检索结果-南通市图书馆

Deep learning CNN-APSO-LSSVM hybrid fusion model for feature optimization and gas-bearing prediction

Petroleum Science 2024年第4期21卷 2329-2344页

作者： Jiu-Qiang Yang Nian-Tian Lin Kai zhang Yan Cui Chao Fu dong zhang College of Earth Sciences and Engineering Shandong University of Science and Technology Laboratory for Marine Mineral Resources Qingdao National Laboratory for Marine Science and Technology Transportation Institute of Inner Mongolia University Key Laboratory of Gas Hydrate Qingdao Institute of Marine Geology Ministry of Natural Resources

Conventional machine learning(CML) methods have been successfully applied for gas reservoir prediction. Their prediction accuracy largely depends on the quality of the sample data; therefore, feature optimization of the input samples is particularly important. Commonly used feature optimization methods increase the interpretability of gas reservoirs; however, their steps are cumbersome, and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently. In contrast to CML methods, deep learning(DL) methods can directly extract the important features of targets from raw data. Therefore, this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM). This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes, considerably simplifying the feature optimization. A CNN was used for feature optimization to highlight sensitive gas reservoir information. APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results. The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction, giving full play to the advantages of DL and CML methods. The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model. In the feature optimization process of multicomponent seismic attribute data, CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods. In the prediction process, the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy. The constructed CNN-APSO-LSSVM mode

关键词： Multicomponent seismic data Deep learning Adaptive particle swarm optimization Convolutional neural network Least squares support vector machine Feature optimization Gas-bearing distribution prediction

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

A Galaxy Image Augmentation Method Based on Few-shot Learning and Generative Adversarial Networks

引用

Research in Astronomy and Astrophysics 2024年第3期24卷 180-193页

作者： Yiqi Yao Jinqu zhang Ping Du Shuyu dong School of Artificial Intelligence South China Normal UniversityFoshan 528225China School of Computer Science South China Normal UniversityGuangzhou 510631China Guangdong Construction Vocational Technology Institute Guangzhou 511500China

Galaxy morphology classifications based on machine learning are a typical technique to handle enormous amounts of astronomical observation data,but the key challenge is how to provide enough training data for the machine learning *** this article proposes an image data augmentation method that combines few-shot learning and generative adversarial *** Galaxy10 DECaLs data set is selected for the experiments with consistency,variance,and augmentation effects being *** popular networks,including AlexNet,VGG,and ResNet,are used as examples to study the effectiveness of different augmentation methods on galaxy morphology *** results show that the proposed method can generate galaxy images and can be used for expanding the classification model’s training *** to comparative studies,the best enhancement effect on model performance is obtained by generating a data set that is 0.5–1 time larger than the original data ***,different augmentation strategies have considerably varied effects on different types of ***-GAN achieved the best classification performance on the ResNet network for In-between Round Smooth Galaxies and Unbarred Loose Spiral Galaxies,with F1 Scores of 89.54%and 63.18%,*** comparison reveals that various data augmentation techniques have varied effects on different categories of galaxy morphology and machine learning ***,the best augmentation strategies for each galaxy category are suggested.

关键词： techniques image processing-galaxies structure-galaxies general

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Improving flangeability of multiphase steel by increasing microstructural homogeneity

引用

Journal of Iron and Steel Research International 2024年第7期31卷 1736-1745页

作者： Xiao-yu Yang Yong-gang Yang xing Fang Han-long zhang Zhen-li Mi Beijing Advanced Innovation Center for Materials Genome Engineering Institute of Engineering TechnologyUniversity of Science and Technology BeijingBeijing 100083China Shanghai Baosteel Group Corp.Technology Center Shanghai 201900China

