检索结果-内蒙古大学图书馆

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Zhao, Huayu Chen, Yixue Dang, Bo Jian, Xiangzhou Department of Electrical Automation Design Beijing Shougang International Engineering Technology Co. Ltd Beijing China Department of Mechanical and Aerospace Enginerring Case Western Reserve University Cleveland United States Department of Computer Science San Francisco Bay University San Francisco United States Department of Mechanical Engineering Columbia University New York United States

ISBN: (纸本)9798331541729

Steel production scheduling represents a pivotal aspect of the steel manufacturing process, encompassing the strategic allocation of resources and the optimization of production processes. This directly impacts the efficiency and cost-effectiveness of the production process. However, conventional scheduling optimization techniques are ill-equipped to address the intricate nuances of the steel production environment and the deluge of real-time data. In this work, a method of steel production scheduling optimization based on deep reinforcement learning was proposed and subsequently innovated and optimized. The Deep Q Network (DQN) was employed as the fundamental model, with the objective of enhancing the stability and convergence speed of the model. This was achieved through the design of the state space and action space of production scheduling, as well as the incorporation of experience playback and target networks. With regard to model optimization, an adaptive adjustment mechanism of the reward function is proposed, which enables the model to balance the optimization of multiple objectives, such as production efficiency and energy consumption, with greater accuracy. Furthermore, the network structure has been enhanced and a multi-head attention mechanism has been incorporated to augment the model's capacity for scheduling decisions in intricate production scenarios. The optimized model was subjected to experimental verification on an actual steel production dataset, and its performance in terms of scheduling efficiency and resource allocation accuracy was found to be excellent. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Maximizing Power Utilization through Machine Learning and IoT based Power Flow Strategies in DC Micro Grids with Renewable Energy Resources 7

Maximizing Power Utilization through Machine Learning and Io...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Senthilkumar, G. Mallala, Balasubbareddy Sivarajan, S. Harish, Cholleti Harsha, Devareddy Natrayan, L. Panimalar Engineering College Department of Computer Science And Engineering Tamil Nadu Chennai India Chaitanya Bharathi Institute of Technology Department of Electrical And Electronics Engineering Telangana Hyderabad India Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Department of Electrical And Electronics Engineering Tamilnadu Chennai India SIMATS Saveetha School of Engineering Department of Mechanical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350359299

The various challenges in the power grid with renewable energy systems are overcome using the implementation of DC microgrids. This helps in obtaining a reliable and efficient energy management system. The maximization of power utilization in microgrids with renewable energy resources is achieved using machine learning with simulated annealing optimization integrated with the Internet of Things through power flow strategies. The variable and intermittent generation patterns are exhibited through renewable energy sources such as wind and solar energy sources. The energy is monitored and obtained through control strategies. The proactive energy management with energy storage capacity and load demand through renewable energy is achieved through machine learning algorithms. The optimum allocation of energy resources is achieved through a simulated annealing optimization algorithm. Another parameter includes the energy distribution strategy that helps to maximize the power utilization in microgrids. This is initiated through factors such as energy storage capacity and various energy generation constraints. This helps to improve the grid stability by reducing the energy losses in the system during transmission and distribution. The power flow strategies with real-time monitoring and control parameters are achieved through the Internet of Things (IoT). The storage levels are monitored using sensors and smart devices. This helps to obtain sustainable power utilization with improved reliability © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Overview of Multi-agent Systems for Controlling Smart Grids

引用

CSEE Journal of Power and Energy Systems 2022年第1期8卷 115-131页

作者： Om Prakash Mahela Mahdi Khosravy Neeraj Gupta Baseem Khan Hassan Haes Alhelou Rajendra Mahla Nilesh Patel Pierluigi Siano Power System Planning Division Rajasthan Rajya Vidyut Prasaran Nigam Ltd.Jaipur-302005India Media Integrated Communication Laboratory Graduate School of EngineeringOsaka UniversityOsakaJapan Computer Science and Engineering Department Oakland UniversityRochesterUSA Department of Electrical and Computer Engineering Hawassa UniversityHawassa 1530Ethiopia Faculty of Mechanical and Electrical Engineering Tishreen UniversityLattakiaSyria Department of Electrical Engineering National Institute of Technology Kurukshetra Department of Management&Innovation Systems University of Salerno84084 SalernoItaly

