检索结果-南通市图书馆

Multi-Material Topology Optimization of 2D Structures Using Convolutional Neural Networks

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第8期140卷 1919-1947页

作者： Jiaxiang Luo Weien Zhou Bingxiao Du Daokui Li wen yao College of Aerospace Science and Engineering National University of Defense TechnologyChangsha410073China Defense Innovation Institute Chinese Academy of Military ScienceBeijing100071China Intelligent Game and Decision Laboratory Chinese Academy of Military ScienceBeijing100071China

In recent years,there has been significant research on the application of deep learning(DL)in topology optimization(TO)to accelerate structural ***,these methods have primarily focused on solving binary TO problems,and effective solutions for multi-material topology optimization(MMTO)which requires a lot of computing resources are still ***,this paper proposes the framework of multiphase topology optimization using deep learning to accelerate MMTO *** framework employs convolutional neural network(CNN)to construct a surrogate model for solving MMTO,and the obtained surrogate model can rapidly generate multi-material structure topologies in negligible time without any *** performance evaluation results show that the proposed method not only outputs multi-material topologies with clear material boundary but also reduces the calculation cost with high prediction ***,in order to find a more reasonable modeling method for MMTO,this paper studies the characteristics of surrogate modeling as regression task and classification *** the training of 297 models,our findings show that the regression task yields slightly better results than the classification task in most ***,The results indicate that the prediction accuracy is primarily influenced by factors such as the TO problem,material category,and data ***,factors such as the domain size and the material property have minimal impact on the accuracy.

关键词： Multi-material topology optimization convolutional neural networks deep learning finite element analysis

A new two-step variational model for multiplicative noise removal with applications to texture images

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

Applied Mathematics(A Journal of Chinese Universities) 2024年第3期39卷 486-501页

作者： ZHANG Long-hui yao wen-juan SHI Sheng-zhu GUO Zhi-chang ZHANG Da-zhi School of Mathematics Harbin Institute of TechnologyHarbin 150001China

Multiplicative noise removal problems have attracted much attention in recent *** additive noise,multiplicative noise destroys almost all information of the original image,especially for texture *** by the TV-Stokes model,we propose a new two-step variational model to denoise the texture images corrupted by multiplicative noise with a good geometry explanation in this *** the first step,we convert the multiplicative denoising problem into an additive one by the logarithm transform and propagate the isophote directions in the tangential field *** the isophote directions are constructed,an image is restored to fit the constructed directions in the second *** existence and uniqueness of the solution to the variational problems are *** these two steps,we use the gradient descent method and construct finite difference schemes to solve the ***,the augmented Lagrangian method and the fast Fourier transform are adopted to accelerate the *** results show that the proposed model can remove the multiplicative noise efficiently and protect the texture well.

关键词： multiplicative noise removal texture images total variation two-step variational method aug-mented Lagrangian method

Populational change of CD4^(+)CD25^(+)Treg cells is responsible for the synergistic effect of the combination of RAMP2 with baicalin in treating recurrent spontaneous abortion mouse models

在线全文

学校读者我要写书评

暂无评论

Traditional Medicine Research 2024年第8期9卷 59-66页

作者： Cong Chen Zhuo-Lan Li Jing-Tian Guo wen-yao Xue Wei Guo Department of Gynecology Jiangsu Province Hospital of Chinese MedicineAffiliated Hospital of Nanjing University of Chinese MedicineNanjing 210029China Jiangsu Key Laboratory of Druggability of Biopharmaceuticals State Key Laboratory of Natural MedicinesSchool of Life Science and TechnologyChina Pharmaceutical UniversityNanjing 211198China

Background: The absence of a safe and effective therapy for recurrent spontaneous abortion due to a maternofetal failure in immunological tolerance remains an intractable clinical obstacle for surgeons. Recently, traditional Chinese medicine has become a feasible alternative for certain diseases, including recurrent spontaneous abortion. However, because of the complex composition of the traditional Chinese medicine formula, its action mechanism remains unclear. Methods: We selected two isolated active ingredients (RAMP and baicalin) from the traditional Chinese medicine formula and used an abortion-prone CBA/J × DBA/2 model to simulate human RSA and compared the changes in fetal resorption rate, Treg cell percentage, and relevant cytokines before and after combination therapy. In addition, The mechanisms were preliminarily discussed using in vitro differentiation models. Results: In CBA/J × DBA/2 abortion-prone mice, the combination therapy resulted in a lower embryo resorption rate compared to that obtained with individual delivery of either RAMP or baicalin, thereby playing an embryo-protective role through the increase in Treg cells for the maintenance of maternal-fetal immune tolerance. In in vitro primary cell differentiation experiments, the concentration of Treg cells significantly increased from 11% to 17.9% after the combination therapy compared to that of the single administration group. Conclusion: the synergistic effects of RAMP and baicalin were responsible for Treg differentiation. The present study provides a solid basis for improving the applicability of traditional Chinese herbs in the treatment of recurrent spontaneous abortion.

