检索结果-内蒙古大学图书馆

21st International Conference on Networking, Sensing and control, ICNSC 2024

作者： Guo, Zeyu Guo, Xiwang Wang, Jiacun Qin, Shujin Qi, Liang Kang, Qi Liaoning Petrochemical University Information and Control Engineering Fushun China Monmouth University Computer Science and Software Eng. Wes Long BranchNJ United States Shangqiu Normal University Economics and Management Shangqiu China Shandong Technology University Computer Science Department Qingdao China New Jersey Institute of Technology Electrical and Computer Engineering Newark United States

ISBN: (纸本)9798350365221

As disassembly lines evolve, keeping workers safe from all potential dangers has become paramount. This work proposes an improved approach, Proximal Policy Optimization for Disassembly Line(PPO-DL), to address Multi-objective Dis-assembly Line Balancing Problem(MDLBP) that integrates task switching time and hazardous tasks. The MDLBP model aims to optimize disassembly net profit, balance workstation utilization, and mitigate penalties from hazardous tasks. The proposed PPO-DL modifies the action space of PPO to accommodate MD LBP characteristics, ensuring efficient learning by restricting actions to valid ranges through action masking. Comparative experiments with PPO, Q-learning, and A2C demonstrate PPO-DL's superiority in finding near-optimal solutions across various scenarios. © 2024 IEEE.

关键词： Assembly machines

来源：评论

学校读者我要写书评

暂无评论

Lightweight Security Protection System Architecture for Digital Grid Mobile Application Platform 2

Lightweight Security Protection System Architecture for Digi...

引用

2nd International Conference on Green Communication, Network, and Internet of Things, CNIoT 2022

作者： Ren, Jiyuan Liu, Fuyang Song, Yang Wang, Zhe Yin, Lu Wang, Jing Dispatching and Control Center Northeast Branch of State Grid Corporation of China Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781510662940

The risk of data leakage and security vulnerabilities exist in digital grid mobile application platforms such as "i State Grid". To address this problem, an application security plug-in for digital grid smart terminals is designed. A lightweight mobile application security protection system architecture is proposed to prevent user data from being damaged and leaked. The system architecture mainly contains three aspects: static environment assessment of mobile applications, dynamic detection of malicious applications, and mobile application risk assessment. That also reduces the security risk from external factors such as the Internet, and effectively ensures the safe and stable operation of the "i State Grid" system. © 2023 SPIE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Core Losses Calculation and Thermal Evaluation Using the VBR-Based Finite Element Model of Induction Motors

Computationally Efficient Core Losses Calculation and Therma...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Valipoor, Zahra Koti, Hossein Nejadi Demerdash, Nabeel A. O. Marquette University Electrical and Computer Engineering Department Milwaukee United States Rockwell Automation Inc. Motion Control Team Mequon United States

ISBN: (纸本)9798350316445

Accuracy of the simulation results obtained from the FEA analysis of electric motors is highly dependent on the quality of the motor performance metrics such as motor steady state temperatures and losses. In addition such FEA analysis is typically computationally burdensome and demanding. Improving the computational burden and accuracy of core losses calculation and thermal evaluation in Time-Stepping Finite Element (TS-FE) models of induction motors is addressed in this paper. The Virtual Blocked Rotor (VBR)-based Time-Stepping Finite Element (TS-FE) technique is utilized to mitigate the numerical transient response of the induction motor FE model. The motor core losses have been calculated through the harmonic based core loss calculation that assumes variable loss coefficients as a function of magnetic flux density. In addition, the motor estimated losses, including the calculated core losses are fed to a thermal network model to estimate the temperature of different motor components. © 2023 IEEE.

关键词： Core Losses Induction Motor Temperature Thermal Calibration VBR-based FEA

来源：评论

学校读者我要写书评

暂无评论

Retinal disorder diagnosis based on hybrid deep learning models

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Sedik, Ahmed El-Shafai, Walid El-Hag, Noha A. El-Banby, Ghada M. Abd El-Samie, Fathi E. Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Kafr el-Sheikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt The Higher Institute of Commercial Sciences Algarbia Al Mahalla Al Kubra31951 Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtained with several modalities, such as magnetic resonance (MR) and confocal microscopy, need to be classified for anomaly detection. The MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, brain tumors are represented as areas composed of abnormal cells that need to be detected. On the other hand, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye, such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify normal and abnormal cases of both brain tumor and DR diseases. The CNN model is composed of six convolutional layers and six max-pooling layers. A soft-max activation function takes the classification decision. The proposed Conv-LSTM model is composed of three stages: pre-processing, feature extraction, and classification. The deep learning model performance is better than those of traditional networks. The CNN gives an accuracy of 94.26% for DR classification and 95.8% for brain tumor classification, while the Conv-LSTM gives the maximum accuracy of 96.41% for DR classification and 97.4% for brain tumor classification. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Confocal microscopy

