检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,126 篇 会议
37 篇 期刊文献
7 册 图书

馆藏范围

1,170 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

643 篇 工学
- 305 篇 计算机科学与技术...
- 196 篇 电气工程
- 159 篇 控制科学与工程
- 146 篇 软件工程
- 99 篇 机械工程
- 73 篇 电子科学与技术（可...
- 71 篇 信息与通信工程
- 67 篇 动力工程及工程热...
- 57 篇 石油与天然气工程
- 47 篇 力学（可授工学、理...
- 42 篇 材料科学与工程（可...
- 39 篇 土木工程
- 33 篇 化学工程与技术
- 23 篇 交通运输工程
- 23 篇 生物工程
- 22 篇 航空宇航科学与技...
- 21 篇 建筑学
- 20 篇 仪器科学与技术
- 16 篇 环境科学与工程（可...
274 篇 理学
- 171 篇 数学
- 91 篇 物理学
- 38 篇 系统科学
- 34 篇 统计学（可授理学、...
- 24 篇 生物学
- 20 篇 化学
- 19 篇 地球物理学
- 17 篇 地质学
108 篇 管理学
- 95 篇 管理科学与工程(可...
- 41 篇 工商管理
16 篇 经济学
- 14 篇 应用经济学
13 篇 法学
12 篇 医学
6 篇 教育学
4 篇 农学
3 篇 军事学
2 篇 文学
1 篇 艺术学

主题

197 篇 optimization
175 篇 computational mo...
67 篇 simulation
48 篇 data models
46 篇 analytical model...
45 篇 mathematical mod...
41 篇 design optimizat...
39 篇 predictive model...
33 篇 load modeling
29 篇 integrated circu...
28 篇 surrogate modeli...
27 篇 simulation-drive...
25 篇 antenna design
24 篇 adaptation model...
23 篇 circuit simulati...
23 篇 real-time system...
21 篇 numerical models
20 篇 modeling
20 篇 machine learning
20 篇 uncertainty

机构

15 篇 engineering opti...
15 篇 faculty of elect...
13 篇 reykjavik univ e...
13 篇 gdansk univ tech...
12 篇 gdansk univ tech...
10 篇 reykjavik univ e...
10 篇 promodel corpora...
7 篇 southern univ sc...
7 篇 reykjavik univ s...
7 篇 engineering opti...
6 篇 iowa state univ ...
6 篇 school of scienc...
6 篇 engineering opti...
6 篇 engineering opti...
5 篇 reykjavik univ s...
5 篇 schlumberger uni...
5 篇 reykjavik univ s...
4 篇 shanghai univers...
4 篇 engineering opti...
4 篇 gdansk univ tech...

作者

72 篇 koziel slawomir
35 篇 slawomir koziel
34 篇 bekasiewicz adri...
17 篇 leifsson leifur
17 篇 adrian bekasiewi...
13 篇 pietrenko-dabrow...
13 篇 ogurtsov stanisl...
10 篇 cheng qingsha s.
9 篇 stanislav ogurts...
9 篇 s. koziel
8 篇 kurgan piotr
8 篇 koziel s.
6 篇 s. ogurtsov
5 篇 c.r. harrell
5 篇 anna pietrenko-d...
5 篇 harrell charles ...
4 篇 ogurtsov s.
4 篇 oskar von stryk
4 篇 wei wang
3 篇 bekasiewicz a.

语言

1,108 篇 英文
48 篇 其他
17 篇 中文
1 篇 德文

检索条件"任意字段=Conference on Simulation-Driven Modeling and Optimization"

共 1170 条记录，以下是311-320 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

AutoOPT: Data Generation and optimization for Digital Twin Network (DTN)

AutoOPT: Data Generation and Optimization for Digital Twin N...