Agents are intelligent entities that act flexibly and autonomously and make wise decisions based on their intelligence and experience.A multi-agent system(MAS)contains multiple,intelligent,and interconnected collaborating agents for solving a problem beyond the ability of a single agent.A smart grid(SG)combines advanced intelligent systems,control techniques,and sensing methods with an existing utility power *** controlling smart grids,various control systems with different architectures have already been ***-based control of power system operations has been shown to overcome the limitations of time required for analysis,relaying,and protection;transmission switching;communication protocols;and management of plant *** systems provide an alternative for fast and accurate power network *** paper provides a comprehensive overview of MASs used for the control of smart *** paper provides a wide-spectrum view of the status of smart grids,MAS-based control techniques and their implementation for the control of smart *** of MASs in the control of various aspects of smart grids-including the management of energy,marketing energy,pricing,scheduling energy,reliability,network security,fault handling capability,communication between agents,SG-electrical vehicles,SG-building energy systems,and soft grids—have been critically *** than a hundred publications on the topic of MAS-based control of smart grids have been critically examined,classified,and arranged for fast reference.

关键词： Coordinated control multi-agent systems renewable energy sources smart energy infrastructure smart grid

来源：评论

学校读者我要写书评

暂无评论

A predictive surrogate model based on linear and nonlinear solution manifold reduction in cardiovascular FSI: A comparative study

引用

computers in Biology and Medicine 2025年 189卷 109959-109959页

作者： Barzegar Gerdroodbary, M. Salavatidezfouli, Sajad Department of Electromechanical Engineering C-MAST-Center for Mechanical and Aerospace Science and Technology Universidade da Beira Interior Covilha Portugal Department of Electrical and Computer Engineering Aarhus University Aarhus Denmark

This study investigates the fluid-structure interaction (FSI) simulation of the abdominal aorta, with a particular focus on the hemodynamic alterations induced by aneurysmal deformations. The hemodynamic behavior within the aorta is highly dependent on the geometric characteristics of the aneurysm, necessitating the use of patient-specific models to ensure accurate predictions. The primary objective of this research is to enhance the predictive capability of flow and structural indices in a complex FSI biomechanical setting under varying physiological conditions, namely rest and exercise states. This paper presents a comparative analysis between two distinct yet promising surrogate models: Proper Orthogonal Decomposition coupled with Long Short-Term Memory (POD + LSTM) and Convolutional Neural Network combined with Long Short-Term Memory (CNN + LSTM). The methodology, model selection, and comparative performance analysis are discussed in detail, providing insights into the efficacy and limitations of each approach in the context of personalized cardiovascular simulations. © 2025 The Authors

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-purpose Video Annotation for Fast Labeling

Efficient Multi-purpose Video Annotation for Fast Labeling

引用

2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023

作者： Mobaraki, Mobina Ahani, Soodeh Yi, Kwang Moo Asadi, Mahyar Van Heusden, Klaske Dumont, Guy A. University of British Columbia Electrical and Computer Engineering Vancouver Canada University of British Columbia Computer Science Vancouver Canada Novarc Technologies Co. Vancouver Canada School of Mechanical Engineering Kelowna Canada

ISBN: (纸本)9798350359855

We propose an efficient method to label the frames of a video consistently and quickly. Our method is motivated by welding videos, where molten metal moves continuously, and some frames may be noisy due to the high intensity of arc and spatters that can obscure the desired point to be annotated. The traditional annotation methods which pause the videos and annotate each frame individually are time-consuming and may result in inconsistent labeling between different annotators for noisy frames of a video. Our new proposed method benefits from the fact that video sequences are contiguous. We track the location of the cursor while the video is being played, with the user controlling the playback speed, including the playback direction. We process the recorded cursor locations to convert them to the final annotation. Compared to frame-to-frame annotation methods, we show that our proposed interface speeds up the annotating process by 21 times while maintaining consistency of the labels. © 2023 IEEE.