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient VBR-Based Sensitivity Analysis of Induction Motors

Computationally Efficient VBR-Based Sensitivity Analysis of ...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Koti, Hossein Nejadi Valipoor, Zahra Demerdash, Nabeel A. O. Rockwell Automation Inc. Motion Control Team Mequon United States Marquette University Electrical and Computer Engineering Department Milwaukee United States

ISBN: (纸本)9798350316445

Sensitivity analysis is a powerful tool that can be utilized for reducing the size of the design space at hand to explore and significantly reduce the computational burden of the optimization process. This is achieved by 'smart' design variable selection. The term 'smart' indicates fixing the un-conflicting design variables that do not require exploration to their maximum or minimum values, depending on their enhancing or degrading effect on the objective functions and allowing the conflicting design variables to be explored within their allowable dynamic range. Intelligent optimization is a critical part of induction motor design process. In this paper, computationally efficient sensitivity analysis is performed to effectively reduce the number of the design variables that will be actively explored in the optimization process of the induction motors. This goal is achieved through the VBR-based TS-FEA together with Design of Experiment and Response Surface Methodology. In addition, the motor estimated losses, including the calculated core losses are fed to a thermal network model to estimate the temperature of different motor components. © 2023 IEEE.

关键词： Core Losses Induction Motor Temperature Thermal Calibration VBR-based FEA

来源：评论

学校读者我要写书评

暂无评论

Beam-line parameter image processing optimization and maintenance for beam alignment in the National Ignition Facility 7

Beam-line parameter image processing optimization and mainte...

引用

High Power Lasers for Fusion Research VII 2023

作者： Awwal, Abdul A.S. Leach, Richard Lowe-Webb, Roger Kamm, Vicki Miller Integrated Computer Control System National Ignition Facility Computational Engineering Division Lawrence Livermore National Laboratory LivermoreCA94551 United States

ISBN: (纸本)9781510659070

The National Ignition Facility (NIF) employs 192 laser beams to achieve inertial confinement fusion by irradiating a mm scale fusion target. Automatic alignment (AA) image processing algorithms are used to align 192 beams to the NIF target chamber center. Cameras placed along the beam path supply the images that are analyzed by AA algorithms to provide beam location and alignment information. NIF has the capability of using beam-specific database parameters. This allows beam line images to be processed using optimized algorithms tailored to individual beam alignment needs. For a given segment of alignment in the NIF beam path, 192 different versions of the algorithm can be run simply by changing data base parameters. This capability is vital to alignment precision in a system as complex and mature as NIF. Since optical components and devices age, laser parameters and beam alignment quality can and do change. Constant beam-by-beam monitoring of alignment performance is needed in order to mitigate any issues caused by such changes. The objective of this work is to evaluate how periodic AA algorithm beam parameter changes might better maintain alignment requirements over time in the NIF facility. We show examples from final optics assembly (FOA) and harmonic generator (THG, SHG) loops. © 2023 SPIE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Fed-Autoformer: A Federated Learning-Based Battery Anomaly Detection Approach for Electric Vehicle Charging with Privacy Preservation 30th

Fed-Autoformer: A Federated Learning-Based Battery Anomaly D...

引用

30th International Conference on Computational and Experimental engineering and Sciences, ICCES 2024

作者： Yan, Xuhan Yang, Shunbo Guo, Yiguo Fu, Yimu Wu, Sixing Li, Jianbin School of Control and Computer Engineering North China Electric Power University Beijing China Economic Technology Research Institute State Grid Shandong Electric Power Company Shandong Jinan City China

ISBN: (纸本)9783031829062

The battery management system ensures the safe operation of electric vehicles (EVs) by detecting abnormalities in the battery energy storage system. However, the extensive and widely dispersed data in EV battery data, along with the presence of users’ private details, raise a demand for effective anomaly detection and privacy protection. To tackle those two challenges, we propose Fed-Autoformer, a distributed anomaly detection architecture based on real vehicle charging data to detect battery anomalies and protect privacy. Thus, we first propose a novel anomaly detection model for EV charging data based on the Autoformer encoder architecture. In particular, it enables an autocorrelation attention mechanism to extract and consider the intrinsic correlation of battery data features (e.g., voltage, current, state of charge (SOC), etc.) for anomaly detection. In addition, we introduce a federated learning architecture to protect the privacy of battery charging data and improve the federated learning training process based on the differences between vehicle batteries in charging stations to ensure detection accuracy while protecting the privacy of EV charging data. Finally, we comprehensively analyze the feasibility and effectiveness of our proposed architecture using a real EV charging dataset. Our proposed federated learning approach for EV battery anomaly detection not only effectively protects privacy through federated learning but also improves the accuracy by 3.2% compared to most mainstream time series anomaly detection models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

Modeling a Single Camera System based on Predicted Bounding Box and Pan-Tilt Angles 13

Modeling a Single Camera System based on Predicted Bounding ...

