检索结果-内蒙古大学图书馆

IEEE International Conference on Intelligent Transportation engineering (ICITE)

作者： Liyong Wang Long Jin Haojie Ji Jingyan Wang Yupeng Chen Junzhe Fang State Key Laboratory of Intelligent Vehicle Safety Technology Chongqing China Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science & Technology University Beijing China State Key Laboratory of Intelligent Vehicle Safety Chongqing China China Automotive Engineering Research Institute Co. Ltd Chongqing China

ISBN: (数字)9798350314212

ISBN: (纸本)9798350314229

The rapid development of intelligent and connected vehicle (ICV) has brought increasing communication data and valuable data assets. However, the diversity and complexity of ICV data make it hard to carry out data security risk assessment. Aiming at the problem, this paper proposes an effective analytical method for the data security risk assessment method of ICVs. Considering the typical scenario for the generated data of ICVs, a data security classification and grading framework is constructed from the aspects of in-vehicle data, personal data, and external environment data. The data security risk assessment model is built for ICVs and includes functional modules such as asset identification, threat identification, impact assessment, vulnerability identification, and risk assessment. This work provides methods and security management and control strategy support for ICV data security risk assessment.

关键词： Industries Connected vehicles Data security Security management Transportation Data models Complexity theory Risk management

来源：评论

学校读者我要写书评

暂无评论

Multi-Branch Mutual-Distillation Transformer for EEG-Based Seizure Subtype Classification

arXiv

引用

arXiv 2024年

作者： Peng, Ruimin Du, Zhenbang Zhao, Changming Luo, Jingwei Liu, Wenzhong Chen, Xinxing Wu, Dongrui Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China AI Platform Software Engineering Research Center Dongfeng Corporation Research & Development Institute Wuhan430072 China China Electronic System Technology Co. Ltd. Beijing100089 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen518055 China

Cross-subject electroencephalogram (EEG) based seizure subtype classification is very important in precise epilepsy diagnostics. Deep learning is a promising solution, due to its ability to automatically extract latent patterns. However, it usually requires a large amount of training data, which may not always be available in clinical practice. This paper proposes Multi-Branch Mutual-Distillation (MBMD) Transformer for cross-subject EEG-based seizure subtype classification, which can be effectively trained from small labeled data. MBMD Transformer replaces all even-numbered encoder blocks of the vanilla Vision Transformer by our designed multi-branch encoder blocks. A mutual-distillation strategy is proposed to transfer knowledge between the raw EEG data and its wavelets of different frequency bands. Experiments on two public EEG datasets demonstrated that our proposed MBMD Transformer outperformed several traditional machine learning and state-of-the-art deep learning approaches. To our knowledge, this is the first work on knowledge distillation for EEG-based seizure subtype classification. © 2024, CC BY.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning-Based Energy Management Strategy for Fuel Cell Electric Vehicle Considering Coupled-Energy Sources Degradations

SSRN

引用

SSRN 2023年

作者： Huo, Weiwei Liu, Teng Li, Fajia Institute of Electromechanical Engineering Beijing Information Science & Technology University Beijing100192 China Collaborative Innovation Center of Electric Vehicles in Beijing Beijing Information Science & Technology University Beijing100192 China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing100192 China University of Jinan Jinan250024 China

The energy management strategy (EMS) is crucial for fuel cell electric vehicles (FCEV) by decreasing the equivalent fuel consumption and postponing fuel cell (FC) deterioration. An improved EMS based on the Twin Delayed Deep Deterministic Policy Gradient (TD3) deep reinforcement learning considering energy sources degradation and economic factor is proposed in this paper. The working condition identification (WCI) implemented by ensemble bagged trees (EBT) is used to expand the diversity of EMS application scenarios. The drastic loading change of FC is avoided for minimizing the instantaneous cost (MIC), which reduces FC degradation greatly. TD3 is applied to optimize the total cost combined with WCI and MIC. The training results based on 13 classic working conditions show that the degradation of the FC system is effectively suppressed, decreasing the overall cost and accelerating the algorithm's convergence time significantly. © 2023, The Authors. All rights reserved.

关键词： Energy management

来源：评论

学校读者我要写书评

暂无评论

A Double Node Thin-Film Thermocouples for In-Situ measurement

A Double Node Thin-Film Thermocouples for In-Situ Measuremen...

