资源类型

期刊论文 19

年份

2024 1

2023 2

2022 1

2020 2

2019 1

2018 1

2016 1

2012 2

2009 2

2008 1

2007 1

2006 1

2004 1

2001 1

展开 ︾

关键词

CITATION 1

RAMI 4.0 1

WIMS 1

Weibull分布杂波 1

ZMNL 1

中医；药材推荐；知识图谱；图注意力网络 1

中国 1

中子 1

主观意图 1

人工智能 1

价值维 1

仿真 1

信息物理系统（CPS） 1

功能性 1

医院中子照射器 1

医院中子照射器I型堆 1

反应性 1

发展规划 1

可学习性 1

展开 ︾

检索范围：

排序： 展示方式：

Physics-Informed Deep Learning-Based Real-Time Structural Response Prediction Method

Ying Zhou,Shiqiao Meng,Yujie Lou,Qingzhao Kong,

《工程（英文）》 doi: 10.1016/j.eng.2023.08.011

摘要： High-precision and efficient structural response prediction is essential for intelligent disaster prevention and mitigation in building structures, including post-earthquake damage assessment, structural health monitoring, and seismic resilience assessment of buildings. To improve the accuracy and efficiency of structural response prediction, this study proposes a novel physics-informed deep-learning-based real-time structural response prediction method that can predict a large number of nodes in a structure through a data-driven training method and an autoregressive training strategy. The proposed method includes a Phy-Seisformer model that incorporates the physical information of the structure into the model, thereby enabling higher-precision predictions. Experiments were conducted on a four-story masonry structure, an eleven-story reinforced concrete irregular structure, and a twenty-one-story reinforced concrete frame structure to verify the accuracy and efficiency of the proposed method. In addition, the effectiveness of the structure in the Phy-Seisformer model was verified using an ablation study. Furthermore, by conducting a comparative experiment, the impact of the range of seismic wave amplitudes on the prediction accuracy was studied. The experimental results show that the method proposed in this paper can achieve very high accuracy and at least 5000 times faster calculation speed than finite element calculations for different types of building structures.

关键词： Structural seismic response prediction     Physics information informed     Real-time prediction     Earthquake engineering     Data-driven machine learning    

HTML PDF 收藏

FlowDNN：一种用于快速精确流场预测的物理启发深度神经网络 Research Articles

陈东林1,高翔1,2,徐传福1,2,王思齐1,2,陈世钊1,方建滨1,王铮3

《信息与电子工程前沿（英文）》 2022年 第23卷 第2期   页码 207-219 doi: 10.1631/FITEE.2000435

摘要： 对于与流场相关的设计优化问题，例如飞机和汽车空气动力学设计，计算流体力学（CFD）模拟通常用于预测流场并分析性能。虽然CFD模拟十分重要，但它的迭代计算非常需要计算资源且极其耗时。昂贵的模拟开销限制了大范围设计空间的探索，并阻碍了实时的交互式设计。在本文中，我们提出FlowDNN模型，它是一种新颖的深度神经网络，可从CFD结果中高效地学习流场表示。FlowDNN根据给定的流动条件和几何形状可以直接预测预期的流场结果，从而极大地节省计算时间。FlowDNN首次结合了流体力学的基本守恒定律和注意力机制进行定常流场预测。这样做不仅可以提高预测准确性，而且可以维持预测流场的物理一致性，这对于CFD模拟至关重要。本文设计了多种指标以评估FlowDNN预测的整体流场和关键区域的结果（如流场快速变化的边界层）。实验结果表明，FlowDNN明显优于其他方法且具有更短的推理时间和更准确的结果。它与最新的GPU并行求解器相比，生成流场的速度提升14 000倍以上，同时保持预测误差在5%以内。

