检索结果-内蒙古大学图书馆

12th IEEE PES Asia-Pacific Power and Energy engineering Conference, APPEEC 2020

作者： Wang, Qi Li, Ning Gu, Xin Zhang, Nianchu Chen, Yonghua He, Guoxin Nanjing Normal University School of Electrical and Automation Engineering Nanjing China Simulation and Operation Control Nari Group Corporation Laboratory of Integrated Energy System Nanjing China

ISBN: (纸本)9781728157481

Energy interconnection system integrating 'Internet+' has become a new developing form of energy industry with the increase of Chinese urbanization level. It features the characteristics of multiple energy entities interconnection and independent decision. The decision-making structure, requirements of massive data processing, real-time communication and privacy security prevent the further application of centralized optimization method based on independent decision-making entities. Additionally, the difference of optimization among the energy entities cannot be ignored in the distributed optimization application. Integrating the concepts of 'cloud supervision' and 'weak centralization', this paper proposes a centralized distributed collaborative regulation and control architecture, and studies the decision-making method under this architecture to accelerate the local and global optimization. Based on this, this paper analyzes and summarizes the key technologies involved, including edge-cloud collaborative deployment mechanism, engineering data processing and service technology for energy interconnection system in new-type towns. The purpose is to provide a way to realize the optimal dispatch of energy interconnection system in new-type towns, and provide some suggestions for the development of energy interconnection system in new-type towns. © 2020 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Information-containing Adversarial Perturbation for Combating Facial Manipulation systems

arXiv

引用

arXiv 2023年

作者： Zhu, Yao Chen, Yuefeng Li, Xiaodan Zhang, Rong Tian, Xiang Zheng, Bolun Chen, Yaowu College of Biomedical Engineering & Instrument Science Zhejiang University Hangzhou310027 China Security Department of Alibaba Group Hangzhou311121 China Zhejiang Provincial Key Laboratory for Network Multimedia Technologies Hangzhou310027 China School of Automation Hangzhou Dianzi University Hangzhou310018 China Zhejiang University Embedded System Engineering Research Center Ministry of Education of China Hangzhou310027 China

With the development of deep learning technology, the facial manipulation system has become powerful and easy to use. Such systems can modify the attributes of the given facial images, such as hair color, gender, and age. Malicious applications of such systems pose a serious threat to individuals’ privacy and reputation. Existing studies have proposed various approaches to protect images against facial manipulations. Passive defense methods aim to detect whether the face is real or fake, which works for posterior forensics but can not prevent malicious manipulation. Initiative defense methods protect images upfront by injecting adversarial perturbations into images to disrupt facial manipulation systems but can not identify whether the image is fake. To address the limitation of existing methods, we propose a novel two-tier protection method named Information-containing Adversarial Perturbation (IAP), which provides more comprehensive protection for facial images. We use an encoder to map a facial image and its identity message to a cross-model adversarial example which can disrupt multiple facial manipulation systems to achieve initiative protection. Recovering the message in adversarial examples with a decoder serves passive protection, contributing to provenance tracking and fake image detection. We introduce a feature-level correlation measurement that is more suitable to measure the difference between the facial images than the commonly used mean squared error. Moreover, we propose a spectral diffusion method to spread messages to different frequency channels, thereby improving the robustness of the message against facial manipulation. Extensive experimental results demonstrate that our proposed IAP can recover the messages from the adversarial examples with high average accuracy and effectively disrupt the facial manipulation systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Safe Braking Model of Virtually Coupled Trains for Closer Tracking

An Improved Safe Braking Model of Virtually Coupled Trains f...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Wenxiao Yan Jiayu Wang Liqun Fan Qiusheng Liu Qingdong Jia Yihan Wang Hongjie Liu School of Automation and Intelligence Beijing Jiaotong University Beijing China Shenzhen Metro Group Co. Ltd. Shenzhen China Shenzhen Municipal Design and Research Institute Co. Ltd. Shenzhen China Traffic control Technology Co. Ltd. Beijing China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing China

