检索结果-南通市图书馆

AFSTGCN:Prediction for multivariate time series using an adaptive fused spatial-temporal graph convolutional network

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

Digital Communications and Networks 2024年第2期10卷 292-303页

作者： Yuteng Xiao Kaijian Xia Hongsheng Yin Yu-Dong Zhang Zhenjiang Qian zhaoyang liu Yuehan Liang Xiaodan Li School of Information and Control Engineering China University of Mining and TechnologyXuzhou221116China Department of Informatics University of LeicesterLeicesterLE17RHUK The Affiliated Changshu Hospital of Soochow University Changshu215500China School of Computer Science and Engineering Changshu Institute of TechnologySuzhou215500China

The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other ***,it is important to construct a digital twin ***,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted *** this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)***,we fuse the spatial-temporal graph based on the interrelationship of spatial ***,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding ***,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)*** module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like *** dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted *** on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.

关键词： Adaptive adjacency matrix Digital twin Graph convolutional network Multivariate time series prediction Spatial-temporal graph

Improving millimeter-wave imaging quality using the vortex phase method

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

Defence Technology 2024年第09期 193-202页

作者： Nairui Hu Feng Qi Yelong Wang zhaoyang liu Pengxiang liu Weifan Li Key Laboratory of Terahertz Imaging and Sensing Shenyang Aerospace University Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences

This paper investigates a new vortex wave imaging approach to improve the imaging quality of small metal targets of size less than 1.5 mm. Antennas with different spiral phase plates are designed to efficiently transmit vortex beams with orbital angular momentums(OAMs). By analyzing the OAM spectrum of the target, it was discovered that the predominant reflection contains a particular OAM mode that carries abundant azimuthal information. This can be explained by the OAM selectivity of the target and the guidance of the vortex transmitting beam. A simple reflection vortex imaging system was designed to capture the phase information. Measurement results show that the high image contrast reaches 14.9%, which is twice as high as that of the imaging without OAM. Both of simulations and experiments demonstrate that the vortex phase imaging approach proposed in this paper can effectively improve the imaging quality at 80 GHz. This approach is suitable for other millimeter wave imaging systems and is helpful to improve the resolution in anti-terrorism security checks.

关键词：

Encapsulated Fe(IV)Molecular Complex for Photoacoustic Imaging

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

CCS Chemistry 2024年第5期6卷 1184-1197页

作者： Ye Xu Chao Li Zhong-Yu Yu Jiamin Wang zhaoyang liu Chao Jiang Zhen-Feng Chen Xiaoyu Wu Ming-Xing Li Hong Yang Zhao-Xi Wang Jonathan L.Sessler Department of Chemistry Center for Supramolecular Chemistry and CatalysisInnovative Drug Research CenterShanghai UniversityShanghai 200444 College of Chemistry and Materials Science Shanghai Key Laboratory of Rare Earth Functional MaterialsShanghai Frontiers Science Center of Biomimetic CatalysisShanghai Normal UniversityShanghai 200234 Sijing Community Health Service Center of Songjiang District Shanghai 201601 Key Laboratory for Chemistry and Molecular Engineering of Medicinal Resources Guangxi Normal UniversityGuilin 541004 Department of Chemistry The University of Texas at AustinAustinTexas 78712-1224

stable neutral Fe(IV)complex(Fe-HDCL),readily accessible on the g scale,was found to possess high water solubility and good stability(<5%degradation over 4 h upon photoirradiation).Fe-HDCL is green and absorbs light effectively in the visible region(500–800 nm)with aλmax at 650 nm(ɛ=7830 M^(−1)cm^(−1)).Fe-HDCL also exhibits photothermal(PT)behavior comparable to single-wall carbon nanotubes in the solid *** aqueous solution,high PT conversion(η=72.6%)is achieved,and a strong hyperthermia-based inhibition of cell growth is observed upon subjecting Fe-HDCL to near-infrared 730 nm laser *** biological studies in vitro and in vivo confirmed that Fe-HDCL is biocompatible,clears readily,and allows the visual detection of blood *** subjecting mice to intravenous injection at low doses(e.g.,50μmol·kg^(−1)),Fe-HDCL also permits the photoacoustic(PA)imaging of kidneys and the evaluation of renal fibrosis in mouse *** addition,Fe-HDCL allows PA-based imaging of brain tissues,presumably reflecting its ability to pass through the blood-brain *** thus propose that Fe-HDCL has a role to play as PT agent and as a photodiagnostic.