引用

IEEE International conference on Cloud Computing, CLOUD

作者： Mei Li Cheng Zhou Lu Lu Yan Zhang Tao Sun China Mobile Research Institute Beijing China Department of Informatics University of Oslo Oslo Norway

Traditional network management solutions can not easily meet the requirements of new applications (such as AR/VR, cloud gaming, and vehicular networks) at a reasonable cost. Digital Twin Network (DTN) builds real-time mirrors of physical networks, which can enhance the simulation, optimization, verification, and control capabilities that physical networks lack. AI models have been used to model complex network environments, which helps build real-time, lightweight, and high-precision DTN. This paper proposes a data generation and optimization method for data-driven DTN AI modeling through Data-Centric AI called AutoOPT. First, AutoOPT generates data in small networks based on scale-independent indicators, which helps the model generalize to large networks. Then, AutoOPT automatically filters out high-quality data through seed sample selection and incremental optimization, which helps the model be effectively trained to enhance accuracy and generalization. We apply AutoOPT to the DTN performance modeling scenario and test on GNNet Challenge datasets. The experimental results show that AutoOPT is more cost-efficient than the winning solutions of the challenge but can obtain similar results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Analysis of Power System Performance Under High PV and EV Penetration

Probabilistic Analysis of Power System Performance Under Hig...

引用

IEEE Green Technologies conference (IEEE-Green)

作者： Abdulrahman Almazroui Salman Mohagheghi Electrical Engineering Department Colorado School of Mines Golden CO USA

ISBN: (数字)9798331520182

ISBN: (纸本)9798331520199

This paper investigates the impact of high penetration levels of photovoltaic (PV) generation and electric vehicle charging stations (EVCS) on the operational efficiency of modern distribution grids. A probabilistic modeling framework is developed to address the uncertainties associated with PV generation, driven by weather variability, and EV charging demands, influenced by stochastic user behaviors. Using a modified version of the IEEE 123-bus system, various scenarios with different levels of PV and EVCS penetration are analyzed to evaluate their effects on voltage, power losses, and system reliability. Monte Carlo simulation is used to generate samples, while each sample realization is solved using an unbalanced voltage, var, and watt optimization (VVWO) model. Results demonstrate that coordination between PV and EVCS operations can mitigate the challenges posed by fluctuating renewable generation and increased EV demand. High PV penetration is shown to reduce power losses, support voltage stability, and minimize EVCS demand curtailment. The findings emphasize the importance of coordinated PV and EVCS management and offer insights for grid planners to enhance the hosting capacity of distribution networks.

关键词： Photovoltaic systems Reactive power Monte Carlo methods Power system stability Probabilistic logic Electric vehicle charging Power grids Reliability Voltage control optimization

来源：评论

学校读者我要写书评

暂无评论

Improved Initialization of Non-Linear Solvers in Numerical simulation of Flow in Porous Media with a Deep Learning Approach 83

Improved Initialization of Non-Linear Solvers in Numerical S...

引用

2022 SPE EuropEC - Europe Energy conference featured at the 83rd EAGE Annual conference and Exhibition, EURO 2022

作者： Abbasi, Jassem Andersen, Pål Østebø Department of Energy Resources University of Stavanger 4036 Norway

ISBN: (纸本)9781613998656

Partial Differential Equations (PDEs) have a wide list of applications in modeling complex processes including flow in porous materials. Solution of these equations that are mostly highly non-linear is generally possible using numerical algorithms that are carried out by iterative approaches like Newton's method, where the calculations to find the solution at a new time step are started using an initial guess of the unknown variables. The computational efficiency of the calculations is highly dependent on the closeness of these initial guesses to the exact values. As a routine, solvers pick the solutions at the previous timestep as the kickoff point for Newton's method. Improvement of this starting point at each time step can reduce the timeto-solution of the solver. This study focuses on using a Deep Learning (DL) algorithm for optimization of a PDE solver and improvement of the computational efficiency of simulation of flow in porous media by providing more efficient initial guesses for the unknown variables. In this work, a 1D gravity-capillary driven two-phase flow problem with a fully implicit Newton's solver was hired as the base numerical model. A fully connected neural network (NN) was initialized and added to the numerical solver, at the point before starting each timestep. The data from the most important features and the target properties were collected from a series of simulation cases and the DL model was trained with the Adam optimizer. After training and testing, the default initialization approach (i.e., solution at previous timestep) was replaced by the hybrid DL-based approach that provides an initial guess for cells with high saturation gradients. Saturation gradients at the previous timestep, location, and mobility ratio of both phases are selected as the input features. The results showed that applying the developed algorithm to numerical simulation problems reduced the run-time in the range of 15-35% in different cases, while the required proce