引用

Automation, Robotics and Computer engineering (ICARCE), International Conference on

作者： Rong Ma Meiju Zhang Zhongkai Zhang Manguo Huang Xiaobo Liang Jiangjiang Liu Zhaojun Liu Bian Tian State Key Laboratory for Mechanical Manufacturing Systems Engineering Xi'an Jiaotong University Xi'an China Beijing Changcheng Aeronautic Measurement and Control Technology Research Institute Aviation Key Laboratory of Science and Technology on Special Condition Monitoring Sensor Technology Beijing China

ISBN: (纸本)9781665475495

The design, fabrication, testing and implementation of a new high-performance tungsten-rhenium thin film thermocouple are introduced. In this paper, tungsten-rhenium TFTCs are taken as the research object, after simulation analysis in COMSOL software and design, it is made by screen-printing technology and magnetron sputtering. This kind of thin film thermocouple primarily utilizes two kinds of electrode materials with varying composition combination, mainly tungsten with 5% rhenium and tungsten with 26% rhenium. Furthermore, high-temperature annealing is performed to maintain the mechanical properties and thus improve thermoelectric performance. The results demonstrate that the performance is reliable in the temperature range of 150-600 C° with a repeatability of 2.02%, providing application value for high-temperature in-situ sensing.

关键词： Temperature measurement Temperature distribution Thermocouples Tungsten Robot sensing systems Software Sensors

来源：评论

学校读者我要写书评

暂无评论

Mechanical Properties and Microstructure of Gnps Toughened Laminated Si3n4-Based Ceramic Tool Materials

SSRN

引用

SSRN 2023年

作者： Zhang, Dachuang Xiao, Guangchun Chen, Hui Yi, Mingdong Zhang, Jingjie Chen, Zhaoqiang Xu, Chonghai School of Mechanical Engineering Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Key Laboratory of Equipments Manufacturing and Intelligent Measurement and Control China National Light Industry Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Shandong Institute of Mechanical Design and Research Jinan250031 China

In this paper, graphene nanoplatelets (GNPs) toughened laminated Si3N4-based composite ceramic tool materials were prepared by SPS-HF sintering, in which Si3N4/TiC and Si3N4/SiC(w)/GNPs composites were used as the interlayer material and surface material, respectively. The effects of sintering temperature, holding time, SiC(w) content and GNPs content on the mechanical properties and microstructure of Si3N4/SiC(w)/GNPs surface materials were studied. The effects of layer number and layer thickness ratio on the mechanical properties and microstructure of GNPs toughened laminated Si3N4-based composites were also analyzed. The small addition of GNPs can improve the conductivity of Si3N4/SiC(w)/GNPs composites, and more GNPs are not conducive to the further improvement of its conductivity. The higher current intensity can promote the sintering of Si3N4/SiC(w)/GNPs composites and the growth of Si3N4 grains in the matrix, which is favorable to the improvement of density. However, the higher current intensity will decrease the flexural strength of the composite. The flexural strength and fracture toughness are 656.2MPa and 8.67 MPa·m1/2 with 0.5wt % content of GNPs, and increased 14.0% and 20.0%, respectively, compared with the monolithic Si3N4/SiC(w) composites. The mechanical properties of GNPs toughened laminated Si3N4-based ceramics tool materials increase with the increase of the layer number and the layer thickness ratio. The best mechanical properties can be obtained with the layer of 7 and layer thickness ratio of 6. The fracture toughness, flexural strength and Vickers hardness are 9.92±0.13 MPa·m1/2, 682±15 MPa and 15.1±0.1 GPa, respectively. Several toughness mechanisms such as crack deflection, crack bridging and GNPs bridging were observed to be responsible for the improvement of fracture toughness of laminated Si3N4-based ceramic tool materials. © 2023, The Authors. All rights reserved.

关键词： Ductile fracture

来源：评论

学校读者我要写书评

暂无评论

Co-Optimization Method for Modular Robots Based on Evolutionary Algorithm

Co-Optimization Method for Modular Robots Based on Evolution...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Peng Zhao Meibao Yao Bo Zheng Xueming Xiao Intelligent Robotics Lab (IRL) School of Artificial Intelligence Jilin University Changchun China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education China Shanghai Aerospace Control Technology Institute Shanghai China CVIR Lab Changchun University of Science and Technology Changchun China Key Lab of Optoelectronic Measurement and Optical Information Transmission Technology

