检索结果-内蒙古大学图书馆

Carbon dioxide storage and cumulative oil production predictions in unconventional reservoirs applying optimized machine-learning models

引用

Petroleum science 2025年第1期22卷 296-323页

作者： Shadfar Davoodi Hung Vo Thanh David A.Wood Mohammad Mehrad Sergey V.Muravyov Valeriy S.Rukavishnikov School of Earth Sciences & Engineering Tomsk Polytechnic University Laboratory for Computational Mechanics Institute for Computational Science and Artificial Intelligence Van Lang University Applied Science Research Center Applied Science Private University DWA Energy Limited Division for Automation & Robotics Tomsk Polytechnic University

To achieve carbon dioxide（CO2） storage through enhanced oil recovery, accurate forecasting of CO2subsurface storage and cumulative oil production is essential. This study develops hybrid predictive models for the determination of CO2storage mass and cumulative oil production in unconventional reservoirs. It does so with two multi-layer perceptron neural networks（MLPNN） and a least-squares support vector machine（LSSVM）, hybridized with grey wolf optimization（GWO） and/or particle swarm optimization（PSO）. Large, simulated datasets were divided into training（70%） and testing（30%）groups, with normalization applied to both groups. Mahalanobis distance identifies/eliminates outliers in the training subset only. A non-dominated sorting genetic algorithm（NSGA-II） combined with LSSVM selected seven influential features from the nine available input parameters: reservoir depth, porosity,permeability, thickness, bottom-hole pressure, area, CO2injection rate, residual oil saturation to gas flooding, and residual oil saturation to water flooding. Predictive models were developed and tested,with performance evaluated with an overfitting index（OFI）, scoring analysis, and partial dependence plots（PDP）, during training and independent testing to enhance model focus and effectiveness. The LSSVM-GWO model generated the lowest root mean square error（RMSE） values（0.4052 MMT for CO2storage and 9.7392 MMbbl for cumulative oil production） in the training group. That trained model also exhibited excellent generalization and minimal overfitting when applied to the testing group（RMSE of0.6224 MMT for CO2storage and 12.5143 MMbbl for cumulative oil production）. PDP analysis revealed that the input features “area” and “porosity” had the most influence on the LSSVM-GWO model's prediction performance. This paper presents a new hybrid modeling approach that achieves accurate forecasting of CO2subsurface storage and cumulative oil production. It also establishes a new standard for such forecasting,

关键词： Hybrid machine learning Least-squares support vector machine Grey wolf optimization Feature selection Carbon dioxide storage Enhanced oil recovery

来源：评论

学校读者我要写书评

暂无评论

Energy-Free Sensing and Context Recognition Using Photovoltaic Cells

引用

IEEE Sensors Journal 2025年第9期25卷 15598-15611页

作者： Shintani, Kaede Rizk, Hamada Yamaguchi, Hirozumi Osaka University Graduate School of Information Science and Technology Department of Information Networking Suita565-0871 Japan Tanta University Tanta31733 Egypt RIKEN Center for Computational Science Kobe650-0047 Japan RIKEN Center for Computational Science Department of Computer and Control Engineering Kobe650-0047 Japan

The field of energy-free sensing and context recognition has recently gained significant attention as it allows operating systems without external power sources. Photovoltaic cells can convert light energy into electrical energy to power sensing devices, but their power may not be sufficient to ensure energy-free sensing due to the varying power needs of sensors and high computational demands. In this article, we propose the use of photovoltaic cells as a standalone sensor for the recognition of different contexts, including user identification, step counting, and location tracking. The system utilizes the photocurrent readings generated by the photovoltaic cells to capture the unique mobility patterns of different users. By analyzing these patterns, the system can accurately identify the user, count the number of steps taken, and track the user’s location. We propose a computationally efficient dynamic time warping (DTW) to match the variable length sequences of photocurrent readings to a database of known patterns and identify the closest subject and location matches. The system was rigorously evaluated in a realistic environment, and the results indicate that it can accurately estimate step count, identify subjects, and localize them with an accuracy of 88%, 90%, and 43 cm, respectively. This is achieved while the proposed system is nonintrusive and can operate without external power sources, making it a promising technology for energy-free sensing and context recognition. © 2001-2012 IEEE.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

