Cyber-Systems and Robotics 2023年第1期5卷 122-131页

作者： Junyi Tao Weichen Dai Da Kong Jiayan Wan Bin He Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhouChina School of Computer Science Hangzhou Dianzi UniversityHangzhouChina Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province HangzhouChina

In this study,a localisation system without cumulative errors is ***,depth odometry is achieved only by using the depth information from the depth *** the point cloud cross-source map registration is realised by 3D particle filtering to obtain the pose of the point cloud relative to the ***,we fuse the odometry results with the point cloud to map registration results,so the system can operate effectively even if the map is *** effectiveness of the system for long-term localisation,localisation in the incomplete map,and localisation in low light through multiple experiments on the self-recorded dataset is *** with other methods,the results are better than theirs and achieve high indoor localisation accuracy.

关键词： indoor positioning robots

来源：评论

学校读者我要写书评

暂无评论

Impact Analysis of MTD on the Frequency Stability in Smart Grid

引用

IEEE/CAA Journal of Automatica Sinica 2023年第1期10卷 275-277页

作者： Zhenyong Zhang Ruilong Deng the State Key Laboratory of Public Big Data and the College of Computer Science and Technology Guizhou UniversityGuiyang 550025China IEEE the State Key Laboratory of Industrial Control Technology Zhejiang UniversityHangzhou 310027China

Dear Editor, In order to accommodate the effects of false data injection attacks(FDIAs), the moving target defense(MTD) strategy is recently proposed to enhance the security of the smart grid by perturbing branch susceptances. However, most pioneer work only focus on the defending performance of MTD in terms of detecting FDIAs and the impact of MTD on the static factors such as the power and economic losses.

关键词： Smart MTD Impact

来源：评论

学校读者我要写书评

暂无评论

Prediction model on hydrolysis kinetics of phthalate monoester:A density functional theory study

引用

Journal of Environmental sciences 2024年第1期135卷 51-58页

作者： Tong Xu Jingwen Chen Deming Xia Weihao Tang Jiansheng Cui Chun Liu Shuangjiang Li College of Environmental Science and Engineering Hebei University of Science and TechnologyShijiazhuang 050000China Key Laboratory of Industrial Ecology and Environmental Engineering(Ministry of Education) School of Environmental Science and TechnologyDalian University of TechnologyDalian 116024China National-Regional Joint Engineering Research Center for Soil Pollution Control and Remediation in South China Guangdong Key Laboratory of Integrated Agro-environmental Pollution Control and ManagementInstitute of Eco-environmental and Soil SciencesGuangdong Academy of SciencesGuangzhou 510650China

As primary degradation products of phthalate esters,phthalate monoesters(MPEs)have been widely detected in various aquatic environments and drawn growing toxicological *** kinetics that is of importance for assessing environmental persistence of chemicals remain elusive for ***,kinetics of base-catalyzed and neutral hydrolysis for 18 MPEs with different leaving groups was investigated by density functional theory *** indicate that MPEs with leaving groups having p Kaof<10 prefer dissociative transition *** are more persistent than their parents,and their hydrolysis half-lives were calculated to vary from 3.4 min to 79.2 years(p H=7–9).A quantitative structure-activity relationship model was developed for predicting the hydrolysis kinetics *** was found that p Kaof the leaving groups and electronegativity of the MPEs are key factors determining the hydrolysis *** work may lay a theoretical foundation for better understanding the chemical process that governs MPE persistence in aquatic environments.

关键词： Phthalate monoesters Phthalate esters Hydrolysis Density functional theory Quantitative structure-activity relationship

来源：评论

学校读者我要写书评

暂无评论

Cut-wire metasurface embedded in magnetic mediums for ultra-wideband polarization-insensitive absorber with environmental adaptability

引用

Journal of Materials science & technology 2024年第11期178卷 162-170页

作者： Jiangyong Liu Yuping Duan Tuo Zhang Yanan Liu Wei Chen Yupeng Shi Lingxi Huang Huifang Pang Key Laboratory of Solidification Control and Digital Preparation Technology(Liaoning Province) School of Materials Science and EngineeringDalian University of TechnologyDalian 116085China Key Laboratory of Functional Nanocomposites of Shanxi Province College of Materials Science and EngineeringNorth University of ChinaTaiyuan 030051China

