检索结果-内蒙古大学图书馆

5th international conference on Signal Processing and Computer Science, SPCS 2024

作者： Li, Xianyi School of Control Science and Engineering Shandong University Shandong Jinan250002 China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

In this paper, a new network called CSGNet is introduced for automatic modulation recognition, designed to improve recognition accuracy in complex electromagnetic environments. This innovative network leverages the strengths of both Convolutional Neural Networks (CNN) and Gate Recurrent Units (GRU) while mitigating their inherent weaknesses. Additionally, it incorporates a Self-Attention mechanism to further enhance its perceptual abilities. The primary advantage of this method is its superior recognition accuracy under low SNR conditions compared to traditional methods. The process starts by extracting basic I/Q data from the RadioML 2018.01a dataset as input. Subsequently, the CSGNet model performs an end-to-end modulation recognition task. The results demonstrate that this method excels at multiple SNR levels, highlighting the significant potential of deep learning in solving automatic modulation recognition challenges. This study underscores the effectiveness of integrating CNN, GRU, and Self-Attention mechanisms in enhancing the robustness and accuracy of modulation recognition systems. Furthermore, it demonstrates how deep learning techniques can be effectively applied to complex signal processing tasks. The findings suggest that CSGNet could be a valuable tool for improving communication systems, especially in challenging environments with low SNR. © 2025 SPIE.

关键词： Modulation Signal to noise ratio Feature extraction Deep learning Matrices Data modeling Machine learning Data processing Neural networks Quadrature amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

Research on the Optimal control Strategy of Smart Buildings Considering Demand Response

Research on the Optimal Control Strategy of Smart Buildings ...

引用

international conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Chen, Jingwen Qian, Cheng Chen, Songsong Gong, Feixiang Liu, Yaoxian College of Electrical and Control Engineering Shaanxi University of Science and Technology Xi’an710021 China Haidian District Beijing100192 China

ISBN: (纸本)9789819618637

At present, there are many problems in the research on building system regulation and control, such as conflicting scheduling methods and underutilization of demand-side response resources, which will hinder the stable operation of power grids and the development of high penetration rate of clean energy. This paper proposes a two-layer optimal control strategy for intelligent buildings considering demand-side response. Firstly, the mathematical modeling of the intelligent building energy system is carried out, and then different demand response scenarios and power balance constraints are set. A two-layer optimal control model based on Lasso-GRNN neural network was established for day-ahead optimal control and intraday dynamic control. Finally, the effectiveness of the proposed strategy is verified by simulation analysis. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： demand-side response smart buildings Two-layer optimization control

来源：评论

学校读者我要写书评

暂无评论

Limit Behavior of a Semi-Markov Process Depending on a Small Parameter for Telecommunication systems

Limit Behavior of a Semi-Markov Process Depending on a Small...

引用

international conference on Applied Innovations in IT, ICAIIT 2024

作者： Degtyar, Sergii Kopiika, Oleh Shusharin, Yurii Kyiv National Economic University Named After Vadym Hetman Kyiv Ukraine Institute of Applied Control Systems National Academy of Sciences of Ukraine Kyiv Ukraine

ISBN: (纸本)9783031892950

The limit behavior of a semi-Markov process, depending on a small parameter, is important for the analysis and optimization of telecommunication systems. Semi-Markov processes are an extension of Markov processes that allow modeling systems with preservation of some previous states. Such processes are important, for example, for modeling data transmission over wireless channels or communication networks. The limit behavior of a semi-Markov process is determined by a small parameter, which is usually denoted as Ε (epsilon). Various important characteristics of the system depend on the limit value of Ε, such as the probability of blocking, data transfer rate, average waiting time, etc. Markov renewal theorems are used as analytical tool for studying the limiting behavior of a semi-Markov process that depends on a small parameter Ε>0 at Ε→0,t→∞,Εt→u. This theorem makes it possible to study transient phenomena arising in telecommunication systems, such as the asymptotic behavior of additive functionals from ergodic processes, boundary value problems for random walks and processes with independent increments, branched processes close to critical ones, and others. Analyzing the limit behavior of a semi-Markov process with respect to a small parameter is a valuable tool for understanding and optimizing telecommunication systems, ensuring their reliability, and meeting performance requirements. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Data transfer rates

来源：评论

学校读者我要写书评

暂无评论

Research on Distributed Wind and Solar Power modeling Method Based on Swarm Intelligence

Research on Distributed Wind and Solar Power Modeling Method...