ISBN: (数字)9798350365221

ISBN: (纸本)9798350365238

With the rapid growth of transportation passenger flow in recent years, the research direction of Virtual Coupling (V C) in railways has become hot. V C increases capacity by tracking shorter distances. The traditional train emergency braking (EB) model can no longer meet the high operating efficiency requirements of VC. VC urgently needs a more efficient safety EB model. Therefore, to improve efficiency, a measurement of the EB model's rationality is defined considering safety and efficiency. Based on the defined model measurement, an EB model optimization method and a new EB model are proposed. The new model is closer to the actual braking process of the train and ensures safety from the distance level. That is, the braking trajectory of the train calculated by the new model is closer to the actual braking trajectory of the train, and the two braking trajectories satisfy the specific safety constraints. Finally, the safety and efficiency of the new model were verified through simulation experiments. The new model can avoid train collisions during the entire EB process. Experimental results show that compared with the traditional old EB model of VC based on space-time interval [1], the new model's minimum safe distance (MSD) between two VC train units can be reduced by 39%.

关键词： Couplings Analytical models Optimization methods Transportation Process control Safety Trajectory Sensors Brakes

来源：评论

学校读者我要写书评

暂无评论

Research on Image Enhancement and Detection Techniques for Multiple Fault Types in Insulators of Power Transmission Lines

SSRN

引用

SSRN 2024年

作者： He, Min Qin, Liang Li, Qiang Zhu, Wanjun Deng, Xinlan Liu, Kaipei Hubei Key Laboratory of Power Equipment System Security for Integrated Energy 299 Bayi Road Wuchang District Hubei Wuhan430072 China School of Electrical Engineering and Automation Wuhan University 299 Bayi Road Wuchang District Hubei Wuhan430072 China State Grid Information Telecommunication Group Co. Ltd. Changping District Future Science and Technology City Beijing102211 China

Insulators are crucial components in power transmission lines, and their exposure to harsh environmental conditions can lead to malfunctions. The complexity of insulator inspection arises primarily from the intricate lighting and background conditions in the inspection environment. Effectively and promptly detecting the fault status of these insulators in such a complex environment is an urgent issue that needs to be *** paper addresses the challenges posed by complex lighting conditions, particularly the issues of uneven illumination in low-light and high overexposure environments. A novel adversarial network based on structure and brightness layer decomposition and fusion is designed to tackle these challenges. Through the implementation of a brightness balance loss strategy, the usability of inspection images is enhanced, resulting in an average PSNR improvement of 0.4 and an SSIM improvement of 0.29 in the enhanced ***, an improved YOLOv8-based algorithm for detecting multiple fault types in aerial images of insulators with complex backgrounds and varying fault sizes is designed. This algorithm aims to achieve rapid and accurate localization of insulators and their respective fault areas.A portion of the approach utilizes the distribu tion characteristics of insulators, combining them with an axial attention feature extraction structure to extract targets in complex backgrounds. In the subsequent feature fusion stage, a multi-scale feature fusion structure, Res-PANet, based on residual skip connections, is constructed to replace the original PANet network. This replacement aims to enhance the detection accuracy of the network in multi-object *** results indicate that the detection model, after preprocessing for complex lighting conditions, achieves a higher detection accuracy, with an average precision of 89.93%. This demonstrates a strong practical value for engineering applications. © 2024, The Authors. All rights r

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

An OpenPLC-based Active Real-time Anomaly Detection Framework for Industrial Control systems

An OpenPLC-based Active Real-time Anomaly Detection Framewor...