关键词： 深度神经网络；流场预测性能；注意机制；物理损失函数    

HTML PDF 收藏

基于内嵌物理信息深度学习模型的增材制造工艺参数及熔池尺寸预测 Article

赵明志, 韦辉亮, 茅仪铭, 张长东, 刘婷婷, 廖文和

《工程（英文）》 2023年 第23卷 第4期   页码 181-195 doi: 10.1016/j.eng.2022.09.015

摘要：

熔池特征对激光粉末床熔融（PBF）的打印质量有显著影响，打印参数和熔池尺寸的定量预测对LPBF中复杂过程的智能控制至关重要。然而由于高度非线性，打印参数和熔池尺寸的双向预测一直极具挑战。为了解决此问题，本工作融合典型实验、机理模型和深度学习研究激光PBF过程中关键参数和熔池特性的正向和逆向预测。实验提供基础数据，机理模型显著增强数据集，多层感知器（MLP）深度学习模型则根据实验和机理模型构建的数据集预测熔池尺寸和工艺参数。结果表明可以实现熔池尺寸和工艺参数的双向预测，最高预测准确率接近99.9%，平均预测准确率超过90.0%。此外，MLP模型的预测准确率与数据集的特征密切相关，即数据集的可学习性对预测准确率有至关重要的影响。通过机理模型增强数据集后的最高预测精度为97.3%，而仅使用实验数据集时的最高预测精度只有68.3%。MLP模型的预测准确率在很大程度上取决于数据集的质量。研究结果表明使用MLP进行复杂相关性的双向预测对于激光PBF是可行的，本工作为选定智能增材制造的工艺条件和结果提供了一个新颖而实用的框架。

关键词： 增材制造     熔池     模型     深度学习     可学习性    

HTML PDF 收藏

Where physics meets chemistry: Thin film deposition from reactive plasmas

Andrew Michelmore, Jason D. Whittle, James W. Bradley, Robert D. Short

《化学科学与工程前沿（英文）》 2016年 第10卷 第4期   页码 441-458 doi: 10.1007/s11705-016-1598-7

摘要： Functionalising surfaces using polymeric thin films is an industrially important field. One technique for achieving nanoscale, controlled surface functionalization is plasma deposition. Plasma deposition has advantages over other surface engineering processes, including that it is solvent free, substrate and geometry independent, and the surface properties of the film can be designed by judicious choice of precursor and plasma conditions. Despite the utility of this method, the mechanisms of plasma polymer growth are generally unknown, and are usually described by chemical (i.e., radical) pathways. In this review, we aim to show that plasma physics drives the chemistry of the plasma phase, and surface-plasma interactions. For example, we show that ionic species can react in the plasma to form larger ions, and also arrive at surfaces with energies greater than 1000 kJ?mol (>10 eV) and thus facilitate surface reactions that have not been taken into account previously. Thus, improving thin film deposition processes requires an understanding of both physical and chemical processes in plasma.

关键词： thin films     plasma physics     plasma chemistry     functionalization     polymer    

HTML PDF 收藏

空间物理和空间天气探测与研究

王赤

《中国工程科学》 2008年 第10卷 第6期   页码 41-45

摘要：

空间物理学是1957年人造卫星发射成功后迅速发展起来的一门交叉学科。近50年来，空间已成为人类生存的第四环境，其重要性日益突出。20世纪90年代初，空间物理学与空间应用的密切结合产生了专门研究和预报空间环境中灾害性过程及其变化规律，减轻或防止空间灾害并为人类活动服务的空间天气学。文章简要总结了国外及国内空间物理和空间天气探测的历程和发展趋势，并提出对我国未来空间物理和空间天气探测发展规划和探测路线图的几点建议。

关键词： 空间物理     空间天气     空间物理探测     发展规划    

HTML PDF 收藏

物理学与中国能源可持续发展——献给2005世界物理年

杜祥琬,李庆忠

《中国工程科学》 2006年 第8卷 第2期   页码 1-6

摘要：

物理学与工程技术有着密切的相互联系，能源工程技术与物理学的关系具有典型的代表性，物理学的应用可以对我国能源事业的发展做出重要的贡献。文章着重阐述了原子核物理学和核能工程（包括裂变核能和聚变核能），光电效应与光伏发电，风能、生物质能与物理学，物理化学与煤的多联产、洁净化技术，地球物理学与能源资源勘探等能源问题；讨论了物理学在节能中的三个应用：节能照明、建筑节能和交通节能；分析了中国能源的可持续发展前景。