Deploying robots instead of human labor in complex and hazardous environments is a highly effective strategy. However, current fixed-configuration robot platforms struggle to meet the demanding exploration requirements in non-structured environments. In contrast, reconfigurable modular robots are able to adjust their configurations in response to environmental and task requirements, thereby offering immense potential for tackling complex exploration tasks in unstructured environments. This versatility of reconfigurable modular robots allows them to better adapt to various environmental and task demands, such as using snake or caterpillar configurations to navigate narrow holes, or quadruped configurations to traverse rugged terrain. However, the current research on modular robots primarily focuses on optimizing either their own configurations or solely the motion control model, potentially limiting their adaptability to the environment and hindering the full realization of their reconfigurability. To address this limitation, this paper improves upon traditional EA and proposes a configuration-motion co-optimization method and a new encoding method for modular robots, which jointly models and optimizes both configuration and motion. The method includes dynamic encoding of configuration-motion and the design of compatible operators, effectively enhancing the adaptive capabilities of modular robots in complex environments. The method was validated using the Webots platform, and the results demonstrate successful generation of adaptable reconfiguration schemes for various terrains. Compared to traditional EA, this method has shown superior performance in handling diverse tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synergetic Lubrication between Self-Lubricating Ceramic Tools and Nanofluids: Advancing the Application of Self-Lubricating Ceramic Cutting Tools

SSRN

引用

SSRN 2023年

作者： Li, Yifei Chen, Hui Zhang, Jingjie Xiao, Guangchun Yi, Mingdong Chen, Zhaoqiang Xu, Chonghai School of Mechanical Engineering Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Key Laboratory of Equipment Manufacturing and Intelligent Measurement and Control China National Light Industry Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Shandong Machinery Design & Research Institute Jinan250031 China

In the field of ceramic tool processing, the incorporation of solid lubricants into self-lubricating ceramic tools forms a supportive lubricating film during the cutting process, effectively enhancing the cutting performance of the tools. Concurrently, Nanofluid Minimum Lubrication technology (NMQL), as an emerging lubrication method, holds the potential to improve tool performance. However, due to significant cutting forces, NMQL faces challenges in effectively reaching the machining area, thereby limiting its cooling and lubricating efficiency. To overcome this challenge, our study proposes an innovative strategy by combining self-lubricating ceramic tools with nanofluids, aiming to enhance ceramic tool performance through synergistic lubrication effects. We conducted experimental studies under various lubrication conditions, comparing the performance of self-lubricating ceramic tools with traditional ceramic tools in cutting operations. A comprehensive evaluation of parameters such as tool life, cutting temperature, and cutting forces was performed. The results demonstrate that self-lubricating ceramic tools enable more efficient penetration of nanofluids into the machining area. In comparison to sole nanofluid lubrication, the synergistic effect significantly improves tool performance while substantially reducing production costs. This research contributes to advancing the development and widespread application of self-lubricating ceramic tools in the field of mechanical processing. © 2023, The Authors. All rights reserved.

关键词： Lubrication

来源：评论

学校读者我要写书评

暂无评论

A Mars Multi-terrain Simulator Using a Modular Terrain Construction Framework

A Mars Multi-terrain Simulator Using a Modular Terrain Const...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Yun Jiang Meibao Yao Bo Zheng Tao Hu Tao Cao Xueming Xiao Intelligent Robotics Lab (IRL) School of Artificial Intelligence Jilin University Changchun China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education China Shanghai Aerospace Control Technology Institute Shanghai China CVIR Lab Changchun University of Science and Technology Changchun China Key Lab of Optoelectronic Measurement and Optical Information Transmission Technology

Mars exploration tasks are inseparable from the support of robotic equipment. More comprehensive environmental awareness capabilities can improve the efficiency of robots on the surface of Mars. Artificial neural networks have emerged as pivotal tools in enhancing the perceptual capabilities of robots. The cornerstone of effective neural network training lies in the availability of high-quality data. Regrettably, the unstructured terrains, particularly the Martian landscape, lack real-world datasets with high-quality annotations. To overcome this challenge, using simulators to generate large amounts of high-quality data for researchers is a good option. Nonetheless, the creation of these simulators requires complex details such as ground texture characteristics and rock distribution, which increases research costs. In response, we introduce a novel approach – the modular terrain construction framework and construct a Mars multi-terrain simulator based on it. This innovative simulator not only simplifies the simulation process but also grants users the flexibility to alter it to their specific research needs. One of the standout features of our simulator is its capacity to generate rich metadata, such as semantic and depth, which can be used seamlessly for a multitude of downstream applications. To validate the reliability of the data produced by our simulator, we have assessed its performance on a semantic segmentation task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Condition Monitoring and Fault Diagnosis of Coal Mill Based on Mechanism Modeling Simulation and D-S Evidence Fusion

Condition Monitoring and Fault Diagnosis of Coal Mill Based ...