关键词： recurrent spontaneous abortion Atractylodes macrocephala Koidz. Scutellaria baicalensis Georgi CBA/J×DBA/2 regulatory T cells

液晶分子优化给体材料组装制备高性能有机太阳能电池

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

高分子学报 2024年第6期55卷 698-708页

作者：曾光张奔李耀文苏州大学苏州市新型半导体光电材料与器件重点实验室苏州215123

活性层形貌优化是实现高效、稳定的体异质结有机太阳能电池(OSC)的关键,添加剂工程被广泛用于优化OSC活性层的膜形貌.基于此,本文工作提出了一种利用具有简单结构的液晶分子4-氰基-4'-庚基联苯(7-CB)作为添加剂优化给体聚合物(PM6)在共... 详细信息

活性层形貌优化是实现高效、稳定的体异质结有机太阳能电池(OSC)的关键,添加剂工程被广泛用于优化OSC活性层的膜形貌.基于此,本文工作提出了一种利用具有简单结构的液晶分子4-氰基-4'-庚基联苯(7-CB)作为添加剂优化给体聚合物(PM6)在共混膜中聚集行为的策略.通过掠入射广角X射线散射、原位吸收光谱及分子动力学模拟等表征发现,7-CB通过与PM6的烷基侧链之间的范德华力和CH/π相互作用诱导PM6规整排列,增强了PM6之间的相互作用,提高了活性层薄膜的结晶度.得益于此,无任何后处理的活性层薄膜中电荷传输得到改善,电荷重组被大幅抑制.基于7-CB处理的PM6:L8-BO制备的硬质和柔性二元OSCs效率分别从15.41%和14.90%提高到18.01%和17.26%.

关键词：有机太阳能电池添加剂自组装

Phase structure evolution and its effect on magnetic and mechanical properties of B-doped Sm_(2)Co_(17)-type magnets with high Fe content

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第9期33卷 582-588页

作者： yao-wen Li Zhuang Liu Hai-Chen Wu Fang Wang Chao-Qun Zhu Dong-Liang Tan Yu Liu Yang Yang Ming-Xiao Zhang Ren-Jie Chen A-Ru Yan Key Laboratory of Magnetic Molecules and Magnetic Information Materials of Ministry ofEducation&School of Chemistry and Materials Science Shanxi Normal UniversityTaiyuan 030032China CISRI&NIMTE Joint Innovation Center for Rare Earth Permanent Magnets Ningbo Institute ofMaterial Technology and EngineeringChinese Academy of SciencesNingbo 315201China University of Chinese Academy of Sciences Beijing 100049China

The unique cellular microstructure of Fe-rich Sm_(2)Co_(17)-type permanent magnets is closely associated with the structure of the solid solution *** investigate the phase structure,magnetic properties,and mechanical behavior of B-doped Sm_(2)Co_(17)-type magnets with high Fe *** doped B atoms can diffuse into the interstitial vacancy,resulting in lattice expansion and promote the homogenization of the phase organizational structure during the solid solution treatment in ***,the resulting second phase plays a dominant role to result in more microtwin structures and highly ordered 2:17R phases in the solid solution stage,which inhibits the ordering transformation of 1:7H phase during aging and affects the generation of the cellular structure,and to result in a decrease in magnetic properties,yet the interface formed between it and the matrix phase hinders the movement of dislocations and enhances the mechanical ***,the precipitation of high flexural strain grain boundary phase induced by B element doping is also a new and effective way to improve the flexural strain of Sm_(2)Co_(17)-type *** study provides a new understanding of the phase structure evolution and its effect on the magnetic and mechanical properties of Sm_(2)Co_(17)-type magnets with high Fe content.

关键词： Sm_(2)Co_(17)-type magnets magnetic and mechanical properties

在线全文

学校读者我要写书评

暂无评论

“社会美育”:蔡元培美育思想的第二原理

求是学刊 2024年第5期51卷 161-168页

作者：姚文放首都师范大学艺术与美育研究院北京100048

蔡元培在大力提倡“以美育代宗教”的同时,长期重视社会美育,并在《美育实施的方法》中为之正名,提出“社会美育”的概念。蔡元培的美育思想是一个双线结构“,以美育代宗教”说与“社会美育”的互恰关系一以贯之,并行不悖,构成一主一从... 详细信息

蔡元培在大力提倡“以美育代宗教”的同时,长期重视社会美育,并在《美育实施的方法》中为之正名,提出“社会美育”的概念。蔡元培的美育思想是一个双线结构“,以美育代宗教”说与“社会美育”的互恰关系一以贯之,并行不悖,构成一主一从两大线索。在这个意义上说“,社会美育”构成了蔡元培美育思想的第二原理。在蔡元培那里“,社会美育”以陶养感情、促进人生为精神旨趣。对“社会美育”的建构与西方美学相关,也不乏结合本土传统的创造和开新。在20世纪30年代,蔡元培美育思想的开拓创新与抗日的烽火共始终,战争风云在其美学思想中留下了浓重的痕迹,也给其“社会美育”注入了勇猛悲壮的内涵,使之达到了新的升华。