Application of large language models to quantum state simulation

引用

science China(Physics,Mechanics & Astronomy) 2025年第4期68卷 45-61页

作者： Shuangxiang Zhou Ronghang Chen Zheng An Chao Zhang Shi-Yao Hou College of Physics and Electronic Engineering Center for Computational SciencesSichuan Normal UniversityChengdu 610068China Department of Physics The Hong Kong University of Science and TechnologyHong Kong 999077China

Quantum computers leverage the unique advantages of quantum mechanics to achieve acceleration over classical computers for certain ***,various quantum simulators provide powerful tools for researchers,but simulating quantum evolution with these simulators often incurs high time ***,resource consumption grows exponentially as the number of quantum bits *** address this issue,our research aims to utilize Large Language Models(LLMs)to simulate quantum *** paper details the process of constructing 1-qubit and 2-qubit quantum simulator models,extending to multiple qubits,and ultimately implementing a 3-qubit *** study demonstrates that LLMs can effectively learn and predict the evolution patterns among quantum bits,with minimal error compared to the theoretical output *** when dealing with quantum circuits comprising an exponential number of quantum gates,LLMs remain computationally ***,our results highlight the potential of LLMs to predict the outputs of complex quantum dynamics,achieving speeds far surpassing those required to run the same process on a quantum *** finding provides new insights and tools for applying machine learning methods in the field of quantum computing.

关键词： large language models quantum simulation quantum computing

来源：评论

学校读者我要写书评

暂无评论

Fractal autoencoder with redundancy regularization for unsupervised feature selection

引用

science China(Information sciences) 2025年第2期68卷 89-102页

作者： Meiting SUN Fangyu LI Honggui HAN School of Information Science and Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Digital Community Ministry of Education Beijing Institute of Artificial Intelligence

Feature selection is a crucial step in data preprocessing because feature selection reduces the dimensionality of data by eliminating irrelevant and redundant features. Since manual labeling is expensive, unsupervised feature selection has received increasing attention in recent years. However, existing unsupervised feature selection methods tend to prioritize selecting highly correlated features over exploring feature diversity. Thus, a regularized fractal autoencoder(RFAE) method is proposed to select informative features in an unsupervised way. Specifically, the fractal autoencoder network extends autoencoders to construct a correspondence neural network and a selection neural network. The correspondence neural network exploits interfeature correlations and the selection neural network selects the informative features. A redundancy regularization strategy consists of a redundancy elimination regularization term based on the dependency between features and a sparse regularization term based on the group lasso. The redundancy regularization strategy eliminates feature subset redundancy and enhances network generalization ability. Extensive experimental results on six publicly available datasets show that the proposed RFAE outperforms the compared methods regarding clustering accuracy and classification accuracy. Moreover, the proposed RFAE achieves acceptable computation efficiency.

关键词： unsupervised feature selection fractal autoencoder correspondence neural network selection neural network redundancy regularization strategy

来源：评论

学校读者我要写书评

暂无评论

Alkali metal pyridinolate/piperidinolate pairs: A new type of materials for efficient reversible hydrogen storage

引用

Journal of Energy Chemistry 2025年第4期103卷 353-360页

作者： Alexis Munyentwali Yang Yu Xingchi Zhou Wei Zhou Qijun Pei Khai C.Tan Anan Wu Hui Wu Teng He Ping Chen Dalian Institute of Chemical Physics Chinese Academy of Sciences Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry College of Chemistry and Chemical Engineering Xiamen University NIST Center for Neutron Research National Institute of Standards and Technology