引用

international conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Chen, Quanqi He, Yini Jiang, Xiongfeng Xu, Zhongwen Zhang, Xiongbao Chen, Bo Power Dispatch and Control Center of Guangxi Power Grid Company Ltd Guangxi Nanning530023 China CSG Digital Grid Research Institute Co. Ltd Guangdong Guangzhou510663 China

ISBN: (纸本)9789819620418

This paper proposes a distributed wind and photovoltaic power generation modeling method based on swarm intelligence to deal with the uncertainty and complexity problems caused by the connection of distributed photovoltaic and wind power generation systems to the power grid. This method uses a differential evolution algorithm to optimize the search process through chromosome crossover and collaboration between individuals and the survival of the fittest mechanism. The core steps of the algorithm include: population initialization, mutation operation, crossover operation and selection operation. By analyzing the behavioral characteristics of photovoltaic systems and wind power generation systems, and using physical models and statistical models to predict them, a mathematical model of distributed wind and solar power sources was constructed. Research shows that this method can significantly improve the output prediction accuracy and grid dispatch efficiency of distributed photovoltaic and wind power generation systems, solve technical problems caused by distributed power supply access, and enhance the reliability and stability of the power system. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： differential evolution algorithm distributed wind and photovoltaic power swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Research on Antenna Inverse modeling Method Based on Attention Mechanism CNN-BiLSTM

Research on Antenna Inverse Modeling Method Based on Attenti...

引用

international conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Cao, Yuan Hu, Xiao Yin, Songfeng School of Electrical and Control Engineering Liaoning Technical University Huludao125105 China

ISBN: (纸本)9789819620494

In order to solve the problems of long simulation time and many parameters to be optimized in traditional antenna design methods, this paper proposes an antenna inverse modeling method based on the attention mechanism CNN-BiLSTM, which extracts the multidimensional features of the data through convolutional neural network (CNN), and captures the mapping relationship between the electromagnetic response and the geometric parameters of the microwave device by using bidirectional long and short-term memory network (BiLSTM). The introduction of the self-attention mechanism allows the model to notice the correlation between different inputs in the global, maximizing the retention of features and thus improving the robustness of the model. In this paper, the model is applied to the design process of printed dipole antenna. Through comparison, the inverse modeling method shows good prediction and generalization ability, which can be applied to the optimal design of antennas. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Predictive systems for modeling PM10, Ozone, and Temperature Dynamics: A Forecasting Approach for Urban Air Quality in Delhi

引用

AEROSOL SCIENCE AND ENGINEERING 2025年 1-11页

作者： Malik, Rahul Rehman, Fasiur Dhupper, Renu Nadeem, Bisma Jain, Harshita Bhardwaj, Arti Awasthi, Amit Sar, Ayan Choudhury, Tannupriya Amity Univ Uttar Pradesh Amity Inst Environm Sci Noida India Cent Pollut Control Board CPCB Delhi India Acad Sci & Innovat Res AcSIR Ghaziabad India Univ Petr & Energy Studies UPES Sch Adv Engn Dept Phys Dehra Dun India Univ Petr & Energy Studies UPES Sch Comp Sci Dehra Dun 248007 Uttarakhand India

Study investigates the relationship between PM10, ozone and temperature in Delhi's metropolitan areas, a densely populated and industrialized city with significant air pollution problems. Understanding the complex interactions between PM10 and ozone concentrations and climatic variables is the study's main objective. The data included PM10 and ozone concentrations as well as daily readings of the temperature, relative humidity, and other relevant meteorological factors. Regression modelling and correlation analysis is used to examine the relationship between PM10, ozone concentration and temperature. Machine learning approach is used to forecast the Ozone, PM10 and temperature by using the algorithm of auto regressive integrated moving average (ARIMA). Preliminary data indicates a clear relationship between ozone, PM10 concentration and temperature in Delhi's metropolitan areas. The results demonstrate a substantial correlation between these variables, where higher temperatures are linked to higher ozone concentrations and lower PM10 concentrations. Precursor pollutants are implicated in heat-induced photochemical reactions that culminate in the synthesis and deposition of ozone. Study examines the influence of several meteorological factors, such as solar radiation and relative humidity, on the relationship between ozone, PM10, and temperature by observing their past and predicated trends through the years 2018-2026. ARIMA model is used to forecast ozone, temperature, and PM10 levels in Delhi's urban environment that shows good accuracy. The predictions indicate a significant rise in ozone and PM10 concentrations in the coming years, highlighting the urgent need for effective mitigation measures to maintain air quality within national and international standards.

关键词： Correlation Ozone levels PM10 Statistical analysis Temperature Urban regions

来源：评论

学校读者我要写书评

暂无评论

A Direct/Indirect Approach to Optimal control problems 4th

A Direct/Indirect Approach to Optimal Control Problems

引用

4th international conference on Numerical Computations: Theory and Algorithms, NUMTA 2023

作者： Bertolazzi, Enrico Biral, Francesco University of Trento Via Sommarive 9 Trento Italy