关键词： stable Fe(IV)complex blood-brain barrier molecular cage photoacoustic imaging renal fibrosis

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

弱特征表面形貌测量的低成本渐进式匹配方法

红外与激光工程 2024年第7期53卷 169-178页

作者：房长帅刘赵阳王倩雯张效栋天津大学精密测试技术及仪器国家重点实验室天津300072 天津大学精密仪器与光电子工程学院天津300072 三代光学科技(天津)有限公司天津300072

弱特征连续表面的匹配问题是计算机视觉和图像处理中的一个挑战性问题,基于标准夹具的特征辅助可以准确地实现测量数据与模型的匹配,但该方法成本较高。针对该问题,提出了一种低成本的渐进式的匹配算法,首先基于带有边界罚函数的“点到... 详细信息

弱特征连续表面的匹配问题是计算机视觉和图像处理中的一个挑战性问题,基于标准夹具的特征辅助可以准确地实现测量数据与模型的匹配,但该方法成本较高。针对该问题,提出了一种低成本的渐进式的匹配算法,首先基于带有边界罚函数的“点到面”ICP算法实现粗配准,接着通过对测量数据进行两步微调即可对标工业常用评价结果。以汽车玻璃的面形误差评价为例,仿真和实验结果表明,基于所提方法匹配后的面形误差接近传感器本身的误差级别。对于40 cm×40 cm的汽车玻璃,基于所提方法匹配线结构光测量的玻璃数据与三坐标数据,两者偏差在-0.06/0.08 mm,基本满足工业需求。

关键词：仪器科学与技术弱特征表面配准渐进式匹配算法汽车玻璃 ICP算法

在线全文

学校读者我要写书评

暂无评论

砂化白云岩变压力注浆扩散规律研究

岩石力学与工程学报 2024年第S1期43卷 3477-3490页

作者：杨柳姜晓宇陶志刚王丰年刘朝阳中国矿业大学(北京)深部岩土力学与地下工程国家重点实验室北京100083

为研究滇中引水工程玉溪施工段白云岩砂化对隧道注浆加固的影响,进而揭示浆液扩散规律,综合开展扫描电镜(SEM)试验、理论分析以及多物理场流固耦合数值模拟一系列深入研究。结果表明,白云岩在溶蚀作用下砂化且内部构造发育呈多尺度孔隙... 详细信息

为研究滇中引水工程玉溪施工段白云岩砂化对隧道注浆加固的影响,进而揭示浆液扩散规律,综合开展扫描电镜(SEM)试验、理论分析以及多物理场流固耦合数值模拟一系列深入研究。结果表明,白云岩在溶蚀作用下砂化且内部构造发育呈多尺度孔隙-裂隙网络体系分布特征,注浆时浆液扩散迁移的过程中存在前锋面并产生明显指进现象,发育构型不同的裂隙会导致水泥浆液扩散形态的不规则性和非稳定性。相比传统的恒压注浆,变压力梯度注浆更利于对砂化后地层复杂构造发育的多尺度裂隙进行均匀填充,浆液凝固后胶结破碎岩体减小围岩应力分布区域同时缓解拱顶、拱底的应力集中现象,对于提高围岩稳定性具有更加显著的效果。以上研究可为砂化白云岩地层隧道的实际注浆工程设计及施工提供理论参考。

关键词：岩石力学砂化白云岩滇中引水注浆扩散变压力梯度流固耦合

嵌入式共固化缝合阻尼复合材料梁的自由振动分析

在线全文

学校读者我要写书评

暂无评论

振动与冲击 2024年第10期43卷 205-214,222页

作者：刘昭阳梁森胡子健孙瑞骏青岛理工大学机械与汽车工程学院山东青岛266520

嵌入式共固化缝合阻尼复合材料(embedded co-cured stitched damping composite, ECSDC)相对于传统的复合材料具有高比刚度、高比强度,高层间结合性能及三向力学可设计性等优点。运用Hamilton原理、结合能量法和复刚度法,推导出ECSDC梁... 详细信息

嵌入式共固化缝合阻尼复合材料(embedded co-cured stitched damping composite, ECSDC)相对于传统的复合材料具有高比刚度、高比强度,高层间结合性能及三向力学可设计性等优点。运用Hamilton原理、结合能量法和复刚度法,推导出ECSDC梁结构的动力学微分方程表达式,通过将该偏微分方程转化为线性齐次方程组的方式,代入对边简支的边界条件,进而得到该模型的理论解。作为算例,通过进行模态试验、运用ANSYS有限元模拟和MATLAB数值计算研究了ECSDC梁的典型结构,三者所得的结果吻合较好,验证了该理论模型和方法的准确性。在此基础上,用验证的理论模型研究了设计参数对ECSDC梁结构固有振动特性的影响。结果表征了嵌入式共固化缝合阻尼复合材料梁结构比连续阻尼夹嵌复合材料梁结构具有更高的抗弯刚度,为缝合阻尼复合材料动态特性研究提供了理论层面的新思路。

关键词：复合材料缝合阻尼自由振动动力学模态试验

基于强化学习的光网络自适应高效率RWA算法(特邀)

在线全文

学校读者我要写书评

暂无评论

光通信研究 2024年第5期 63-70页

作者：刘兆洋潘必韬北京邮电大学信息与通信工程学院北京100876

【目的】在光网络中,目前基于深度强化学习(DRL)的路由与波长分配(RWA)算法大多依赖于K最短路径(KSP)路由算法提前计算备选路径,这种方法缺乏灵活性和动态性,当网络拓扑变化时需要为所有节点对重新进行KSP计算。为了解决上述问题,文章... 详细信息