引用

Chinese automation Congress (CAC)

作者： Chengxu Zheng Xiaopeng Wang Xiaoyu Luo Chongrong Fang Jianping He The Dept. of Automation Shanghai Jiao Tong University the Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China NSFOCUS Technologies Group Co. Ltd Beijing China

In recent years, the design of anomaly detectors has attracted a tremendous surge of interest due to security issues in industrial control systems (ICS). Restricted by hardware resources, most anomaly detectors can only be deployed at the remote monitoring ends, far away from the control sites, which brings potential threats to anomaly detection. In this paper, we propose an active real-time anomaly detection framework deployed in the controller of OpenPLC, which is a standardized open-source PLC and has high scalability. Specifically, we add adaptive active noises to control signals, and then identify a linear dynamic system model of the plant offline and implement it in the controller. Finally, we design two filters to process the estimated residuals based on the obtained model and use χ 2 detector for anomaly detection. Extensive experiments are conducted on an industrial control virtual platform to show the effectiveness of the proposed detection framework.

关键词： Adaptation models Industrial control Detectors Real-time systems Software Security Task analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Core Real- Time Scheduling Based on Reinforcement Learning

Adaptive Multi-Core Real- Time Scheduling Based on Reinforce...

引用

International Conference on Control and automation (ICCA)

作者： Yonghui Liang Hui Li Fei Shen Qimin Xu Shuna Hua Shanying Zhu Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Re-search Center of Intelligent Control and Management Shanghai China Key Laboratory of Wireless Sensor Network and Communications Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China North Information Control Research Academy Group Company Ltd. Nanjing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

With the transformation towards industrial intel-ligence, multi-core processors are increasingly being applied in real-time networked control systems to ensure secure exe-cution of sensing, computing and actuating tasks under time constraints. However, existing scheduling methods result in either low CPU utilization or many missed task deadlines in dynamic systems. In this paper, we propose a two-layer scheduling architecture to address this issue by fully exploring the complex dependency between real-time tasks. To be specific, the local layer determines task execution priorities considering both dependency between tasks and deadline constraints by utilizing a reinforcement learning approach. Moreover, to better utilize the parallel capabilities of multi-core processors and reduce temporal collisions, this paper minimizes the requested core count for the task set based on a greedy strategy. The global layer designs a scheduling algorithm based on the pre-empt method and provides schedulability analysis of multiple task sets. Experimental results validate the correctness of the proposed scheduling approach, and efficiency is demonstrated through comparisons with baseline method.

关键词： Job shop scheduling Multicore processing Scheduling algorithms Networked control systems Reinforcement learning Real-time systems Sensors

来源：评论

学校读者我要写书评

暂无评论

China’s 10-year progress in DC gas-insulated equipment:From basic research to industry perspective

引用

iEnergy 2022年第4期1卷 400-433页

作者： Chuanyang Li Changhong Zhang Jinzhuang Lv Fangwei Liang Zuodong Liang Xianhao Fan Uwe Riechert Zhen Li Peng Liu Jianyi Xue Cheng Pan Geng Chen Lei Zhang Zheming Wang Wu Lu Hucheng Liang Zijun Pan Weijian Zhuang Giovanni Mazzanti Davide Fabiani Bo Liu Shaohua Cao Jianying Zhong Yuan Deng Zhenle Nan Jingen Tang Jinliang He State Key Laboratory of Power Systems Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Maintenance&Test Center of EHV Power Transmission Company China Southern Power Grid Guangzhou 510663China EHV Power Transmission Company China Southern Power Grid Guangzhou 510663China Hitachi Energy Switzerland Ltd ZürichSwitzerland Key Laboratory of Engineering Dielectrics and Its Application Ministry of EducationHarbin University of Science and TechnologyHarbin 150080China State Key Laboratory of Electrical Insulation and Power Equipment Xi’an Jiaotong UniversityXi’an 710049China School of Electrical Engineering and Automa-tion Hefei University of TechnologyHefei 230009China School of Electrical Engineering and Automation Wuhan UniversityWuhan 430072China Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China Department of Electrical Engineering Shanghai University of Electric PowerShanghai 200090China School of Electrical and Information Engineering Tianjin UniversityTianjin 300072China Department of Electrical Electronic and Information EngineeringUniversity of BolognaBologna 40136Italy Shandong Taikai Electrical Insulation Co. Ltd.Tai’an 271000China PingGao Group CO. Ltd.Pingdingshan 467001China China XD Group Co. Ltd.Xi’an 710075China Jiangsu Jinxin Electric Appliance Co. Ltd.Yangzhou 225202China

The construction of the future energy structure of China under the 2050 carbon-neutral vision requires compact direct current(DC)gas-insulation equipment as important nodes and solutions to support electric power transmission and distribution of long-distance and *** paper reviews China's 10-year progress in DC gas-insulated *** progresses in basic research and industry perspective are presented,with related scientific issues and technical bottlenecks being *** progress in DC gas-insulated equipment worldwide(Europe,Japan,America)is also reported briefly.