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Fast and Reliable Antenna optimization by Design Specification Management and Multi-Fidelity Models

Fast and Reliable Antenna Optimization by Design Specificati...

引用

European conference on Antennas and Propagation, EuCAP

作者： Anna Pietrenko-Dabrowska Slawomir Koziel Faculty of Electronics Telecommunications and Informatics Gdansk University of Technology Gdansk Poland Engineering Optimization & Modeling Center Reykjavik University Reykjavik Iceland

Rigorous numerical optimization has become vital in ensuring the best possible performance of contemporary antenna structures. Still, in many practical cases, computational efficiency and reliability of simulation-driven optimization procedures remain far from satisfactory. The former issue is associated with the computational expenses of repetitive electromagnetic (EM) simulations required by numerical optimization routines, whereas the latter arises partly from the shortage of a sufficient-quality initial designs indispensable for local search procedures. Recently, design specification adjustment procedure has been reported that makes local optimization less vulnerable to inferior-quality starting points. This is achieved by gradually adjusting (shifting) the specs (e.g., target operating frequencies) closer to that of the current design, which makes them reachable by a local optimizer. Seeking cost savings, here, we propose an algorithmic framework that introduces multi-fidelity EM models into the design specification adjustment procedure. Throughout the algorithm run, the resolution of the simulation model is adjusted iteration-wise based on the following indicators: (i) the discrepancy between the assumed and actual operating parameters, and (ii) the algorithm convergence status. As verified using two examples of microstrip antennas, optimized under various demanding scenarios, the obtained savings reach up to sixty percent with regard to a single-fidelity regime, while maintaining comparable reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

optimization of Transportation Traffic using Agile Approach

Optimization of Transportation Traffic using Agile Approach

引用

Electronics and Renewable Systems (ICEARS), International conference on

作者： Ajay K Abhishek Sundaramoorthi S. Prince Mary Dept. of CSE Sathyabama Institute of Science and Technology Chennai Tamilnadu

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Traffic congestion and its related delays present significant challenges to urban infrastructure and societal efficiency. This project demonstrates an intelligent traffic management system that combines real-time vehicle detection, adaptive signal control, and predictive traffic modeling to solve the problem of urban congestion. The implementation of YOLOv8 for the identification and counting of vehicles with accurate precision in low-quality surveillance footage will feed into the production of the real-time data important for the efficient management of traffic flow. Such information feeds into a Signal Switching Algorithm, which continually adjusts signal timings according to the instantaneous level of traffic to optimize intersections for smoother flow. Validation of its effectiveness is done with a computer simulation of a 4-way intersection via Pygame where different scenarios affecting the reduction of congestion are tested upon the algorithm. With all this being said, another model makes use of historical data about traffic to foretell such patterns of flow, allowing pre-optimized signal timings to filter into traffic management to optimize flow even more. Such a system would provide an overall city traffic management approach that operates in real time and has data-driven insight into predicting more sustainable city transportation based on predictive analysis.

关键词： Adaptive systems Vehicle detection Heuristic algorithms Transportation Switches Throughput Real-time systems Feeds optimization Video recording

来源：评论

学校读者我要写书评

暂无评论

Improving Photonic Crystal AND Gate Performance Via optimization Using Machine Learning

Improving Photonic Crystal AND Gate Performance Via Optimiza...

