检索结果-内蒙古大学图书馆

IEEE Electric Ship Technologies Symposium, ESTS

作者： Rounak Siddaiah Robert M. Cuzner Chaianan Sailabada Juan Ordonez Narayanan Rajagopal Christina DiMarino Avi Chatterjee Julie Chalfant Department of Electrical Engineering Sustainable Electrical Energy Systems University of Wisconsin Milwaukee Milwaukee WI USA Department of Mechanical Engineering Center for Advanced Power Systems Florida State University Tallahassee FL USA Center for Power Electronics Systems Virginia Polytechnic Institute and State University Arlington VA USA Sea Grant Design Laboratory Massachusetts Institute of Technology Cambridge MA USA

Naval shipboard power systems are complex and difficult to size and arrange due to their geographically distributed components. A modular Power Electronic Distribution System (PEPDS) built inside a Naval Integrated Power Electronic Corridor (NiPEC) has been proposed as a means of providing flexibility of power and energy delivery between sources and loads that significantly reduces electrical-thermal-structural overhead. In this study, a virtual prototyping process/that applies to PEPDS power trains is demonstrated. This approach enables the incorporation of digital twins of system building blocks, such as Power Electronic Building Block (PEBBs) and Integrated PEBB (iPEBBs) that have previously been reported on. The VPP ensures Pareto optimal integration of PEBB/iPEBB into PEPDS power trains and utilizes a unique dimensional compilation approach to account for the impacts of insulation coordination, repairability and thermal management on power density. This paper demonstrates Measure of Performance (MOP) outcomes of VPP and data management that can enable model based early-stage design exploration at the total ship level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization for Vehicular Cooperative Sensing: A Graph Attention Based Reinforcement Learning Approach

Performance Optimization for Vehicular Cooperative Sensing: ...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Xuefei Li Mingzhe Chen Danpu Liu Zhilong Zhang Tony Q. S. Quek Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Computer Engineering and Institute for Data Science and Computing University of Miami Coral Gables FL USA Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

In this paper, the problem of collaborative vehicle sensing is investigated. In the considered model, a set of cooperative vehicles provide sensing information to sensing request vehicles with limited sensing and communication resources. A base station (BS) determines the subset of sensing request vehicles that each cooperative vehicle will serve and the sub-regions that each cooperative vehicle will detect. We formulate an optimization problem aiming to maximize the number of successfully detected sub-regions of sensing request vehicles while satisfying the cooperative sensing energy requirement by jointly determining the cooperative vehicle association and the sensing sub-region selection. To solve this problem, we propose a graph attention based reinforcement learning (RL) algorithm that can generate the graph information vectors based on the correlation between each cooperative vehicle and each sensing request vehicle. Using the learned graph information, the joint cooperative vehicle association and sensing sub-region selection strategy will be determined. Simulation results show that the proposed scheme can improve the number of successfully detected sub-regions of sensing request vehicles by up to 12.5% compared to the conventional RL algorithm without using graph attention networks (GANs).

关键词： Base stations Correlation Network topology Simulation Collaboration Reinforcement learning Vectors Sensors Global communication Optimization

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Generative Semantic Communications for Mobile AIGC: Joint Semantic Encoding and Prompt engineering

arXiv

引用

arXiv 2024年

作者： Liu, Yinqiu Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Mao, Shiwen Zhang, Ping Shen, Xuemin Sherman School of Computer Science and Engineering Nanyang Technological University Singapore School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Department of Electrical and Computer Engineering Auburn University Auburn United States State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering University of Waterloo Canada

Employing massive Mobile AI-Generated Content (AIGC) Service Providers (MASPs) with powerful models, high-quality AIGC services can become accessible for resource-constrained end users. However, this advancement, referred to as mobile AIGC, also introduces a significant challenge: users should download large AIGC outputs from the MASPs, leading to substantial bandwidth consumption and potential transmission failures. In this paper, we apply cross-modal Generative Semantic Communications (G-SemCom) in mobile AIGC to overcome wireless bandwidth constraints. Specifically, we utilize a series of cross-modal attention maps to indicate the correlation between user prompts and each part of AIGC outputs. In this way, the MASP can analyze the prompt context and filter the most semantically important content efficiently. Only semantic information is transmitted, with which users can recover the entire AIGC output with high quality while saving mobile bandwidth. Since the transmitted information not only preserves the semantics but also prompts the recovery, we formulate a joint semantic encoding and prompt engineering problem to optimize the bandwidth allocation among users. Particularly, we present a human-perceptual metric named Joint Perpetual Similarity and Quality (JPSQ), which is fused by two learning-based measurements regarding semantic similarity and aesthetic quality, respectively. Furthermore, we develop the Attention-aware Deep Diffusion (ADD) algorithm, which learns attention maps and leverages the diffusion process to enhance the environment exploration ability of traditional deep reinforcement learning (DRL). Extensive experiments demonstrate that our proposal can reduce the bandwidth consumption of mobile users by 49.4% on average, with almost no perceptual difference in AIGC output quality. Moreover, the ADD algorithm shows superior performance over baseline DRL methods, with 1.74× higher overall reward. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