ISBN: (纸本)9783031812439

Direct methods are well known to have a large convergence rate in the solution of optimal control problems and thanks to the availability of efficient Non-Linear Programming (NLP) algorithms that are widely adopted. Additionally, it has been proved that thanks to the Covector Mapping Principle (CMP) there is essentially no distinction between direct and indirect methods when Pseudo Spectral collocation is used. In this work, inspired by CMP, a map is proposed to connect the discretized equations of the indirect method with those resulting from the direct transcription with the same trapezoidal scheme. The indirect method will benefit this new formulation since it can adopt the same regularization techniques typically implemented in direct approaches while still maintaining the explicit solution of the control as a function of the states and co-states in a bi-level optimization solution strategy. Finally, the proposed mapping is also derived for the implicit dynamics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optimal control systems

来源：评论

学校读者我要写书评

暂无评论

modeling and Simulation Analysis of Monotonic Frequency control for Constant Current Charging of Wireless Power Transfer System

Modeling and Simulation Analysis of Monotonic Frequency Cont...

引用

international conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Liu, Yinchao Zhong, Wenxing Zhejiang University Hangzhou310058 China

ISBN: (纸本)9789819620494

For wireless power transfer (WPT) systems, the Series-Sires (SS) topology is widely used due to its simple structure and high efficiency. However, it is still a problem to realize zero-voltage switching (ZVS) and output rated power with misalignment and wide load range. To solve these problems, this paper analyzes input impedance angle θin, power and primary current characteristics with frequency modulation (FM). First, based on asymmetrical compensation factor τc theory, the demarcation line of θin has been identified, which reveals the distribution pattern of the power factor with different load resistance and frequency, aiding in the design of WPT system with high power factor. Then, the variation patterns of the primary current and system power have been found out, enabling the system to maintain a low primary current while delivering the rated output power. Finally, a 1.6 kW simulation model is designed to verify the theory, whose coupling coefficient varies in [0.15, 0.2] and load ranges in [15 Ω, 25 Ω]. Monotonic frequency control (MFC) can be achieved in constant current (CC) stage. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Surrogate modeling for control of Microbial Biopolymer Production Process 11

Surrogate Modeling for Control of Microbial Biopolymer Produ...

引用

11th Vienna international conference on Mathematical Modelling, MATHMOD 2025

作者： Dürr, Robert Otto, Eric Kok, Rudolph L. Duvigneau, Stefanie Kienle, Achim Bück, Andreas Magdeburg-Stendal University of Applied Sciences Magdeburg39114 Germany Otto-von-Guericke University Magdeburg39106 Germany Max-Planck-Institute for Dynamics of Complex Technical Systems Magdeburg39106 Germany Friedrich-Alexander-University Erlangen-Nuremberg Erlangen39058 Germany

In this contribution, the Dynamic Mode Decomposition with control (DMDc) is used to derive a surrogate model of a continuous PHA biopolymer production process based on a recently published complex process model. Here, snapshot simulation data of the original model is processed to obtain a linear surrogate model formulation using delay coordinates. The quality of the surrogate is statistically validated within simulation studies. Additionally, the influence of the of the order of delay coordinates is investigated. It is shown, that the highly nonlinear dynamics of the PHA-manufacturing process can be approximated accurately by the DMD-based model even for large variations of initial conditions and control variables. This offers the opportunity to apply well-studied and established tools from robust and optimal control in future investigations. Copyright © 2025 The Authors.

关键词： Process control

来源：评论

学校读者我要写书评

暂无评论

modeling of smart additive manufacturing processes for attack analysis and detection 33

Modeling of smart additive manufacturing processes for attac...

引用

33rd Euromicro international conference on Parallel, Distributed, and Network-Based Processing, PDP 2025

作者： Meleshko, Aleksei Desnitsky, Vasily Kotenko, Igor St. Petersburg Federal Research Center of the Russian Academy of Sciences Laboratory of computer security problems Saint-Petersburg Russia

ISBN: (纸本)9798331524937

The paper proposes an approach to modelling the processes of smart industrial additive manufacturing and related types of attacks in laboratory conditions. The objective of such modelling is to analyze potentially relevant types of attacks on such systems and to evaluate their feasibility. A typical customer-oriented 3D printer BQ Prusa i3 Hephestos 2 is taken as a basis for the proposed approach, as it enables the additive printing of end products and individual parts of complex technical products, e.g. Unmanned Aerial Vehicle (UAV) parts, using plastic spools. In the simulated scenario, the printer operates in conjunction with a personal computer (PC). PC sends digital models of the products to print using G-commands transmitted as part of the Universal Serial Bus (USB) traffic. In this scenario, a range of potential forms of unauthorized interference are examined. In particular, an attack on the digital model of the printed product, whereby the model is modified without due authorization, is simulated by using a built testbed. Such an attack assumes that, upon completion of the printing process, the printed product will appear visually almost indistinguishable from the expected one. However, it will have internal design defects that could significantly affect the reliability of the subsequent operation of this product. The experimental part of the work confirms the feasibility of this type of attack, proposes a way of express detection of such modifications by restoring the model based on G-code analysis. © 2025 IEEE.

关键词： Quality control

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：