引用

International conference on System modeling & Advancement in Research Trends (SMART)

作者： Krishan Kumar Narrain Prithvi Dharuman Smita Raghavendra Bhat Hrishikesh Rajesh Mane Arpit Jain Akash Balaji Mali Department of ECE Bhagat Phool Singh Mahila Vishwavidyalaya Sonipat Haryana India National Institute of Technology Trichy Tamil Naidu India Independent Researcher KA India Independent Researcher Pune India Department of Computer Science & Engineering Koneru Lakshmaiah Education Foundation Guntur A.P. India MIDC Pune Maharashtra India

ISBN: (数字)9798350380583

ISBN: (纸本)9798350380590

A new window of space has unlocked the development of depressed-capacity, speedy ocular structures by way of current breakthroughs in a photonic crystal. Photonic crystals will authorize AND gates, which are the fundamental elements in incorporated computer circuits for mathematical plans. This research provides an order for reconstructing the effectiveness of AND gates that is to say established machine intelligence. To train on a dataset, use the Extra Trees Regressor model. Using the judgments from the imitation to forecast the power production for miscellaneous scenes for recommendation and limits. The verdicts signify that the model can create precise forecasts about the product capacity utilizing a Root Mean Square Error (RMSE) A RMSE of 0.18. The model is therefore used to find the highest in-rank principles for the mesh constant and pole range. The ideal values for R and x are driven by expected 0.05 um and 0.12 um, individually. Using the Extra Trees Regressor's prophecies for dependent computations, the research delves further into the addition process for optical port outputs. The effect of determinants like bar sweep and mesh fixed on fence functioning is intentional in detail, with accompanying importance on how these limits influence the achievement of advantageous yield states. The results of the simulation illustrate well that the amended limits can imitate the AND door behaviour in the photonic clear model

关键词： Computational modeling Photonic crystals Machine learning Logic gates Integrated circuit modeling Regression tree analysis optimization Machine intelligence Photonics Bars

来源：评论

学校读者我要写书评

暂无评论

Recent Advances in ANN-Based Methods for Yield-driven Design of EM Structures

Recent Advances in ANN-Based Methods for Yield-Driven Design...

引用

International conference on Numerical Electromagnetic modeling and optimization for RF, Microwave, and Terahertz Applications (NEMO)

作者： Jianan Zhang Q. J. Zhang State Key Laboratory of Millimeter Waves Southeast University Nanjing China Department of Electronics Carleton University Ottawa Canada

ISBN: (纸本)9781665486347

The design of microwave passive components should take into account the tolerances in the manufacturing process. This makes yield estimation and yield-driven design optimization essential steps in electromagnetic (EM) simulation-based microwave component design. Brute-force methods based on Monte Carlo (MC) analyses are not computationally feasible in practice due to the demand for a large number of EM simulations. Artificial neural networks (ANNs) hold a great potential to address this challenge. This paper reviews recent advances in ANN-based methods for the yield-driven design of EM structures, including a neuro-TF surrogate-assisted yield estimation method and the corresponding yield optimization algorithm. These advanced approaches are demonstrated by two microwave examples.

关键词： Analytical models Electric potential Monte Carlo methods Manufacturing processes Artificial neural networks Microwave theory and techniques Numerical models

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Reasonable Storage Capacity of Water - driven Depleted Gas Reservoirs 11th

Evaluation of Reasonable Storage Capacity of Water - Driven ...

引用

11th International Field Exploration and Development conference, IFEDC 2021

作者： Liu, Tuan-hui Guo, Fa-jun Chen, Xi Xi, Zeng-qiang Zhao, Ming-qian Bi, Yang-yang Wang, Ya-ni Xian, Meng-yuan Zhang, Bo Exploration and Development Research Institute of PetroChina HuaBei Oilfield Company Hebei Renqiu China CBM and Gas Storage Division of Petrochina Huabei Oilfield Company Hebei Renqiu China