Multiphase microstructure significantly increases the strength,usually at the expense of flangeability because of lacking microstructure *** further improve the strength-flangeability of multiphase steel,the microstructural homogeneity was advanced by adjusting the hard martensite/austenite(M/A)*** strength-flangeability was measured via uniaxial tensile tests and hole expansion *** microstructures were characterized using a scanning electron microscope equipped with an electron backscatter diffraction detector and a transmission electron *** tests were supplementally used to quantitatively reveal the microstructural homogeneity of the *** show that the adjusted multiphase steel achieves an excellent ultimate tensile strength(~800 MPa)and flangeability(~135%hole expansion ratio).A promising homogeneous multiphase microstructure was obtained by controlling undercooled austenite transformed at about 600℃.This microstructure consists of soft polygonal ferrite,blocky bainitic ferrite,and hard M/A *** volume fraction of M/A islands is around 5%,and the average size is less than l *** nanoindentation analysis indicated that the participation of M/A islands impressively influenced the microstructural *** strain partition and better mechanical compatibility were present in the adjusted multiphase steel since the plasticity initiation started late,which resulted in a positive ***,avoiding M/A islands distributed in the chain along the rolling direction on the matrix hindered the possibility of voids coalescing into cracks and stabilized the flanging performance.

关键词： Multiphase steel Flangeability Martensite/austenite island-Microstructural homogeneity-Microstructure Compact strip production process

来源：

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

Balanced Fracturing and Cold-welding of Magnesium during Ball Milling Assisted by Carbon Coating:Experimental and Molecular Dynamic Simulation

引用

Journal of Wuhan University of Technology(Materials Science) 2024年第4期39卷 895-903页

作者：韩宗盈 dong Hui DING Guoyang zhang Jiale SONG Xiufang College of Energy Storage Technology Shandong University of Science and TechnologyQingdao 266590China College of Chemical and Biological Engineering Shandong University of Science and TechnologyQingdao 266590China

The lignite-derived carbon from self-protection pyrolysis was employed to balance the fracturing and cold-welding of magnesium during ball *** size analysis indicates that the introduction of lignite-derived carbon can effectively reduce the particle size of Mg while the introduction of graphite does no ***,the effect of lignite-derived carbon on crystallite size reduction of Mg is also better than graphite.A moderate cold-welding phenomenon was observed after ball-milling Mg with the lignite-derived carbon,suggesting less Mg is wasted on the milling vials and *** dynamic simulations reveal that the balanced fracturing and cold-welding of magnesium during ball milling is mainly attributed to the special structure of the lignite-derived carbon:graphitized short-range ordered stacking function as dry lubricant and irregular shape/sharp edge function as milling *** preliminary findings in current study are expected to offer implications for designing efficient Mg-based hydrogen storage materials.

关键词： magnesium lignite-derived carbon cold-welding ball milling molecular dynamic

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Microstructure recognition of steels by machine learning based on visual attention mechanism

引用

Journal of Iron and Steel Research International 2024年第4期31卷 909-923页

作者： xing-yu Chen Lin Cheng Cheng-yang Hu Yu-peng zhang Kai-ming Wu The State Key Laboratory of Refractories and Metallurgy Hubei Province Key Laboratory of Systems Science on Metallurgical ProcessingInternational Research Institute for Steel TechnologyCollaborative Center on Advanced SteelsWuhan University of Science and TechnologyWuhan 430081HubeiChina Metals Valley and Band(Foshan)Metallic Composite Materials Co. Ltd.Foshan 528000GuangdongChina

U-Net has achieved good performance with the small-scale datasets through skip connections to merge the features of the low-level layers and high-level layers and has been widely utilized in biomedical image segmentation as well as recent microstructure image segregation of the *** representative visual attention mechanism modules,named as squeeze-and-excitation networks,convolutional block attention module,and extended calibration algorithm,were intro-duced into the traditional U-Net architecture to further improve the prediction *** is found that compared with the original U-Net architecture,the evaluation index of the improved U-Net architecture has been significantly improved for the microstructure segmentation of the steels with the ferrite/martensite composite microstructure and pearlite/ferrite composite microstructure and the complex martensite/austenite island/bainite microstructure,which demonstrates the advantages of the utilization of the visual attention mechanism in the microstructure *** reasons for the accuracy improvement were discussed based on the feature maps analysis.