引用

13th IEEE International Conference on System engineering and Technology, ICSET 2023

作者： Putri, Adi Novitarini Maria, Fabiola Hidayat, Egi Mahayana, Dimitri Machbub, Carmadi Institut Teknologi Bandung Control and Computer Research Group School of Electrical Engineering and Informatics Bandung Indonesia Institut Teknologi Sains Bandung Bekasi Indonesia

ISBN: (纸本)9798350340891

The control schemes that are related to visual servoing systems are often done through trial and error. Based on the classical control concept, it is necessary to have a mathematical model of the plant before designing the controller. Therefore, this research focuses on producing a mathematical model of the pan-tilt system. We propose the combination of the computer vision method with the classic system identification method, namely N4SID to obtain the dynamics model of a pan-tilt system. In this research, the system identification procedure was successful in producing a state-space model of a visual servoing system using a pan-tilt system and a single camera. This study merged traditional system identification techniques with computer vision to create a discrete-time linear state-space model. When the system order value equals three, the approximation with the minimum MSE value is obtained. © 2023 IEEE.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Balancing Human-robot Collaborative Disassembly Line by Using Dingo Optimization Algorithm 4

Balancing Human-robot Collaborative Disassembly Line by Usin...

引用

4th IEEE International Conference on Human-Machine Systems, ICHMS 2024

作者： Guo, Xiwang Zhou, Liangbo Zhou, Mengchu Wang, Weitian Wang, Jiacun Qi, Liang Liaoning Petrochemical University Information And Control Engineering Fushun China Liaoning Petrochemical University Information And Control Fushun China New Jersey Institute Of Technology Electrical And Computer Engineering NewarkNJ United States Montclair State University School Of Computing Montclair United States Monmouth University Computer Science And Software Eng. West Long BranchNJ United States Shandong University Of Sci. And Tech. Computer Intelligent Sci. And Tech. Qingdao China

ISBN: (纸本)9798350315790

Disassembling and recycling scrapped products play important roles in effectively reducing environmental pollution and improving resource sustainability. A multi-product human-robot collaborative disassembly-line-balancing problem (MHDP) arises from doing so and represents an important yet to be solved in the remanufacturing field. This work explores how to use optimization algorithms to schedule tasks between humans and robots to maximize remanufacturing profit in human-robot collaboration contexts. Specifically, we investigate MHDP and develop a mixed integer programming model considering various system constraints. We propose a dingo optimization algorithm that simulates wild dogs' social hierarchy and chasing processes to solve MHDP. We compare the proposed algorithm with an exact solution finder, i.e., IBM CPLEX and a well-known intelligent optimization method, i.e., Genetic Algorithm to show its competitive performance in terms of solution accuracy and efficiency. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Path Planning with Multiple Constraints for Autonomous Vehicles Based on Nonlinear Reduced-Order Model Predictive control

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Badiei, Mohammad Hossein Dashtaki, Saeed Mohammadi Vafamand, Navid Piran, Md. Jalil University of Tehran School of Electrical and Computer Engineering College of Engineering Tehran Iran Shiraz University Department of Power and Control Engineering Shiraz Iran Sejong University Department of Computer Science and Engineering Korea Republic of

In this paper, we present a Risk-Aware Nonlinear Reduced-Order Model Predictive control framework that utilizes real-time state estimation, reduced-order modeling, and optimization for reliable and efficient path planning with low energy consumption. Our method employs filtering techniques to estimate the system's state by correcting for process and measurement noise, providing an accurate representation of the vehicle's position and environment. A reduced-order model predicts future states based on the estimated input, while the optimizer adjusts control inputs to meet trajectory and safety constraints, such as avoiding obstacles. By incorporating adapted filtering techniques and optimized cost functions, our approach minimizes computational overhead while maintaining precise control over vehicle navigation. In the experiments, we introduce communication and process noises, allowing the robot to operate without knowing the precise location of obstacles and resulting in potential near-collisions. This involves redefining the constrained optimal control problem for a reduced-order model, addressing input constraints amidst uncertainties. Our method achieves over 94% success in collision-free navigation within the first 50 steps, while maintaining precise trajectory alignment and adapting to environmental changes. It also improves prediction speed up to 15% per cycle compared to NMPC and demonstrates 91% overall effectiveness in avoiding collisions and reaching the target. © 1975-2011 IEEE.

关键词： Cost functions

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：