关键词： 物理学     中国     能源     节能     可持续发展    

HTML PDF 收藏

不辱历史使命致力民族强盛的中国工程物理研究院

《中国工程科学》 2001年 第3卷 第8期   页码 91-92

HTML PDF 收藏

泰州大桥中塔沉井基础承载力模型试验研究

阮静,胡丰

《中国工程科学》 2012年 第14卷 第5期   页码 57-61

摘要：

泰州大桥中塔位于江中心，基础覆盖层高达200 m。通过多方面比选，基础采用58 m×44 m四角倒圆的矩形沉井，高76 m。为确保泰州大桥中塔沉井基础的安全和稳定，开展了1∶100的模型试验，获取了泰州大桥沉井极限承载力以及沉井埋深、土体含水量、侧壁摩阻力对极限承载力的影响。

关键词： 沉井承载力     泰州大桥     物理模型试验    

HTML PDF 收藏

Analysis and experiment of controllability of magnetorheological fluids based on micro-pipeline

Yongqing SU, Yikuan SONG, Jiguang YUE

《机械工程前沿（英文）》 2009年 第4卷 第3期   页码 339-344 doi: 10.1007/s11465-009-0048-3

摘要： The controllability of the magneto-rheological fluid (MRF) flowing through a micro-pipeline is analyzed. The coupled formulas for MRF are deduced by analyzing the property of the flow field and magnetic field. Then, the relationship between the flow speed of MRF and the special shear stress under the effect of the magnetic field is founded. The model of the MRF and micro-pipeline is established by using multi-physics software of Comsol, the curve of - in an ideal condition is attained by modifying parameters, and by adding the boundary condition of the model. This paper provides a theoretical proof of the controllability of MRF flowing through the micro-pipeline and explores MRF’s application on the micro-drive and control field.

关键词： Magneto-rheological fluids (MRF)     micro-pipeline     coupled model     multi-physics simulation    

HTML PDF 收藏

用于重建物理和虚拟抓取的可重构数据手套 Article

刘航欣, 张泽宇, 焦子元, Zhenliang Zhang, Minchen Li, 蒋陈凡夫, 朱毅鑫, Song-Chun Zhu

《工程（英文）》 2024年 第32卷 第1期   页码 203-220 doi: 10.1016/j.eng.2023.01.009

摘要：

In this work, we present a reconfigurable data glove design to capture different modes of human hand–object interactions, which are critical in training embodied artificial intelligence (AI) agents for fine manipulation tasks. To achieve various downstream tasks with distinct features, our reconfigurable data glove operates in three modes sharing a unified backbone design that reconstructs hand gestures in real time. In the tactile-sensing mode, the glove system aggregates manipulation force via customized force sensors made from a soft and thin piezoresistive material; this design minimizes interference during complex hand movements. The virtual reality (VR) mode enables real-time interaction in a physically plausible fashion: A caging-based approach is devised to determine stable grasps by detecting collision events. Leveraging a state-of-the-art finite element method, the simulation mode collects data on fine-grained four-dimensional manipulation events comprising hand and object motions in three-dimensional space and how the object's physical properties (e.g., stress and energy) change in accordance with manipulation over time. Notably, the glove system presented here is the first to use high-fidelity simulation to investigate the unobservable physical and causal factors behind manipulation actions. In a series of experiments, we characterize our data glove in terms of individual sensors and the overall system. More specifically, we evaluate the system's three modes by ① recording hand gestures and associated forces, ② improving manipulation fluency in VR, and ③ producing realistic simulation effects of various tool uses, respectively. Based on these three modes, our reconfigurable data glove collects and reconstructs fine-grained human grasp data in both physical and virtual environments, thereby opening up new avenues for the learning of manipulation skills for embodied AI agents.

