检索结果-南通市图书馆

预防LLM赋能的智能聊天机器人全生命周期能源和碳足迹剧增（英文）

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Engineering 2024年第9期 202-210页

作者：蒋鹏 Christian Sonne 李望良 Fengqi You Siming You Department of Industrial Engineering and Management Business School Sichuan University Department of Ecoscience Aarhus University Chinese Academy of Sciences Key Laboratory of green Process and Engineering Institute of Process Engineering Chinese Academy of Sciences Systems Engineering Cornell University James Watt School of Engineering University of Glasgow

intelligent chatbots powered by large language models(LLMs) have recently been sweeping the world,with potential for a wide variety of industrial applications. Global frontier technology companies are feverishly participating in LLM-powered chatbot design and development, providing several alternatives beyond the famous ChatGPT. However, training, fine-tuning, and updating such intelligent chatbots consume substantial amounts of electricity, resulting in significant carbon emissions. The research and development of all intelligent LLMs and software, hardware manufacturing(e.g., graphics processing units and supercomputers), related data/operations management, and material recycling supporting chatbot services are associated with carbon emissions to varying extents. Attention should therefore be paid to the entire life-cycle energy and carbon footprints of LLM-powered intelligent chatbots in both the present and future in order to mitigate their climate change impact. In this work, we clarify and highlight the energy consumption and carbon emission implications of eight main phases throughout the life cycle of the development of such intelligent chatbots. Based on a life-cycle and interaction analysis of these phases,we propose a system-level solution with three strategic pathways to optimize the management of this industry and mitigate the related footprints. While anticipating the enormous potential of this advanced technology and its products, we make an appeal for a rethinking of the mitigation pathways and strategies of the life-cycle energy usage and carbon emissions of the LLM-powered intelligent chatbot industry and a reshaping of their energy and environmental implications at this early stage of development.

关键词：

Wireless/wired integrated transmission for industrial cyber-physical systems: risk-sensitive co-design of 5G and TSN protocols

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第1期65卷 56-71页

作者： Yajing ZHANG Qimin XU Xinping GUAN Cailian CHEN Mingyan LI Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research center of intelligent Control and Management College of Computer Science Chongqing University

The growing popularity of intelligent manufacturing is driven by deterministic transmission demands of applications in industrial cyber-physical systems(ICPS). However, the ossified shortages of industrial wireless communication such as diverse quality of service(Qo S) and complex signaling processes incur a severe long tail of transmission delay distribution. As a solution, the 5 th generation(5 G) wireless communication technology provides ultra-reliable and low-latency communication(URLLC) for industry scenarios. Moreover, the newly proposed time-sensitive networking(TSN) standards guarantee the transmission determinacy by gate mechanism. In this paper, we propose a heterogeneous time-sensitive network(HTSN) co-designed by 5 G and TSN. We first develop a predictive multi-priority wireless scheduling mechanism based on semi-persistent scheduling(SPS) to reduce signaling delay by reserving resources in *** we propose an adaptive data injection mechanism for TSN based on per-stream filtering and policing(PSFP), which dynamically adjusts the priority of data for queue injection in TSN. To further reduce the long tail of delay, we employ a risk-sensitive learning method to improve the worst-case delay. Simulations on a hot rolling production scenario demonstrate that the proposed mechanisms under HTSN achieve great performance in terms of integrated delay and resource utilization.

关键词： industrial cyber-physical systems (ICPS) 5G-TSN co-design wireless/wired integrated network risk-sensitive reinforcement learning deterministic communication

SE-COTR: A Novel Fruit Segmentation Model for green Apples Application in Complex Orchard

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Plant Phenomics 2022年第1期4卷 12-25页

作者： Zhifen Wang Zhonghua Zhang Yuqi Lu Rong Luo Yi Niu Xinbo Yang Shaoxue Jing Chengzhi Ruan Yuanjie Zheng Weikuan Jia School of Information Science and Engineering Shandong Normal UniversityJinan 250358China State Key Laboratory of Biobased Materials and green Papermaking Qilu University of Technology(Shandong Academy of Science)Jinan 25035China School of Informatics University of LeicesterLeicester LE17RHUK Department of Engineering Design and Mathematics University of the West of EnglandBristol BS161QYUK Fujian Key Laboratory of intelligent Control and manufacturing of Agricultural Machinery Wuyishan 354300China Key Laboratory of Facility Agriculture Measurement and Control technology and Equipment of Machinery industry Jiangsu UniversityZhenjiang 212013China

Because of the unstructured characteristics of natural orchards,the efficient detection and segmentation applications of green fruits remain an essential challenge for intelligent ***,an innovative fruit segmentation method based on deep learning,termed SE-COTR(segmentation based on coordinate transformer),is proposed to achieve accurate and real-time segmentation of green apples.