Chemical hydrogen storage in organic materials is a promising method thanks to its high storage density,reversibility,and ***,the dehydrogenation process of organic materials requires high temperatures due to their unfavorable thermodynamic *** study proposes a strategy to design a new type of hydrogen storage materials,i.e.,alkali metal pyridinolate/piperidinolate pairs,by combining the effects of a heteroatom and an alkali metal in one molecule to achieve suitable dehydrogenation thermodynamics along with high hydrogen storage *** air-stable compounds can be synthesized using low-cost reactants and water as a green *** predictions indicate that enthalpy changes of dehydrogenation（ΔHd） can be significantly reduced to the optimal range for efficient hydrogen release,exemplified by lithium 2-piperidinolate with a 5.6 wt% hydrogen capacity and a suitable ΔHdof 32.2 kJ/*** results obtained using sodium systems validate the computational predictions,demonstrating reversible hydrogen storage even below 100℃.The superior hydrogen desorption performance of alkali metal piperidinolates could be attributed to their suitable ΔHdinduced by the combined effect of ring nitrogen and metal substitution on their *** study not only reports new low-cost hydrogen storage materials but also provides a rational design strategy for developing metalorganic compounds possessing high hydrogen capacities and suitable thermodynamics for efficient hydrogen storage.

关键词： Alkali metal pyridinolates Alkali metal substitution Hydrogen storage Metalorganic compounds Ring nitrogen

来源：评论

学校读者我要写书评

暂无评论

Atomic origin of minor alloying element effect on glass forming ability of metallic glass

引用

Chinese Physics B 2025年第3期34卷 483-489页

作者： Shan Zhang Qingan Li Yong Yang Pengfei Guan Beijing Computational Science Research Center Beijing 100193China Department of Mechanical Engineering College of EngineeringCity University of Hong KongTat Chee AvenueKowloon TongKowloonHong KongChina Advanced Interdisciplinary Sciences Research(AiR)Center Ningbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 315201China

The glass-forming ability(GFA)of metallic glasses is a key scientific challenge in their development and application,with compositional dependence playing a crucial *** studies have demonstrated that the addition of specific minor elements can greatly enhance the GFA of parent alloys,yet the underlying mechanism remains *** this study,we use the ZrCuAl system as a model to explore how the addition of minor Al influences the crystallization rate by modulating the properties of the crystal-liquid interface,thereby affecting the *** results reveal that the minor addition of Al significantly reduces the crystal growth rate,a phenomenon not governed by particle density fluctuations at the *** impact of minor element additions extends beyond a modest increase in crystal-unfavorable motifs in the bulk supercooled *** importantly,it leads to a significant enrichment of these motifs at the crystal-supercooled liquid interface,forming a dense topological network of crystal-unfavorable structures that effectively prevent the growth of the crystalline interface and enhance *** results provide valuable insights for the design and development of high-performance metallic glasses.

关键词： metallic glass glass forming ability interface structure molecular dynamics(MD)

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Predicting Knowledge Graph Updates from Edit Histories 26th

Predicting Knowledge Graph Updates from Edit Histories

引用

26th International Conference on Information Integration and Web Intelligence, iiWAS 2024

作者： Okura, Maiki Amagasa, Toshiyuki Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Japan Center for Computational Science University of Tsukuba Ibaraki Tsukuba Japan

ISBN: (纸本)9783031780899

Knowledge graphs (KGs) are inherently incomplete and require continuous maintenance to keep up with the latest status of the target domain. Various studies have been conducted to automate this maintenance, but it still relies heavily on human labor. To alleviate such a burden, predicting updates in KGs is useful for maintaining KGs. In this study, we focus on predicting which entities to be updated in KGs containing many entities. Our basic idea is to exploit the KG’s structural information and the edit history, making it possible to predict entities likely to be updated in the next time interval. We have constructed a dataset including edit history based on Wikidata, a general-purpose knowledge graph, and developed a method to predict entities that will be updated based on link relations and edit history, and confirmed their usefulness through experiments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Edit history Knowledge graph Update prediction

来源：评论

学校读者我要写书评

暂无评论

Fe single atom trigger asymmetric In-In polarized site pairs boosting near-infrared N2 photoreduction