关键词： Data glove     Tactile sensing     Virtual reality     Physics-based simulation    

HTML PDF 收藏

工程科学领域的发展与现代物理学

宋文淼

《中国工程科学》 2004年 第6卷 第9期   页码 14-19

摘要：

从工程科学发展的角度探讨了相对论、量子理论和宏观物理学之间的关系,它们之间的矛盾和共同点,以及如何在共同的发展中寻找建立更加深刻的物理理论的可能途经。

关键词： 相对论     量子理论     工程科学     波函数空间     波粒二象性    

HTML PDF 收藏

电磁超材料：从新物理现象到新信息系统 Review Articles

Rui-yuan WU, Tie-jun CUI

《信息与电子工程前沿（英文）》 2020年 第21卷 第1期   页码 4-26 doi: 10.1631/FITEE.1900465

摘要： 由于对电磁波强大的调控能力，超材料和超表面吸引了越来越多研究者的关注。本文回顾总结近年来电磁超材料的发展，从最初的新物理现象到现在的新信息系统。首先展示等效媒质超材料的定义和应用，包括隐身衣和超材料透镜等。随后介绍二维超材料，即电磁超表面，对空间波和表面波的调控功能，同时概述表面等离子激元及其在微波段的应用。在此基础上，着重介绍新颖的数字编码超材料和可编程超材料，统称信息超材料。通过将理论层的信息科学与物理层的超材料设计联系在一起，实现一系列新型器件和系统，同时实现信息和电磁波调控。最后，对超材料的未来发展做出展望。

关键词： 超材料；等效媒质理论；超表面；表面等离子激元；数字编码；可编程；信息    

HTML PDF 收藏

一种知识引导的基于中医学信息的药材推荐方法 Research Article

金哲,张引,苗嘉旭,杨易,庄越挺,潘云鹤

《信息与电子工程前沿（英文）》 2023年 第24卷 第10期   页码 1416-1429 doi: 10.1631/FITEE.2200662

摘要： 在中国几千年历史中，中医一直是人们关注的焦点。近年来，随着人工智能技术的兴起，部分研究开始以数据驱动的方式学习中医的方剂，即根据病人的症状推荐一组药材。现有大多数药材推荐模型忽略了中医领域的知识，例如药材和症状之间的关系，中药药方形成逻辑，等等。本文提出一种以知识为引导、结合中医学信息的药材推荐方法。本文使用的知识包括从中医典籍及处方中提取的知识图谱，以此得到症状和药材之间的交互和共生关系。利用这些信息，基于图注意力网络提取症状和药材的特征向量。在此基础上，将处方学等中医学信息加入到预测层中，提高了模型对药材的预测能力。最后，在中医处方数据集上进行的实验表明，该方法优于目前主流的药材推荐算法。

关键词： 中医；药材推荐；知识图谱；图注意力网络    

HTML PDF 收藏

一种改进的Weibull分布杂波仿真方法

姜斌,和湘,黎湘,王宏强,郭桂蓉

《中国工程科学》 2007年 第9卷 第1期   页码 44-48

摘要：

针对目前Weibull分布杂波仿真中没有考虑线性滤波器物理可实现性问题，首先深入研究了该杂波模 型的统计特性及其ZMNL仿真方法；在此基础上，引入最小相位特性与复倒谱技术，提出了一种物理可实现的滤 波器产生方法，同时详细阐述了物理可实现Weibull分布杂波随机序列产生的流程；最后，进行了仿真实验，仿 真结果证明了该方法的准确性和有效性。该方法产生的杂波可用于雷达信号模拟、雷达图像分析及雷达最优信 号处理器设计。

关键词： Weibull分布杂波     ZMNL     复倒谱     物理可实现线性滤波器     仿真    

HTML PDF 收藏

Towards an integrated modeling of the plasma-solid interface

Michael Bonitz, Alexey Filinov, Jan-Willem Abraham, Karsten Balzer, Hanno Kählert, Eckhard Pehlke, Franz X. Bronold, Matthias Pamperin, Markus Becker, Dettlef Loffhagen, Holger Fehske