关键词： Liquid metals

来源：评论

学校读者我要写书评

暂无评论

AI -Based Smart Auditorium for Energy and Space Management Using Intelligent Compact Controller 2

AI -Based Smart Auditorium for Energy and Space Management U...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Teli, S.N. Doke, Kanchan K. Siva Kumar, S. Rajan Bab, W. Paul, Sachin Gee Mohan Raj, C. Bharati Vidyapeeth College of Engineering Dept. of Mechanical Engineering Navi Mumbai400 614 India Bharati Vidyapeeth College of Engineering Dept. of Computer Engineering Navi Mumbai400 614 India Nehru Institute of Engineering and Technology Dept. of Computer Science and Engineering Coimbatore641-105 India Sri Eshwar College of Engineering Dept. of Electrical and Electronics Engineering Tamil Nadu Coimbatore641202 India Ilahia College of Engineering and Technology Dept. of Electrical and Electronics Engineering Kerala 686673 India Sri Eshwar College of Engineering Dept. of Electrical and Electronics Engineering Tamil Nadu Coimbatore641202 India

ISBN: (纸本)9798350327533

Efficient use of energy rather than production is essential in this era. A large percentage of electricity is being wasted unnecessarily. This energy wastage often occurs in crowded places such as college auditoriums and movie theaters. Energy efficiency can be brought into practical life by providing only as much energy as there is to as many people as there are. Apart from energy savings, by introducing automation and artificial intelligence, the sizes of even the largest halls can be adapted to suit the needs. Thus space and energy savings can be ensured by limiting the size of the space and the number of appliances required. This is called energy-saving implementation. This is the main objective of the article. FX5U controller is used here for automating the seating selection and actuating the corresponding electromechanical output based on the user input. The input and outputs are independently controlled and the efficient energy and space management can be accomplished by implementing the suitable AI algorithm as a script or ladder in the FX5U controller side. The GOT2000 is used for interfacing / data transferring between the human and the machine. © 2024 IEEE.

关键词： Efficient use of Energy FX5U Programmable Logic Controller GOT2000 Human Machine Interface Smart Auditorium Space and Energy Management

来源：评论

学校读者我要写书评

暂无评论

A Quality Diversity Study in EvoDevo Processes for engineering Design 13

A Quality Diversity Study in EvoDevo Processes for Engineeri...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Buchanan, Edgar Hickinbotham, Simon Dubey, Rahul Friel, Imelda Colligan, Andrew Price, Mark Tyrrell, Andy M. School of Physics Engineering and Technology University of York Intelligent Systems & Robotics Research Group United Kingdom Missouri State University Computer Science United States School of Mechanical & Aerospace Engineering Queen's University Belfast United Kingdom

ISBN: (纸本)9798350308365

For a long time engineering design has relied on human engineers manually crafting and refining designs using their expertise and experience. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are employed to investigate a broader design space that may go beyond what human engineers have considered. Previous literature has demonstrated the use of quality and diversity (QD) algorithms in evolutionary approaches to drive the process to better quality solutions. This paper provides a study to understand the effects of using QD algorithms in EvoDevo processes for engineering design. This paper also analyses the impact of using different behavioural characterisations (BC) in the performance of the quality of the solutions found. The results demonstrate that quality and diversity algorithms can find better solutions than other EAs for engineering design problems. It was also found that the characterisation of the BC is important to get the best results. © 2024 IEEE.

关键词： evodevo generative design neural networks quality diversity structural engineering

来源：评论

学校读者我要写书评

暂无评论

Characterization of the Dynamical Properties of Safety Filters for Linear Planar Systems

Characterization of the Dynamical Properties of Safety Filte...