MBSE Approach to Early Naval Ship design Exploration with Power Electronic Power Distribution System in Power and Energy Corridors

引用

IEEE Transactions on Transportation Electrification 2025年

作者： Cuzner, Robert Chalfant, Julie Gross, David Shabani, Hamed Ali, Naqash Steurer, Mischa University of Wisconsin-Milwaukee Department of Electrical Engineering MilwaukeeWI53211 United States Design Laboratory of the MIT Sea Grant College Program Massachusetts Institute of Technology CambridgeMA02139 United States Florida State University Center for Advanced Power Systems TallahasseeFL32310 United States

The concept development of any system includes the definition of various parameters of interest and determination of the threshold (satisfactory) and goal (desired) value for each. These are classically organized into Measures of Effectiveness, Measures of Performance (MOPs), & Technical Performance Measures (TPMs). These form the basis of performance requirements, the means for evaluating design, and the measure by which systems are validated. A cross-cutting sub-set of MOPs and TPMs, Key Performance Parameters (KPPs) can define the trade space within which to optimize the emerging solution. Applying this systematic approach is substantially complicated when the system of interest aims for unprecedented capabilities from emerging technologies, which is the situation for electric ship research. This paper presents an Integration Framework that effectively maps out a process leading to defined parameter objectives, which is being developed and used in the U.S. department of Navy sponsored Power Electronic Power Distribution System (PEPDS) research initiative. The method then integrates the Model-Based systems engineering (MBSE) system model with genetic algorithm trade space exploration tools. © 2025 IEEE. All rights reserved.

关键词： Warships

来源：评论

学校读者我要写书评

暂无评论

A methodology to capture the single blade loads on a cross-flow tidal turbine flume model 15th

A methodology to capture the single blade loads on a cross-f...

引用

15th European Wave and Tidal Energy Conference, EWTEC 2023

作者： Bennecke, Timo Abbaszadeh, Shokoofeh Ruiz-Hussmann, Karla Joedecke, Paul Delafin, Pierre-Luc Weber, Christian-Toralf Hoerner, Stefan Laboratory of Fluid Dynamics and Technical Flows Otto-von-Guericke-University Magdeburg Universitätsplatz 2 Magdeburg39106 Germany Chair Electrical Drive Systems Otto-vonGuericke-University Magdeburg Universitätsplatz 2 Magdeburg39106 Germany University of Applied Sciences Department of Engineering and Industrial Design Magdeburg Germany Univ. Grenoble Alpes CNRS Grenoble INP LEGI Grenoble France

The OPTIDE project aims to improve the efficiency and durability of hydrokinetic cross-flow tidal turbines (CFTT). CFTT are attractive for the exploitation of tidal energy, because of high area-based power densities of such turbine arrays, a simple design and the ability to operate under varying flow conditions. Nevertheless, the efficiency of single CFTT is lower relative to the most commonly used axial turbine type. Furthermore the life time is often limited due to alternating and pulsating stresses. A promising approach to overcome these drawbacks is intracycle blade pitching. In this case the angle of attack is continuously adjusted individually for each blade during the rotation. The project aims to explore the influence of active blade pitching on CFTTs and to optimize it by numerical and experimental means. Therefore, a labscaled three-bladed experimental turbine with embedded pitch actuators is developed. The turbine is equipped with multiple full-bridges of strain gauges for the detection of tangential and radial components of the blade loads, from which the structural stress is calculated subsequently. To ensure the turbines mechanical durability, weakly coupled fluid-solid-interaction (FSI) simulations have been performed. Additionally, the FSI simulations show that a setup with strain gauges on a single blade support only allows for the measurement of the radial blade load component, as the measurements are distorted by pitching moments and secondary force paths. A revised instrumentation setup is developed and presented. The FSI simulations are adapted, to prove the suitability of the revised setup. © 2023 European Wave and Tidal Energy Conference.