关键词：社会美育蔡元培美育思想第二原理

Structural knowledge-driven meta-learning for task offloading in vehicular networks with integrated communications,sensing and computing

在线全文

学校读者我要写书评

暂无评论

Journal of Information and Intelligence 2024年第4期2卷 302-324页

作者： Ruijin Sun yao wen Nan Cheng Wei Wang Rong Chai Yilong Hui State Key Laboratory of ISN Xidian UniversityXi'an 710071China Chongqing Key Laboratory of Mobile Communication Technology Chongqing University of Posts and TelecommunicationsChongqing 400065China

Task offloading is a potential solution to satisfy the strict requirements of computation-intensive and latency-sensitive vehicular applications due to the limited onboard computing ***,the overwhelming upload traffic may lead to unacceptable uploading *** tackle this issue,for tasks taking environmental data as input,the data perceived by roadside units(RSU)equipped with several sensors can be directly exploited for computation,resulting in a novel task offloading paradigm with integrated communications,sensing and computing(I-CSC).With this paradigm,vehicles can select to upload their sensed data to RSUs or transmit computing instructions to RSUs during the *** optimizing the computation mode and network resources,in this paper,we investigate an I-CSC-based task offloading problem to reduce the cost caused by resource consumption while guaranteeing the latency of each *** this nonconvex problem can be handled by the alternating minimization(AM)algorithm that alternatively minimizes the divided four sub-problems,it leads to high computational complexity and local optimal *** tackle this challenge,we propose a creative structural knowledge-driven meta-learning(SKDML)method,involving both the model-based AM algorithm and neural ***,borrowing the iterative structure of the AM algorithm,also referred to as structural knowledge,the proposed SKDML adopts long short-term memory(LSTM)networkbased meta-learning to learn an adaptive optimizer for updating variables in each sub-problem,instead of the handcrafted counterpart in the AM ***,to pull out the solution from the local optimum,our proposed SKDML updates parameters in LSTM with the global loss *** results demonstrate that our method outperforms both the AM algorithm and the meta-learning without structural knowledge in terms of both the online processing time and the network performance.

关键词： Knowledge-driven meta-learning Integration of communication Sensing and computing Task offloading Vehicular networks

基于改进神经网络的船舶航行速度估计数学模型

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

舰船科学技术 2024年第4期46卷 70-73页

作者：姚光文上海华东师范大学物理与电子科学学院上海200241 上海电子信息职业技术学院上海201411

船舶航行速度直接影响船舶航行安全与路径规划效果,为此建立基于改进神经网络的船舶航行速度估计数学模型,提升船舶航行速度估计效果。利用位置编码机制,编码处理风速与波高等船舶航向速度相关数据;在编解码卷积神经网络内,引入自注意... 详细信息

船舶航行速度直接影响船舶航行安全与路径规划效果,为此建立基于改进神经网络的船舶航行速度估计数学模型,提升船舶航行速度估计效果。利用位置编码机制,编码处理风速与波高等船舶航向速度相关数据;在编解码卷积神经网络内,引入自注意力机制,得到改进编解码卷积神经网络;利用编码后的船舶航速训练数据,训练改进神经网络,建立船舶航行速度估计数学模型;在该模型内,输入编码后的船舶航速测试数据,通过自注意力机制,提取船舶航速数据特征,并结合自注意力蒸馏剔除冗余特征;通过全连接层处理船舶航速数据特征,输出船舶航行速度估计结果。实验证明,该模型可有效提取船舶航速数据特征;该模型可精准估计船舶航行速度;在不同浪向下,该模型船舶航行速度估计的决定系数均较高,即估计精度较高。

关键词：改进神经网络船舶航行速度估计数学模型位置编码自注意力机制

Probing the peripheral self-generated magnetic field distribution in laser-plasma magnetic reconnection with Martin-Puplett interferometer polarimeter

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第4期33卷 129-134页

作者：张雅芃姚嘉文刘正东马作霖仲佳勇 Department of Astronomy Beijing Normal UniversityBeijing 100875China Institute for Frontiers in Astronomy and Astrophysics Beijing Normal UniversityBeijing 102206China

Magnetic reconnection of the self-generated magnetic fields in laser-plasma interaction is an important laboratory method for modeling high-energy density astronomical and astrophysical *** use the Martin-Puplett interferometer(MPI)polarimeter to probe the peripheral magnetic fields generated in the common magnetic reconnection configuration,two separated coplanar plane targets,in laser-target *** introduce a new method that can obtain polarization information from the interference pattern instead of the sinusoidal function fitting of the intensity.A bidirectional magnetic field is observed from the side view,which is consistent with the magneto-hydro-dynamical(MHD)simulation results of self-generated magnetic field *** find that the cancellation of reverse magnetic fields after averaging and integration along the observing direction could reduce the magnetic field strength by one to two orders of *** indicates that imaging resolution can significantly affect the accuracy of measured magnetic field strength.

关键词： laser-plasma experiment polarimeter self-generated magnetic field magnetic reconnection