检索结果-南通市图书馆

Intelligent Vehicle for Urban Road Traffic Recognition System Using Deep Learning Algorithm

在线全文

学校读者我要写书评

暂无评论

Intelligent Vehicle for Urban Road Traffic Recognition Syste...

作者： ASHIKUR RAHMAN mohammad 重庆交通大学

学位级别：硕士

城市道路的目标识别和监测技术是计算机视觉领域的关键研究途径,在日常生活中得到了广泛应用。人类探测作为主要焦点,具有独特的特征,将目标的典型属性与无与伦比的可变性相结合。因此,与行人检测和跟踪相关的技术挑战超过了普通目标所... 详细信息

城市道路的目标识别和监测技术是计算机视觉领域的关键研究途径,在日常生活中得到了广泛应用。人类探测作为主要焦点,具有独特的特征,将目标的典型属性与无与伦比的可变性相结合。因此,与行人检测和跟踪相关的技术挑战超过了普通目标所面临的挑战,这使得这一主题变得特别复杂和苛刻。对这一主题的探索不仅具有科学研究意义,而且具有相当大的社会应用价值。智能汽车技术的快速发展导致了解决城市道路交通复杂性的范式转变。本文介绍了新能源智能汽车领域内交通识别系统的一种开创性方法,利用最先进的深度学习算法。本研究强调YOLO v8(You Only Look Once)和DETR(Detection Transformer)的融合,推动了物体检测的前沿,特别是在自动驾驶汽车的背景下。使用深度学习算法进行城市道路交通监测面临着一些挑战,包括高计算需求、实时处理要求、多样化和复杂的城市环境,以及对物体检测和分类的高精度要求。像Faster R-CNN这样的传统模型虽然准确,但计算密集且速度较慢,因此不太适合实时应用。DETR以其基于转换器的架构提供了稳健的特征提取,但可能会在速度和复杂性方面遇到困难。YOLO模型效率高、速度快,适用于实时检测,但它们可能会为速度牺牲一些准确性。所提出的DETR-YOLO v8n融合模型旨在通过将DETR的鲁棒特征提取的优势与YOLO v8n的实时检测能力相结合来解决这些问题。这种融合利用注意力机制来突出相关特征,在不显著影响速度的情况下提高准确性。通过集成这些方法,DETR-YOLO v8n Fusion模型提供了一个平衡的解决方案,可以提高检测精度,保持实时处理,并有效地导航城市道路环境的复杂性,从而改善整体交通监控和管理。这项研究错综复杂地探索了YOLO v8的细微改进,展示了其在城市道路交通场景中的卓越性能。细化的锚盒预测细化了空间定位,而特征金字塔网络增强了模型在不同尺度上辨别物体的能力。先进的主干架构增强了特征提取,从而增强了网络的整体辨别能力。所提出的系统以YOLO v8和DETR的融合为基础,强调了其在复杂交通环境中显著提高新能源智能汽车安全性和有效性的潜力。这项研究不仅有助于新兴的智能交通解决方案领域,而且有助于不断完善自动驾驶汽车的目标检测机制。这些发现强调了接受YOLO v8进化改进的关键性,为追求智能和响应能力强的城市交通系统的先进识别系统树立了新的基准。近年来,深度学习的出现在计算机视觉方面取得了重大进展,特别是在目标检测精度方面。然而,深度模型的复杂性阻碍了检测速度的提高,再加上硬件需求的提高,从而阻碍了其对行人检测和跟踪的适用性。因此,本文对行人检测与跟踪进行了全面的研究。这项研究的高潮涉及对峰值响应和目标损失之间相关性的检查。在本文中,我们使用最新的YOLO v8升级了这三项改进,用于城市道路的交通监控。*** v8引入了精细的锚盒预测,增强了空间定位,以更精确地识别对象位置。这一改进对于智能汽车在复杂城市环境中的精确导航至关重要。2.在YOLO v8中引入特征金字塔网络解决了多尺度检测中的挑战。这种增强使该模型能够有效地识别和分类不同大小的对象,确保在不同的交通场景中具有强大的检测能力。*** v8的高级骨干架构提高了特征提取效率,捕捉了复杂的细节和上下文信息。这一改进提高了模型的鉴别力,特别是在具有挑战性的城市道路交通条件下,从而提高了物体检测任务的整体性能。在我之前的研究中,我使用Tensor Flow深度学习框架,来完成网络模型的设计与训练。为了验证本文提出模型的可行性与检测效果,将本文算法的检测实验结果与当前常见的目标检测算法进行对比分析,对比的算法包括SSD、YOLO V3和GANet(Guided Attention Net Work),在相同数据集进行对比,检测准确率结果如下:SSD模型的平均查准率为68.2%,YOLO V3网络模型的平均查准率为73.8%,GANet网络模型的平均查准率为76.8%:而本文采用的Faster R-CNN平均查准率为86.3%。由此可知,Faster R-CNN网络模型在城市道路目标检测准确.在智能汽车自动驾驶道路智能识别实验中,本文改进了DETR(Detection Transformer)网络结构,并与其他常见的识别算法,如Faster R-CNN、YOLO(You Only Look Once)和SSD(Single Shot Multi Box Detector)进行了对比。在我之前的研究中,它的结果如下,以评价指标的数据说明:(1)准确率(Precision):指模型检测到的物体中真实物体的比例。综合了测试集上的准确率结果,DETR网络达到了90%的准确率,超过了Faster R-CNN和YOL