引用

IEEE Conference on Decision and Control

作者： Yiting Chen Pol Mestres Emiliano Dall’Anese Jorge Cortés Department of Electrical and Computer Engineering Boston University Department of Mechanical and Aerospace Engineering University of California San Diego

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper studies the dynamical properties of closed-loop systems obtained from control barrier function-based safety filters. We provide a sufficient and necessary condition for the existence of undesirable equilibria and show that the Jacobian matrix of the closed-loop system evaluated at an undesirable equilibrium always has a nonpositive eigenvalue. In the special case of linear planar systems and ellipsoidal obstacles, we give a complete characterization of the dynamical properties of the corresponding closed-loop system. We show that for underactuated systems, the safety filter always introduces a single undesirable equilibrium, which is a saddle-point. We prove that all trajectories outside the global stable manifold of such equilibrium converge to the origin. In the fully actuated case, we discuss how the choice of nominal controller affects the stability properties of the closed-loop system. Various simulations illustrate our results.

关键词： Manifolds Jacobian matrices Filters Stability analysis Eigenvalues and eigenfunctions Safety Trajectory Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

MA-CVP-MVSNet: Multi-View Stereo Model Based on Hybrid Attention Network 3

MA-CVP-MVSNet: Multi-View Stereo Model Based on Hybrid Atten...

引用

3rd International Conference on Electronic Information engineering and computer science, EIECS 2023

作者： Lu, Lu Huang, Hongbo Yan, Xiaoxu Liu, Yizhuo Zhang, Zixia Chen, Hanjun Zhou, Shichao Rui, Zixuan Beijing Information Science and Technology University Mechanical Electrical Engineering School Beijing China Beijing Information Science and Technology University Computer School Beijing China

ISBN: (纸本)9798350316674

In current deep-learning-based multi-view stereo methods, feature extraction and cost volume regularization are two key steps that affect the reconstruction quality. Most current methods have difficulties both in accurately extract the required features and fully utilize the multi-scale contextual semantic information in the cost volumes. In this work, we propose a MA-CVP-MVSNet based on hybrid attention mechanism for multi-view stereo. The proposed method consists of two core attention mechanisms. One is the Criss-Cross Attention module to capture the global dependencies of the pixels in the feature map. The other is the SK Attention module, which is used for cost volume regularization to aggregate multi-scale contextual semantic information in the cost volumes. Experiments show that our method has a remarkable improvement in accuracy and achieves competitive results. © 2023 IEEE.

关键词： Attention mechanism Cost volume Depth estimation Feature extraction Multi-view stereo

来源：评论

学校读者我要写书评

暂无评论

Enhanced Model Predictive Control Strategy for the Three-Phase 5-Level Multiplexed Converter

Enhanced Model Predictive Control Strategy for the Three-Pha...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Di Benedetto, Marco Formentini, Andrea Lidozzi, Alessandro Solero, Luca Marchesoni, Mario Roma Tre University Department of Industrial Electronic and Mechanical Engineering Roma Italy University of Genova Department of Naval Electrical Electronics and Telecommunications Engineering Genova Italy Roma Tre University Department of Civil Computer Science and Aeronautical Technologies Engineering Roma Italy

ISBN: (纸本)9798350376067

This paper presents a Finite Control Set Model Predictive Control (FCS-MPC) algorithm for the three-phase 5-level multiplexed converter (3φ5L MLMXC). The 3φ5L MLMXC comprises two Flying Capacitors (FC) topologies connected to the three-phase NPC topology. The main idea of the proposed control algorithm is to balance the flying capacitors placed in the top and bottom FC converter. The proposed topology is deeply described, and the MPC algorithm for 3φ5L MLMXC has been presented. The SVM algorithm has been implemented in a field-programmable gate array (FPGA). Simulation and Hardware-In-the-Loop results show the usefulness of the presented analysis. © 2024 IEEE.

关键词： Hardware-in-the-loop simulation

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：