关键词： Strain gages

来源：评论

学校读者我要写书评

暂无评论

Etch of Nano-Tsv with Smooth Sidewall and Excellent Selection Ratio for Backside Power Delivery Network

SSRN

引用

SSRN 2024年

作者： Wang, Yang Liu, Ziyu Sun, Yabin Chen, Lin Sun, Qingqing School of Microelectronics Fudan University Shanghai200433 China The State Key Laboratory of Integrated Chips and Systems Fudan University China Jiashan Fudan Institute Zhejiang Province Jiaxing314100 China Department of Electrical Engineering East China Normal University Shanghai200241 China

Backside Power Delivery Network (BSPDN) is a crucial technology for integrated circuits at sub-3 nm technology nodes. The primary challenge lies in utilizing nano through silicon via (nano-TSV) to establish connections between the backside power network and buried power rails, thereby facilitating transistor powering. The key technology is to ensure a smooth sidewall morphology and prevent damage to buried power rails (BPR) due to over-etching. In this study, non-Bosch and Bosch techniques are compared using simulation. The results demonstrate that while the non-Bosch technique yields smooth sidewalls, it inevitably leads to over-etching, whereas Bosch avoids over-etching. The etching of scallop-free nano-TSV is achieved by optimizing the Bosch process, which involves the use of inductively coupled plasma (ICP). Finally, metal filling of nano-TSV is achieved. The nano-TSV etching method is successfully established for BSPDN. © 2024, The Authors. All rights reserved.

关键词： Inductively coupled plasma

来源：评论

学校读者我要写书评

暂无评论

Investigation on Loss Reduction Strategies of Single-Core HVAC Submarine Cables 22

Investigation on Loss Reduction Strategies of Single-Core HV...

引用

22nd International Symposium on High Voltage engineering, ISH 2021

作者： Xu, Xing Meng, Fanbo Paramene, Ashish Chen, Xiangrong Qiu, Lifeng Zhou, Wenjun Zhejiang Provincial Key Laboratory of Electrical Machine Systems College of Electrical Engineering Zhejiang University Hangzhou310027 China Department of Electrical Engineering National Institute of Technology Assam Silchar788010 India Zhejiang Huayun Electric Power Engineering Design & Consultation Company Hangzhou310027 China

ISBN: (纸本)9781839536052

Submarine cables play an important role in the cross-sea transmission system. However, the power loss in such systems should be reduced as it affects the service life and limits the ampacity of the submarine cables. This paper proposes an accurate methodology based on the multi-conductor analysis theory to investigate the loss reduction strategies of the single-core high voltage AC (HVAC) submarine cable. The coupled line model is used to improve the calculation efficiency. The case study of the 500-kV submarine cable line of Zhoushan 500 kV power transmission project is conducted. The results show that connecting resistors and reactors at the grounding ends of the cable sheath can significantly reduce power loss. The connection of reactors exhibits a higher reduction of power loss than the resistors. © 2021 The Institution of engineering and Technology.

关键词： Submarines

来源：评论

学校读者我要写书评

暂无评论

QoE-Guaranteed Optimization in MEC-Enabled Metaverse: An Active Inference Deep Reinforcement Learning Approach

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Du, Jianbo Gong, Jie Chu, Xiaoli Xiong, Zehui Chen, Xianfu Dong, Mianxiong Yu, F. Richard Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security School of Communications and Information Engineering Xi'an710121 China The University of Sheffield Mappin Street Department of Electronic and Electrical Engineering SheffieldS1 3JD United Kingdom Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore Singapore Shenzhen CyberAray Network Technology Company Ltd Shenzhen518000 China Muroran Institute of Technology Department of Sciences and Informatics Muroran050-8585 Japan Carleton University Systems and Computer Engineering OttawaON Canada