引用

第34届中国控制与决策会议

作者： Tian Qiu Yuchen Yang Yue Guo Xiaofeng Chen Key Laboratory of Industrial Process Measurement and Control New Technology and System North China Electric Power University School of Control and Computer Engineering North China Electric Power University North China Electric Power Research Institute Co. Ltd

The coal mill is the key equipment of powdering system in coal-fired power plants,whose working state has an important influence on the combustion stability of boiler as well as the operation ***,owing to the lack of real fault data,it is difficult and not available enough to support and achieve the research of data-driven fault diagnosis ***-type medium-speed coal mill was selected as the research object in this ***,the existing mechanism model had been further improved to make it more effective and reasonable,and we used it to respectively simulate the typical operating data of the normal condition and three fault *** paper transformed the problem of fault diagnosis into the measurement of similarity between the testing and the typical fault samples,taking the numerical distance and changing trends into account,and adopted the concept of similarity function and transformed the results into the expression and calculation of probability level,which was calculated as the diagnostic evidence of individual parameters under the same time scale.D-S evidence theory was employed to fuse the individual evidence between multiple parameters evidence,getting the fusion of multiparametric evidence as to the final diagnosis ***,the experiments verified the high accuracy of the proposed diagnostic method,and the similarity function has high rationality and feasibility.

关键词： Coal Mill System Process Fault Dynamic Mathematical Model Similarity Function D-S Evidence Fusion Theory Fault Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Enhancing rice production sustainability and resilience via reactivating small water bodies for irrigation and drainage (vol 14, 3794, 2023)

引用

NATURE COMMUNICATIONS 2023年第1期14卷 1-11页

作者： Li, Sisi Zhuang, Yanhua Liu, Hongbin Wang, Zhen Zhang, Fulin Lv, Mingquan Zhai, Limei Fan, Xianpeng Niu, Shiwei Chen, Jingrui Xu, Changxu Wang, Na Ruan, Shuhe Shen, Wangzheng Mi, Menghan Wu, Shengjun Du, Yun Zhang, Liang Hubei Provincial Engineering Research Center of Non-Point Source Pollution Control Innovation Academy for Precision Measurement Science and Technology Chinese Academy of Sciences Wuhan 430077 PR China Key Laboratory for Environment and Disaster Monitoring and Evaluation of Hubei Wuhan 430077 PR China University of Chinese Academy of Sciences Beijing 100049 PR China Institute of Agricultural Resources and Regional Planning Chinese Academy of Agricultural Sciences Beijing 100081 PR China State Environmental Protection Key Laboratory of Soil Health and Green Remediation Huazhong Agricultural University Wuhan 430070 PR China Interdisciplinary Research Center for Territorial Spatial Governance and Green Development Huazhong Agricultural University Wuhan 430070 PR China Institute of Plant Protection Soil and Fertilizer Sciences Hubei Academy of Agricultural Sciences Wuhan 430064 PR China Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing 400714 PR China Liaoning Academy of Agricultural Sciences Shenyang 110161 PR China Institute of Soil & Fertilizer and Resources & Environment Jiangxi Academy of Agricultural Sciences Nanchang 330200 PR China

Rice farming threatens freshwater resources, while also being increasingly vulnerable to drought due to climate change. Rice farming needs to become more sustainable and resilient to climate change by improving irrigation drainage systems. Small water bodies, used to store drainage water and supply irrigation in traditional rice farming systems have gradually been abandoned in recent decades. This has resulted in a higher water footprint (WF) associated with rice farming due to increased freshwater usage and wastewater release, also leaving rice production more vulnerable to extreme weather events. Here, we propose how protecting and reactivating small water bodies for rice irrigation and drainage can decrease rice production WF in China by 30%, save 9% of China’s freshwater consumption, increase irrigation self-sufficiency from 3% to 31%, and alleviate yield loss in dry years by 2–3%. These findings show that redesigning rice irrigation drainage systems can help meet water scarcity challenges posed by climate change.

关键词： Environmental health Hydrology Wetlands ecology

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：