关键词： Application segmentation Complex

Wafer bin map inspection based on DenseNet

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Central South University 2021年第8期28卷 2436-2450页

作者： YU Nai-gong XU Qiao WANG Hong-lu LIN Jia Faculty of Information technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computing Intelligence and intelligent System Beijing 100124China Engineering Research center of Digital Community Ministry of EducationBeijing 100124China

Wafer bin map(WBM)inspection is a critical approach for evaluating the semiconductor manufacturing *** excellent inspection algorithm can improve the production efficiency and *** paper proposes a WBM defect pattern inspection strategy based on the DenseNet deep learning model,the structure and training loss function are improved according to the characteristics of the *** addition,a constrained mean filtering algorithm is proposed to filter the noise *** model prediction,an entropy-based Monte Carlo dropout algorithm is employed to quantify the uncertainty of the model *** experimental results show that the recognition ability of the improved DenseNet is better than that of traditional algorithms in terms of typical WBM defect *** the model uncertainty can not only effectively reduce the miss or false detection rate but also help to identify new patterns.

关键词： wafer defect inspection convolutional neural network DenseNet model uncertainty

Fabrication of sapphire rib waveguides using a femtosecond laser

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2019年第3期15卷 190-194页

作者： WANG Jue TAO Qing HU Chen ZHAI Zhong-sheng CHENG Jian LIU Dun School of Mechanical Engineering Hubei University of TechnologyWuhan430068China Hubei Key Laboratory of Modern manufacturing Quantity Engineering School of Mechanical EngineeringHubeiUniversity of TechnologyWuhan430068China1

We demonstrate a method for fabricating sapphire rib waveguides with femtosecond laser micromachining technology. Finite difference beam propagation method(FD-BPM) is applied to design sapphire rib waveguides. We explore the process of etching on a sapphire substrate surface via direct laser ablation. Rib waveguides that satisfies the dimensions of our design were fabricated. Actual light propagation performance is tested, and with the cut-back method, the insertion loss of 2.9±0.5 dB/cm is measured.

关键词： FD length Fabrication of sapphire rib waveguides using a femtosecond laser BPM

Fabrication of MoF-based composite for synergistic catalysis

在线全文

学校读者我要写书评

暂无评论

Frontiers of Materials Science 2023年第1期17卷 175-179页

作者： Xin Zhou Yanhu Zhang Weiqiang Zhou Chen Zhou Quan Wang School of Mechanical Engineering Jiangsu UniversityZhenjiang 212013China Institution of green Chemistry and Chemical technology School of Chemistry and Chemical EngineeringJiangsu UniversityZhenjiang 212013China Institute of Laser and Optoelectronics intelligent manufacturing Wenzhou UniversityWenzhou 325035China State Key Laboratory of Transducer technology Chinese Academy of SciencesShanghai 200050China

Heterogeneous catalyst has received extensive attention in the field of chemical industry due to its high activity and selectivity[1-2].In general,the heterogeneous catalysts exhibit certain advantages,such as large surface area,more exposed active sites,and easily recovery[3].For example,noble metal nanoparticles(NPs)were uniformly supported by the porous materials(e.g.,porous carbon,zeolite,and silica)for preparing the heterogeneous catalysts[46].