《化学科学与工程前沿（英文）》 2019年 第13卷 第2期   页码 201-237 doi: 10.1007/s11705-019-1793-4

摘要： Solids facing a plasma are a common situation in many astrophysical systems and laboratory setups. Moreover, many plasma technology applications rely on the control of the plasma-surface interaction, i.e., of the particle, momentum and energy fluxes across the plasma-solid interface. However, presently often a fundamental understanding of them is missing, so most technological applications are being developed via trial and error. The reason is that the physical processes at the interface of a low-temperature plasma and a solid are extremely complex, involving a large number of elementary processes in the plasma, in the solid as well as fluxes across the interface. An accurate theoretical treatment of these processes is very difficult due to the vastly different system properties on both sides of the interface: Quantum versus classical behavior of electrons in the solid and plasma, respectively; as well as the dramatically differing electron densities, length and time scales. Moreover, often the system is far from equilibrium. In the majority of plasma simulations surface processes are either neglected or treated via phenomenological parameters such as sticking coefficients, sputter rates or secondary electron emission coefficients. However, those parameters are known only in some cases and with very limited accuracy. Similarly, while surface physics simulations have often studied the impact of single ions or neutrals, so far, the influence of a plasma medium and correlations between successive impacts have not been taken into account. Such an approach, necessarily neglects the mutual influences between plasma and solid surface and cannot have predictive power. In this paper we discuss in some detail the physical processes of the plasma-solid interface which brings us to the necessity of coupled plasma-solid simulations. We briefly summarize relevant theoretical methods from solid state and surface physics that are suitable to contribute to such an approach and identify four methods. The first are mesoscopic simulations such as kinetic Monte Carlo and molecular dynamics that are able to treat complex processes on large scales but neglect electronic effects. The second are quantum kinetic methods based on the quantum Boltzmann equation that give access to a more accurate treatment of surface processes using simplifying models for the solid. The third approach are simulations of surface process that are based on density functional theory (DFT) and time-dependent DFT. The fourths are nonequilibrium Green functions that able to treat correlation effects in the material and at the interface. The price for the increased quality is a dramatic increase of computational effort and a restriction to short time and length scales. We conclude that, presently, none of the four methods is capable of providing a complete picture of the processes at the interface. Instead, each of them provides complementary information, and we discuss possible combinations.

关键词： plasma physics     surface science     plasma-surface modeling     DFT     nonequilibrium Green functions    

HTML PDF 收藏

标题 作者 时间 类型 操作

Physics-Informed Deep Learning-Based Real-Time Structural Response Prediction Method

Ying Zhou,Shiqiao Meng,Yujie Lou,Qingzhao Kong,

期刊论文

FlowDNN：一种用于快速精确流场预测的物理启发深度神经网络

陈东林1,高翔1,2,徐传福1,2,王思齐1,2,陈世钊1,方建滨1,王铮3

期刊论文

基于内嵌物理信息深度学习模型的增材制造工艺参数及熔池尺寸预测

赵明志, 韦辉亮, 茅仪铭, 张长东, 刘婷婷, 廖文和

期刊论文

Where physics meets chemistry: Thin film deposition from reactive plasmas

Andrew Michelmore, Jason D. Whittle, James W. Bradley, Robert D. Short

期刊论文

空间物理和空间天气探测与研究

王赤

期刊论文

物理学与中国能源可持续发展——献给2005世界物理年

杜祥琬,李庆忠

期刊论文

不辱历史使命致力民族强盛的中国工程物理研究院

期刊论文

泰州大桥中塔沉井基础承载力模型试验研究

阮静,胡丰

期刊论文

Analysis and experiment of controllability of magnetorheological fluids based on micro-pipeline

Yongqing SU, Yikuan SONG, Jiguang YUE

期刊论文

用于重建物理和虚拟抓取的可重构数据手套

刘航欣, 张泽宇, 焦子元, Zhenliang Zhang, Minchen Li, 蒋陈凡夫, 朱毅鑫, Song-Chun Zhu

期刊论文

工程科学领域的发展与现代物理学

宋文淼

期刊论文

电磁超材料：从新物理现象到新信息系统

Rui-yuan WU, Tie-jun CUI

期刊论文

一种知识引导的基于中医学信息的药材推荐方法

金哲,张引,苗嘉旭,杨易,庄越挺,潘云鹤

期刊论文

一种改进的Weibull分布杂波仿真方法

姜斌,和湘,黎湘,王宏强,郭桂蓉

期刊论文

Towards an integrated modeling of the plasma-solid interface

Michael Bonitz, Alexey Filinov, Jan-Willem Abraham, Karsten Balzer, Hanno Kählert, Eckhard Pehlke, Franz X. Bronold, Matthias Pamperin, Markus Becker, Dettlef Loffhagen, Holger Fehske

期刊论文