【目的】在光网络中,目前基于深度强化学习(DRL)的路由与波长分配(RWA)算法大多依赖于K最短路径(KSP)路由算法提前计算备选路径,这种方法缺乏灵活性和动态性,当网络拓扑变化时需要为所有节点对重新进行KSP计算。为了解决上述问题,文章提出了基于DRL的自适应高效率(ADE)-RWA框架。【方法】文章提出的ADE-RWA框架的关键点及创新之处在于训练过程中,DRL的智能体在动作选择时从当前节点出发选择最优单步连接,而不是预先计算的完整路径,从而可以动态实时依据网络状态的变化做出路由策略的改变,以适应链路故障等网络拓扑改变的情况。ADE-RWA框架的另一关键点在于DRL训练过程不仅训练其决策神经网络,并且每次成功分配一条路径时,都将其以路由表(LUT)的形式存储。在DRL训练收敛后,网络路径的LUT信息也将完整。此时使用LUT直接查找可用路径,可有效降低计算成本,提高RWA算法效率。此外,LUT查找与DRL训练能够实现动态切换。文章所提算法通过动态感知网络状态的变化,当网络故障引起拓扑变化时,切换到DRL阶段继续进行训练,保证了LUT的动态更新。【结果】实验结果表明,与KSP-首次拟合(FF)和路由调制和频谱分配的深度学习(DeepRMSA)算法相比,文章所提ADE-RWA框架的阻塞率分别降低了36%和30%;且当发生链路故障时,ADE-RWA框架可以迅速适应网络拓扑的变化。【结论】文章提出了基于DRL的ADE-RWA框架,实现了动态光网络拓扑下的自适应RWA,并降低了计算成本。

关键词：波长路由光网络路由与波长分配深度强化学习数字孪生

同方期刊数据库博看期刊

考虑PWM波形特征的纳米晶磁心损耗模型的研究及验证

在线全文

学校读者我要写书评

暂无评论

电工技术学报 2024年第6期39卷 1602-1612页

作者：赵志刚贾慧杰刘朝阳赵安琪高鹏旭省部共建电工装备可靠性与智能化国家重点实验室(河北工业大学) 天津300401 河北省电磁场与电器可靠性重点实验室(河北工业大学) 天津300401

磁心损耗精确预测对于电力电子变压器的优化设计至关重要。然而,传统的磁心损耗模型在复杂激励下适用性较差,尤其对于占空比可调、高次谐波含量丰富的PWM波磁心损耗预测,计算精度显著下降。基于Jordan损耗分离模型,建立了一种考虑PWM波... 详细信息

磁心损耗精确预测对于电力电子变压器的优化设计至关重要。然而,传统的磁心损耗模型在复杂激励下适用性较差,尤其对于占空比可调、高次谐波含量丰富的PWM波磁心损耗预测,计算精度显著下降。基于Jordan损耗分离模型,建立了一种考虑PWM波形特征的磁心损耗计算方法。首先,该方法根据激励波形特征,推导出相应的波形系数及等效频率来计算PWM波激励下的动态涡流损耗,将Jordan模型的适用范围从正弦拓展到PWM波激励下的磁心损耗计算;然后,分析了不同占空比激励下激励波形有效频率及高次谐波含量变化对损耗系数的影响,并对其进行数学表征,实现了整个占空比范围内磁心损耗的精确预测;最后,搭建了高频非正弦激励下软磁材料磁特性测量平台,针对1K107B纳米晶材料,测量了两种典型PWM波激励下的损耗数据。实验结果表明,所建立的磁心损耗模型具有较高的计算精度,相比于传统的Steinmetz改进公式,整体精度提高了25%。

关键词：纳米晶磁心损耗 PWM波形特征 Jordan模型

Effect of substrate preset temperature on crystal growth and microstructure formation in laser powder deposition of single-crystal superalloy

在线全文

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2018年第11期34卷 2116-2124页

作者： zhaoyang liu Zi Wang College of Innovation and Entrepreneurship Southern University of Science and Technology Shenzhen Key Laboratory for Additive Manufacturing of High Performance Materials Southern University of Science and Technology State Key Laboratory of Powder Metallurgy Central South University

A successful repair of single-crystal components needs to avoid the stray grain formation and achieves continuous epitaxial growth of columnar dendrites in the repaired zone. In this study, the effect of substrate preset temperature on crystal growth and microstructure formation in laser powder deposition of single-crystal superalloy was studied through an improved mathematical model and corresponding experimental approaches. The results indicated that the variation of substrate preset temperature between-30℃ and ＋210℃ changes the molten pool morphology little, but obviously affects the columnar-to-equiaxed transition conditions. The preheating of substrate facilitates the stray grain formation and enlarges the primary columnar dendrite arm spacing, while the situation for precooling of substrate is opposite. Under the specific processing conditions, the critical condition for continuous epitaxial growth is that the substrate preset temperature Tsub≤ ＋90℃. When the substrate preset temperature Tsubis below ＋90℃, the height ratio of melting depth to total height of the molten pool is larger than that of stray grain, ensuring that stray grains can be completely remelted and the continuous columnar dendrites during the multi-layer laser powder deposition process on（001） surface of single-crystal substrate can be achieved.

关键词： Single-crystal superalloy Crystal growth Laser powder deposition