ISBN: (纸本)9789811921483

With the rapid development of domestic natural gas business, demand of natural gas peak shaving, gas storage construction is imminent, but the complicated geological conditions in China, the building is difficult, currently under construction in the vast majority of the gas storage water drive gas reservoir exploitation to the middle and later even dried up, edge-bottom water into water reservoir, greatly reduce the moving inventory, reduce running efficiency. The scientific and reasonable prediction of gas storage capacity parameters is of great importance to the subsequent construction and program optimization and adjustment of gas storage. The gas-water movement of the water-driven depleted gas reservoir is complicated, and the prediction of reservoir capacity is difficult and accurate. In view of the abundant development dynamic data and high cognition degree of depleted gas reservoir, a new method combining numerical simulation and physical simulation experiment is proposed to predict the reasonable storage capacity of depleted gas reservoir. Through geological modeling, the numerical model was fitted and modified to obtain the original effective pore space volume. By making the physical model reflecting the real reservoir physical property and carrying out the simulation experiment reflecting the high-speed injection and production of gas reservoir, the utilization rate of gas-bearing pore space in different zones of the reservoir was obtained. Based on the theory of reservoir capacity calculation, the reasonable reservoir capacity of depleted gas reservoir is predicted. This method is used to predict the reasonable storage capacity of a gas reservoir in North China, and the research results show that the reasonable storage capacity is 3.32 billion cubic meters, compared with the low speed development of gas reservoir, 26% of the inventory cannot be used. This study makes the prediction of reservoir capacity more reasonable and has important reference value an

关键词： Natural gas

来源：评论

学校读者我要写书评

暂无评论

simulation-Based Analyses and Improvements of the Smart Line Management System in Canned Beverage Industry: A Case Study in Europe

Simulation-Based Analyses and Improvements of the Smart Line...

引用

simulation Winter conference

作者： Ahmad Attar Yuqing Jin Martino Luis Shuya Zhong Voicu Ion Sucala Department of Engineering Faculty of Environment Science and Economy Exeter Digital Enterprise Systems Laboratory University of Exeter Exeter Devon UK

Canned water is one of the thriving markets in the food and beverage industry. Given the tight competition in this market, realistic analysis in such production lines has become even more attractive for all participating parties. In this paper, we apply a KPI-driven simulation-based approach to a smart production plant of a key player in the European beverage market. The project covers realistic discrete-event modeling and analysis of the system together with the suggested scenario-based optimization for performance improvement. Here, the smart line management system is modeled and re-coded while considering machine characteristics, failures, and their overall influence on the production process. Our proposed optimized scenario demonstrates noticeably better results in all performance indicators when compared to the existing state of the system. The total increment of the production speed reaches up to 45 percent, resource utilization is evenly optimal, and the overall work-in-progress inventory is reduced significantly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Service Routing optimization Algorithm for Power Communication Optical Transport Network Based on Knowledge Graph and Reinforcement Learning

A Service Routing Optimization Algorithm for Power Communica...

引用

International conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Zhang, Geng Ding, Huixia Wang, Yanan Wang, Lei Han, Xiao China Electric Power Research Institute Beijing China State Grid Tianjin Electric Power Company Tianjin China

ISBN: (纸本)9789811694912

Aimed at the single method of power communication OTN transmission network service routing planning, and lack of comprehensive consideration of risk balance, load balancing, and grid service characteristics. this paper proposes a power communication OTN transmission network service routing optimization algorithm based on reinforcement learning and fusion of multiple constraints. In this paper, the knowledge graph technology is used to obtain data sources in each business system, and at the same time, structured data is used to provide knowledge and computable services for the business system. Research and analyze the current transmission status and service characteristics of the power communication network, as well as the requirements for the effectiveness and reliability of transmission requirements. Aiming at the reasons that affect the effectiveness and reliability of the OTN transmission network, a mathematical assessment model of risk balance based on the importance of the business is proposed. At the same time, in order to avoid the large difference in the capacity of each link of the power communication network leading to deviations in the risk balance evaluation, the information entropy of the communication network is introduced as a joint evaluation index. Finally, the feasibility of the algorithm is simulated. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共117页 << < 28 29 30 31 32 33 34 35 36 37 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：