关键词：深度学习 YOLOv8模型交通检测 DETR Faster R-CNN 自动驾驶

Interplay between temperature-dependent strengthening mechanisms and mechanical stability in high-performance austenitic stainless steels

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2024年第10期31卷 2182-2188页

作者： mohammad Javad Sohrabi Hamed Mirzadeh Saeed Sadeghpour Milad Zolfipour Aghdam Abdol Reza Geranmayeh Reza Mahmudi School of Metallurgy and Materials Engineering College of EngineeringUniversity of Tehran14395-515 TehranIran Centre for Advanced Steels Research Materials and Mechanical EngineeringUniversity of Oulu90014 OuluFinland Department of Mechanical Engineering College of EngineeringUniversity of Tehran14395-515 TehranIran

The effects of deformation temperature on the transformation-induced plasticity(TRIP)-aided 304L,twinning-induced plasti-city(TWIP)-assisted 316L,and highly alloyed stable 904L austenitic stainless steels were compared for the first time to tune the mechan-ical properties,strengthening mechanisms,and strength-ductility *** this purpose,the scanning electron microscopy(SEM),electron backscattered diffraction(EBSD),X-ray diffraction(XRD),tensile testing,work-hardening analysis,and thermodynamics calcu-lations were *** induced plasticity effects led to a high temperature-dependency of work-hardening behavior in the 304L and 316L stainless *** the deformation temperature increased,the metastable 304L stainless steel showed the sequence of TRIP,TWIP,and weakening of the induced plasticity mechanism;while the disappearance of the TWIP effect in the 316L stainless steel was also ***,the solid-solution strengthening in the 904L superaustenitic stainless steel maintained the tensile properties over a wide temper-ature range,surpassing the performance of 304L and 316L stainless *** this regard,the dependency of the total elongation on the de-formation temperature was less pronounced for the 904L alloy due to the absence of additional plasticity *** results re-vealed the importance of solid-solution strengthening and the associated high friction stress for superior mechanical behavior over a wide temperature range.