引用

Materials Today 2025年 86卷 96-103页

作者： Liang, Huimin Ye, Caichao Wu, Yao Li, Yezi Long, Ran Xiong, Jun Jiang, Wei Di, Jun School of Chemistry and Chemical Engineering National Special Superfine Powder Engineering Research Center Nanjing University of Science and Technology Nanjing210094 China Academy for Advanced Interdisciplinary Studies & Department of Materials Science and Engineering Guangdong Provincial Key Laboratory of Computational Science and Material Design Southern University of Science and Technology Shenzhen518055 China School of Materials Science & Engineering Nanyang Technological University Singapore639798 Singapore National Synchrotron Radiation Laboratory CAS Center for Excellence in Nanoscience School of Chemistry and Materials Science University of Science and Technology of China Hefei230026 China Institute for Energy Research Jiangsu University Zhenjiang212013 China

Building differentiated charge distributed polarized atomic pairs may be an alternative for N2 activation. In this work, CuInS2 atomic layers with asymmetric In-In polarized site pairs are prepared by doping Fe single atoms, as proved by X-ray absorption fine structure spectroscopy, quasi in situ X-ray photoelectron spectra and calculated atomic charge distribution. The engineered Fe single atoms tuned the surface atomic charge distribution, building local polarization center to boost directional surface charge separation. The formed In-In polarized site pairs with asymmetric charge distribution creates distinct interaction with two N atoms in N2 molecule, contributing to the enhanced activation of N2. The alternating pathway is regarded as hydrogenation pathway over Fe-CuInS2 with *NNH formation as rate-determining step. The charge-redistributed surface atomic structure after engineered Fe single atoms strengthens intermediate interaction and lower the rate-determining step energy barrier. Benefiting from these features, Fe-CuInS2 exhibits excellent photocatalytic activity under near-infrared (NIR) irradiation with an ammonia synthesis rate of 94.1 μmol g−1 h−1. In comparison, the N2-NH3 conversion rate of Fe-CuInS2 under ultraviolet–visible (UV–Vis) irradiation could reach 137.4 μmol g−1 h−1, which is about 6.8 times higher than that of CuInS2. The apparent quantum efficiencies of Fe-CuInS2-2 at 380, 400, 450, 500, 550, 650, 700, 800, 850 and 1064 nm were 3.0 %, 3.3 %, 2.7 %, 2.1 %, 2.0 %, 1.5 %, 1.3 %, 0.4 %, 0.7 % and 0.6 %, respectively. © 2025 Elsevier Ltd

关键词： X ray absorption fine structure spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Improved Engine Data Acquisition System and Interface to Enable Experimentation With Emerging Alternative Fuels in a Spark-Ignited Cooperative Fuel Research Engine

引用

Journal of engineering for Gas Turbines and Power 2025年第7期147卷 071020页

作者： Loprete, Jason Dimosthenous, Christos Assanis, Dimitris Department of Mechanical Engineering Advanced Energy Research and Technology Center Stony Brook University Stony BrookNY11794 United States Institute for Advanced Computational Science Stony Brook University Stony BrookNY United States

In the face of new engine research challenges, legacy hardware and once state-of-the-art assumptions may become less relevant, especially those made due to the computational limitations of the hardware at the time of initial development. Such legacy elements can potentially limit the effectiveness of accurately describing key parameters or metrics during experimentation or postprocessing. As the behavior of novel fuels is also not always fully understood, this highlights the need for tools to guide the experimental design to avoid unexpected and potentially dangerous outcomes. This paper details the conversion of an existing data acquisition system for a spark-ignited single-cylinder cooperative fuel research (CFR) engine to handle a variety of different emerging alternative fuels. Modifications to the in-house legacy LabVIEW program and data acquisition system are detailed, with emphasis on providing additional tools to aid in the experimentation expediency and safety. The existing CFR testing facility is converted from a single liquid or single gaseous fuel capable system to a multifuel compatible system, complete with on-the-fly calculations of mass, energy, and volume fractions of existing fuel blends, increased low-speed sampling rates, and a calculating tool to command fuel flow set-points for a given blend fraction, equivalence ratio and airflow set-point. Additional factors, such as sensor selection and communication, are discussed with an emphasis on reducing experimental uncertainty. Overall, this work provides insights into possible adjustments and considerations when upgrading existing experimental setups to accommodate emerging alternative fuel use. Copyright © 2025 by ASME.

关键词： Alternative fuels

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：