关键词： Microstructure recognition-Steel Machine learning Visual attention mechanism Visualization

来源：

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

Investigating the Absorption and Desorption Behavior of Methylene Chloride in the Poly(aryl ether ketone) Film with Different Crystallinities

引用

Chinese Journal of Polymer Science 2024年第2期42卷 239-246,I0009页

作者： Hong-Ru Yang Jin-dong zhang dong-Ting Gao Gang Liu Chun-Hai Chen Jia-Nan Yao Center for Advanced Low-Dimension Materials State Key Laboratory for Modification of Chemical Fibers and Polymer MaterialsCollege of Materials Science and EngineeringDonghua UniversityShanghai201620China

Poly(aryl ether keton e)(PAEK) films with different crystallinities were obtained by controlling the cooling rate,which were subjected to the absorption and desorption of methylene chloride(CH_(2)Cl_(2)).We employed attenuated total reflection Fourier transform infrared(ATR-FTIR)spectroscopy analyses to investigate the diffusion behavior of CH_(2)Cl_(2) in PAEK films with different *** to the Fickian diffusion model,the calculated diffu sion coefficients of CH_(2)Cl_(2) in PAEK films were observed to decrease with increasing *** effect of CH_(2)Cl_(2)absorption and desorption on the mechanical properties of PAEK films with different crystallinity was further analyzed using tensile *** tensile tests exhibited that CH_(2)Cl_(2) has two concurrent effects:plasticization and solvent-induced *** scanning calorimetry(DSC) and wide-angle X-ray diffraction(WXRD) techniques further confirmed solvent-induced crystallization *** results would be beneficial to understand the solvent resistance of PAEK materials and consequently provide the practical application conditions of PAEK with a theoretical basis.

关键词： Poly(aryl ether ketone) Diffusion behavior Infrared spectra Solvent-induced crystallization Mechanical properties

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Navigation for autonomous vehicles via fast-stable and smooth reinforcement learning

引用

Science China(Technological Sciences) 2024年第2期67卷 423-434页

作者： zhang RuiXian YANG JiaNan LIANG Ye LU ShengAo dong YiFei YANG BaoQing zhang LiXian School of Astronautics Harbin Institute of TechnologyHarbin 150001China

This paper investigates the navigation problem of autonomous vehicles based on reinforcement learning(RL)with both stability and smoothness *** introducing a data-based Lyapunov function,the stability criterion in mean cost is obtained,where the Lyapunov function has a property of fast ***,an off-policy RL algorithm is proposed to train safe policies,in which a more strict constraint is exerted in the framework of model-free RL to ensure the fast convergence of policy generation,in contrast with the existing RL merely with stability *** addition,by simultaneously introducing constraints on action increments and action distribution variations,the difference between the adjacent actions is effectively alleviated to ensure the smoothness of the obtained policy,instead of only seeking the similarity of the distributions of adjacent actions as commonly done in the past literature.A navigation task of a ground differentially driven mobile vehicle in simulations is adopted to demonstrate the superiority of the proposed algorithm on the fast stability and smoothness.

关键词： autonomous vehicles navigation reinforcement learning smoothness stability

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Enhancing Multi-agent Coordination via Dual-channel Consensus

引用

Machine Intelligence Research 2024年第2期21卷 349-368页

作者： Qingyang zhang Kaishen Wang Jingqing Ruan Yiming Yang Dengpeng xing Bo Xu Institute of Automation Chinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China

Successful coordination in multi-agent systems requires agents to achieve *** works propose methods through information sharing,such as explicit information sharing via communication protocols or exchanging information implicitly via behavior ***,these methods may fail in the absence of communication channels or due to biased *** this work,we propose to develop dual-channel consensus(DuCC)via contrastive representation learning for fully cooperative multi-agent systems,which does not need explicit communication and avoids biased *** comprises two types of consensus:temporally extended consensus within each agent(inner-agent consensus)and mutual consensus across agents(inter-agent consensus).To achieve DuCC,we design two objectives to learn representations of slow environmental features for inner-agent consensus and to realize cognitive consistency as inter-agent *** DuCC is highly general and can be flexibly combined with various MARL *** extensive experiments on StarCraft multi-agent challenge and Google research football demonstrate that our method efficiently reaches consensus and performs superiorly to state-of-the-art MARL algorithms.