In this paper, we consider a MEC-enabled metaverse scenario which consists of a remote metaverse server and an edge server that cooperates to provide services to mobile users. The edge server is deployed at the base station (BS), serves a dual role: augmenting computational capabilities for user equipment (UE) and pre-caching a portion of the metaverse service contents before each time slot. Moreover, the foreground information and the requested contents generated by the UEs can also be cached to the BS. We formulate a problem to maximize the cache hit number by jointly optimizing contents pre-caching and resource allocation at the BS while considering UEs preference and reducing the UEs total energy consumption, essential for the efficient delivery of services in dynamic MEC environments. To solve this problem, we reformulate it as a partially observable markov decision process and propose an active inference enabled deep reinforcement learning algorithm, which combines active inference with deep reinforcement learning to select the optimal strategy by minimizing the expected free energy. Simulations show that the proposed algorithm can effectively improve the total quality of experience and the cache hit number of UEs, while minimizing the UEs total energy consumption compared with other baseline algorithms © 2015 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

EVDMARL: Efficient Value Decomposition-based Multi-Agent Reinforcement Learning with Domain-Randomization for Complex Analog Circuit design Migration 24

EVDMARL: Efficient Value Decomposition-based Multi-Agent Rei...

引用

61st ACM/IEEE design Automation Conference, DAC 2024

作者： Sun, Handa Bi, Zhaori Jiang, Wenning Lu, Ye Yan, Changhao Yang, Fan Hu, Wenchuang Wang, Sheng-Guo Zhou, Dian Zeng, Xuan State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China School of Microelectronics Fudan University Shanghai China Frontier Institute of Chip and System Fudan University Shanghai China School of Information Science and Technology Fudan University Shanghai China Precision Medicine Center of West China Hospital Sichuan University Chengdu China Department of Et Department of Ece University of North Carolina at Charlotte Charlotte United States Department of Electrical Engineering University of Texas at Dallas RichardsonTX United States University of Texas Dallas United States

ISBN: (纸本)9798400706011

Automated analog circuit design migration significantly alleviates the burden on designers in circuit sizing under various operating conditions. Conventional methods model the migration problem as black-box optimization, requiring excessive iterations of costly simulations to converge. Reinforcement learning exhibits significant promise in transfer learning, as it enables the generation of circuits that fulfill specifications efficiently. The paper proposes a novel value decomposition-based multi-agent reinforcement learning framework, aiming to model complex analog circuits and eliminate the need for manually defined specifications of sub-circuits for new operating conditions. Additionally, it incorporates domain randomization techniques to efficiently generate circuits that meet unforeseen scenarios with minimal simulations. Experiment demonstrates that our algorithm can efficiently generate circuits meeting specifications under new operating conditions in few number of steps, outperforming state-of-the-art methods. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Older and Wiser: The Marriage of Device Aging and Intellectual Property Protection of Deep Neural Networks

arXiv

引用

arXiv 2024年

作者： Lin, Ning Wang, Shaocong Zhang, Yue He, Yangu Wong, Kwunhang Basu, Arindam Shang, Dashan Chen, Xiaoming Wang, Zhongrui Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong ACCESS – AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong Institute of Computing Technology Chinese Academy of Sciences Beijing China Key Laboratory of Microelectronics Devices and Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing China Department of Electrical Engineering City University of Hong Kong Hong Kong

Deep neural networks (DNNs), such as the widely-used GPT-3 with billions of parameters, are often kept secret due to high training costs and privacy concerns surrounding the data used to train them. Previous approaches to securing DNNs typically require expensive circuit redesign, resulting in additional overheads such as increased area, energy consumption, and latency. To address these issues, we propose a novel hardware-software co-design approach for DNN intellectual property (IP) protection that capitalizes on the inherent aging characteristics of circuits and a novel differential orientation fine-tuning (DOFT) to ensure effective protection. Hardware-wise, we employ random aging to produce authorized chips. This process circumvents the need for chip redesign, thereby eliminating any additional hardware overhead during the inference procedure of DNNs. Moreover, the authorized chips demonstrate a considerable disparity in DNN inference performance when compared to unauthorized chips. Software-wise, we propose a novel DOFT, which allows pre-trained DNNs to maintain their original accuracy on authorized chips with minimal fine-tuning, while the model’s performance on unauthorized chips is reduced to random guessing. Extensive experiments on various models, including MLP, VGG, ResNet, Mixer, and SwinTransformer, with lightweight binary and practical multi-bit weights demonstrate that the proposed method achieves effective IP protection, with only 10% accuracy on unauthorized chips, while preserving nearly the original accuracy on authorized ones. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

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：