关键词： porous catalysis synergistic

Real-time monitoring flexible hydrogels based on dual physically cross-linked network for promoting wound healing

在线全文

学校读者我要写书评

暂无评论

中国化学快报:英文版 2023年第10期34卷 229-235页

作者： Le Hu Yuxin Wang Qing Liu Man Liu Faming Yang Chunxiao Wang Panpan Pan Lin Wang Li Chen Jingdi Chen Marine College Shandong UniversityWeihai 264209China Shandong Laboratory of Advanced Materials and green manufacturing Yantai 265599China College of Biological Science and technology Fuzhou UniversityFuzhou 350108China

To achieve smart and personalized medicine, the development of hydrogel dressings with sensing properties and biotherapeutic properties that can act as a sensor to monitor of human health in real-time while speeding up wound healing face great challenge. In the present study, a biocompatible dual-network composite hydrogel(DNCGel) sensor was obtained via a simple process. The dual network hydrogel is constructed by the interpenetration of a flexible network formed of poly(vinyl alcohol)(PVA) physical cross-linked by repeated freeze-thawing and a rigid network of iron-chelated xanthan gum(XG) impregnated with Fe^(3+) interpenetration. The pure PVA/XG hydrogels were chelated with ferric ions by immersion to improve the gel strength(compressive modulus and tensile modulus can reach up to 0.62 MPa and0.079 MPa, respectively), conductivity(conductivity values ranging from 9 × 10^(-4) S/cm to 1 × 10^(-3)S/cm)and bacterial inhibition properties(up to 98.56%). Subsequently, the effects of the ratio of PVA and XG and the immersion time of Fe^(3+) on the hydrogels were investigated, and DNGel3 was given the most priority on a comprehensive consideration. It was demonstrated that the DNCGel exhibit good biocompatibility in vitro, effectively facilitate wound healing in vivo(up to 97.8% healing rate) under electrical stimulation, and monitors human movement in real time. This work provides a novel avenue to explore multifunctional intelligent hydrogels that hold great promise in biomedical fields such as smart wound dressings and flexible wearable sensors.

关键词： Conductive hydrogel Dual cross-linked network Antimicrobial activity Real-time monitorin Wound healing

Energy management of hybrid electric propulsion system: Recent progress and a flying car perspective under three-dimensional transportation networks

在线全文

学校读者我要写书评

暂无评论

green Energy and intelligent Transportation 2023年第1期2卷 67-85页

作者： Chao Yang Zhexi Lu Weida Wang Ying Li Yincong Chen Bin Xu School of Mechanical Engineering Beijing Institute of TechnologyBeijing100081China Chongqing Innovation center Beijing Institute of TechnologyChongqing401120China

The hybrid electric propulsion system(HEPS)holds clear potential to support the goal of sustainability in the automobile and aviation *** an important part of the three-dimensional transportation network,vehicles and aircraft using HEPSs have the advantages of high fuel economy,low emission,and low *** fulfill these advantages,the design of their energy management strategies(EMSs)is *** paper presents an in-depth review of EMSs for hybrid electric vehicles(HEVs)and hybrid electric ***,in view of the main challenges of current EMSs of HEVs,the referenced research is reviewed according to the solutions facing real-time implementation problems,variable driving conditions adaptability problems,and multi-objective optimization problems,***,the existing research on the EMSs for hybrid electric aircraft is summarized according to the hybrid electric propulsion *** addition,with the advance in propulsion technology and mechanical manufacturing in recent years,flying cars have gradually become a reality,further enriching the composition of the three-dimensional transportation *** EMSs also play an essential role in the efficient operation of flying cars driven by ***,in the last part of this paper,the development status of flying cars and their future prospects are *** comprehensively summarizing the EMSs of HEPS for vehicles and aircraft,this review aims to provide guidance for the research on the EMSs for flying cars driven by HEPS and serve as the basis for knowledge transfer of relevant researchers.

关键词： Hybrid electric vehicle Hybrid electric aircraft Flying car Energy management strategy Three-dimensional transportation network

Applied Research of IoV in Insurance industry

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Aided Drafting,Design and manufacturing 2014年第2期24卷 54-59页

作者： BI Xiang LIU Zheng-yu LIU Ning-bo ZHANG Li School of Computer and Information Heifei University of Technology Engineering Research center of Safety-critical industry Measure and Control technology of Ministry of Education School of Machinery and Automobile Engineering Hefei University of Technology

A vehicle intelligent terminal is designed to collect vehicle state information and driver behavior information based on the application of Internet of Vehicle in the insurance industry, and data of 12 risk factors affecting the traffic safety is extracted from the information. The Principal Component Analysis is improved and PCA based on the index significant priority is proposed, using which the data of risk factors is processed and 3 principal components are obtained as the pricing factor of the insurance industry.

关键词： IoV(internet of vehicle) insurance industry vehicle intelligent terminal PCA index significant priority pricing factor