关键词： austenitic stainless steels mechanical behavior stacking fault energy metastability mechanical twinning

Multifunctional SnO_(2) QDs/MXene Heterostructures as Laminar Interlayers for Improved Polysulfide Conversion and Lithium Plating Behavior

在线全文

学校读者我要写书评

暂无评论

Nano-Micro Letters 2024年第11期16卷 156-169页

作者： Shungui Deng Weiwei Sun Jiawei Tang mohammad Jafarpour Frank Nüesch Jakob Heier Chuanfang Zhang College of Materials Science and Engineering Sichuan UniversityChengdu 610065People’s Republic of China Laboratory for Functional Polymers Swiss Federal Laboratories for Materials Science and Technology(EMPA)Überlandstrasse 1298600 DübendorfSwitzerland Institute of Materials Science and Engineering Ecole Polytechnique Fédérale de Lausanne(EPFL)Station 121015 LausanneSwitzerland Key Laboratory of Quantum Materials and Devices of Ministry of Education School of PhysicsSoutheast UniversityNanjing 211189People’s Republic of China SEU‑FEI Nano‑Pico Center Key Laboratory of MEMS of Ministry of EducationSoutheast UniversityNanjing 210096People’s Republic of China

Poor cycling stability in lithium–sulfur(Li–S)batteries necessitates advanced electrode/electrolyte design and innovative interlayer *** catalysis has emerged as a promising approach,leveraging the adsorption and catalytic performance on lithium polysulfides(LiPSs)to inhibit LiPSs shuttling and improve redox *** this study,we report an ultrathin and laminar SnO_(2)@MXene heterostructure interlayer(SnO_(2)@MX),where SnO_(2) quantum dots(QDs)are uniformly distributed across the MXene *** combined structure of SnO_(2) QDs and MXene,along with the creation of numerous active boundary sites with coordination electron environments,plays a critical role in manipulating the catalytic kinetics of sulfur *** Li–S cell with the SnO_(2)@MX-modified separator not only demonstrates superior electrochemical performance compared to cells with a bare separator but also induces homogeneous Li deposition during *** a result,an areal capacity of 7.6 mAh cm^(-2) under a sulfur loading of 7.5 mg cm^(-2) and a high stability over 500 cycles are *** work demonstrates a feasible strategy of utilizing a laminar separator interlayer for advanced Li–S batteries awaiting commercialization and may shed light on the understanding of heterostructure catalysis with enhanced reaction kinetics.

关键词： Lithium-sulfur battery Heterogeneous catalysis Heterostructure Redox kinetics Lithium dendrites

Using Longitudinal Fins to Improve the Melting Performance of Stearic Acid in Thermal Energy Storage Devices

在线全文

学校读者我要写书评

暂无评论

Journal of Thermal Science 2024年第5期33卷 1672-1687页

作者： YAN Suying LIU Yiran AO Ci ZHAO Xiaoyan ZHANG Na ZHANG Ruiying AHMADI mohammad Hossein School of Energy and Power Engineering Inner Mongolia University of TechnologyHohhot 010051China Institute of Engineering Thermophysics Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100190China School of Materials Science and Engineering Inner Mongolia University of TechnologyHohhot 010051China Faculty of Mechanical Engineering Shahrood University of TechnologyShahroodIran

The heat transfer efficiency of a thermal energy storage unit(TESU)can be improved by the addition of novel longitudinal fins.A series of TESUs are analyzed using the finite volume method(FVM)to determine the effect of fin angle on the heat transfer *** the fin angle increases,the TES rate first increases,then decreases,reaching a maximum rate at 60°,where the melting time is less by 30.9%,28.58%,21.99%,9.02%,and 18.1%than at 0°,15°,30°,45°,and 80°,*** addition,it is found that the melting time of the phase change material is significantly greater at the bottom of the *** time percentage of this stage decreases as the fin angle increases through these percentages by 7%,14%,23%,33%,and 20%,***,the response surface methodology(RSM)is applied to optimize the longitudinal fin by minimizing the total melting *** analysis concludes that a fin angle of 58.68°reduces the complete melting time of the stearic acid by 44%below the time at 0°.These findings fill a gap in knowledge of the effect on melting performance of the design angle of longitudinal fins and provide a reference for the design of horizontally placed longitudinal finned thermal energy storage units.

关键词： thermal energy storage melting rate enhancement longitudinal fins fin angle phase change materials