Metamaterials with artificial designability and perfect absorption provide a novel design method for the manipulation and attenuation of ***,owing to the limitations of meta-atomic reso-nance effect and the lossless medium,it is difficult to achieve effective microwave absorption in a broad-band frequency ***,an ultra-wideband metamaterial absorber(UWMA)composed of two mag-netic media and a metasurface was designed,and the absorption bandwidth of 2.9 to 18 GHz for 90%absorptivity under normal incidence was achieved,covering almost the entire S,C,X,and Ku *** detailed investigation of equivalent circuit,equivalent medium theory,electromagnetic field dis-tribution and front-back interface interference,the internal physical working mechanism was clarified *** addition,the multi-environment adaptabilities of the proposed absorber,including polariza-tion sensitivity,large angle incidence,dual-station radar stealth,bearing capacity and corrosion resistance,were *** proposed metamaterial absorber presents an effective way to achieve ultra-wideband absorption and compatibility with environmental adaptability,and provides a new way of thinking for intelligent full-band stealth technology.

关键词： Metamaterial Microwave absorber Ultra-wideband Environmental adaptability Polarization-insensitive

来源：评论

学校读者我要写书评

暂无评论

ERASOR++: Height Coding Plus Egocentric Ratio Based Dynamic Object Removal for Static Point Cloud Mapping

ERASOR++: Height Coding Plus Egocentric Ratio Based Dynamic ...

引用

2024 IEEE International Conference on Robotics and Automation, ICRA 2024

作者： Zhang, Jiabao Zhang, Yu Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou China Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province Hangzhou China

ISBN: (纸本)9798350384574

Mapping plays a crucial role in location and navigation within automatic systems. However, the presence of dynamic objects in 3D point cloud maps generated from scan sensors can introduce map distortion and long traces, thereby posing challenges for accurate mapping and navigation. To address this issue, we propose ERASOR++, an enhanced approach based on the Egocentric Ratio of Pseudo Occupancy for effective dynamic object removal. To begin, we introduce the Height Coding Descriptor, which combines height difference and height layer information to encode the point cloud. Subsequently, we propose the Height Stack Test, Ground Layer Test, and Surrounding Point Test methods to precisely and efficiently identify the dynamic bins within point cloud bins, thus overcoming the limitations of prior approaches. Through extensive evaluation on open-source datasets, our approach demonstrates superior performance in terms of precision and efficiency compared to existing methods. Furthermore, the techniques described in our work hold promise for addressing various challenging tasks or aspects through subsequent migration. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Self-Contrastive Learning Fault Diagnosis Network for Signal Imaging: A Case Study

Self-Contrastive Learning Fault Diagnosis Network for Signal...

引用

2024 China Automation Congress, CAC 2024

作者： He, Wenbin Mao, Jianxu Wang, Yaonan Li, Zhe Yan, Feng Liu, Kexin College of Electrical & Information Engineering National Engineering Research Center of Robot Visual Perception & Control Technology Hunan University Hunan China College of Control Science & Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Zhejiang China

ISBN: (纸本)9798350368604

The deep convolution method based on MSDP signal imaging has been proven to be an effective means of monitoring the robot grinding process. This method has very high requirements on the quality of imaging and requires a lot of computing resources. This paper proposes an image self-contrastive learning network that can effectively extract fault information from low-pixel fuzzy images and achieve efficient and accurate condition monitoring. The network first calculates the correlation distance matrix between two identical modified symmetrized dot pattern (MSDP) images and uses the generated similarity labels to calculate the contrast loss to extract the embedded features of the image. Finally, the classification network is trained using the cross entropy loss to achieve the classification of fault images. The method was verified on a robotic grinding platform to significantly reduce the calculation time while maintaining the recognition accuracy, which provides reliable technical support for the real-time monitoring of the robotic grinding process. © 2024 IEEE.

关键词： Contrastive Learning fault diagnosis robotic grinding signal imaging

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：