关键词： Multi-agent reinforcement learning contrastive representation learning consensus multi-agent cooperation cognitive consistency

来源：

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

Chemical Scissors Tailored Nano‑Tellurium with High‑Entropy Morphology for Efficient Foam‑Hydrogel‑Based Solar Photothermal Evaporators

引用

Nano-Micro Letters 2024年第3期16卷 149-168页

作者： Chenyang xing Zihao Li Ziao Wang Shaohui zhang Zhongjian Xie Xi Zhu Zhengchun Peng State Key Laboratory of Radio FrequencyHeterogeneous Integration Shenzhen UniversityShenzhen 518060People’s Republic of China Center for Stretchable Electronics and NanoSensors College of Physics and Optoelectronic EngineeringShenzhen UniversityShenzhen 518060People’s Republic of China School of Science and Engineering The Chinese University of Hong KongShenzhenShenzhen 518172People’s Republic of China Institute of Pediatrics Shenzhen Children’s HospitalShenzhen 518038GuangdongPeople’s Republic of China International Collaborative Laboratory of 2D Materials for Optoelectronics Science and Technology of Ministry of Education Institute of Microscale OptoelectronicsShenzhen UniversityShenzhen 518060People’s Republic of China

The development of tellurium(Te)-based semiconductor nanomaterials for efficient light-to-heat conversion may offer an effective means of harvesting sunlight to address global energy ***,the nanosized Te(nano-Te)materials reported to date suffer from a series of drawbacks,including limited light absorption and a lack of surface ***,we report the preparation of nano-Te by electrochemical exfoliation using an electrolyzable room-temperature ionic ***,cations,and their corresponding electrolytic products acting as chemical scissors can precisely intercalate and functionalize bulk *** resulting nano-Te has high morphological entropy,rich surface functional groups,and broad light *** also constructed foam hydrogels based on poly(vinyl alcohol)/nano-Te,which achieved an evaporation rate and energy efficiency of 4.11 kg m^(−2)h^(−1)and 128%,respectively,under 1 sun ***,the evaporation rate was maintained in the range 2.5-3.0 kg m^(−2)h^(−1)outdoors under 0.5-1.0 sun,providing highly efficient evaporation under low light conditions.

关键词： Tellurium High entropy Electrochemical modification Solar absorption Evaporation rate

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Exceptional points enhance sensing in silicon micromechanical resonators

引用

Microsystems & Nanoengineering 2024年第1期10卷 17-25页

作者： Man-Na zhang Lei dong Li-Feng Wang Qing-An Huang Key Laboratory of MEMS of the Ministry of Education Southeast UniversityNanjing 210096China

Exceptional points(EPs)have recently emerged as a new method for engineering the response of open physical systems,that is,systems that interact with the *** systems at the EPs exhibit a strong response to a small ***,we show a method by which the sensitivity of silicon resonant sensors can be enhanced when operated at *** our experiments,we use a pair of mechanically coupled silicon micromechanical resonators constituting a parity-time(PT)-symmetric *** perturbations introduced on the mechanically coupled spring cause the frequency to split from the EPs into the PT-symmetric regime without broadening the two spectrum linewidths,and this frequency splitting scales with the square root of the perturbation *** overall signal-tonoise ratio is still greatly enhanced,although the measured noise spectral density of the EP sensing scheme has a slight increase comparable to the traditional *** results pave the way for resonant sensors with ultrahigh sensitivity.

关键词： resonant symmetric points

来源：

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

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：