关键词： DC gas-insulated switchgear(GIS) DC gas-insulated power transmission line(GIL) surface charge flashover metal particle offshore projects

来源：评论

学校读者我要写书评

暂无评论

An Integrated Model Combining CNN-GRU with ARIMA for pressure prediction of water supply network

An Integrated Model Combining CNN-GRU with ARIMA for pressur...

引用

第40届中国控制会议

作者： Bo Wang Miaoshun Bai Jingcheng Wang Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Municipal Engineering Design Institute (Group) Co. Ltd

In the problem of time series prediction, the accuracy has always been an enduring research hotspot. In this paper,we proposed an integrated model named CNN-GRU-ARIMA to improve the accuracy of pressure prediction for water supply network. The proposed model is mainly comprised of the two parts, namely ARIMA and CNN-GRU. The ARIMA is usually used for the univariate prediction, and the CNN-GRU represents the multivariate prediction model. Also, several metrics including MAE, RRSE, RMSE are exploited to facilitate quantitative analysis of the accuracy differences between different models mentioned. The experiments show that our proposed scheme adopted in integrated model can achieve the better performance than some state-of-the-art approaches.

关键词： Time series prediction CNN GRU ARIMA

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode Observation and Control for Overhead Cranes with Varying Rope Length

Sliding Mode Observation and Control for Overhead Cranes wit...

引用

2021 China automation Congress, CAC 2021

作者： Huan, Xuwei Niu, Dan Li, Qi Yang, Jun Liu, Guoyao Chen, Xisong Xiao, Xi Key Laboratory of Measurement and Control of CSE Ministry of Education Southeast University Nanjing China Department of Aeronautical and Automotive Engineering Loughborough University LoughboroughLE11 3TU United Kingdom Nanjing Sciyon Automation Group Co. Ltd Nanjing China Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration Nanjing China

ISBN: (纸本)9781665426473

This paper proposes a state observer and controller based on the second-order sliding mode scheme for underactuated overhead cranes with load hoisting and lowering. The designed state observer can effectively estimate the uncertainly and unmodeled dynamics of crane systems, and provide appropriate driving force compensations for the sliding mode controller designed by coupling the load swing angle. This guarantees an accurate load positioning and residual swing elimination. Based on the Lyapunov stability criterion, the asymptotic stability of the control system is proved Several simulations are implemented to verify the effectiveness and robustness of the proposed controller for anti-sway and positioning controls. © 2021 IEEE

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

An Improved Ensemble Deep Learning Model for Water Leakage Detection

An Improved Ensemble Deep Learning Model for Water Leakage D...

引用

第40届中国控制会议

作者： Shuwei Zhang Miaoshun Bai Jingcheng Wang Haotian Xu Shunyu Wu Dept of Automation Shanghai JiaoTong UniversityKey Laboratory of System Control and Information ProcessingMinistry of Education of China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Municipal Engineering Design Institute(Group)Co. Ltd

The leakage location for water supply system is a key point for the efficient operation and maintenance of urban water supply ***,the limited source of leakage dataset,high cost of leakage simulation experiments and the limited prediction accuracy of traditional models increase the difficulty of the leakage location for urban water supply *** paper proposes a new method based on ensemble learning method to address these *** software is employed in this paper for the generation of experimental *** leakage is located and predicted based on the hydraulic model of the water supply system through the design of the improved multi-model weighted voting mechanism for ensemble deep learning *** experiments show that the proposed method has higher precision and lower discretization compared to traditional models.

关键词： Water supply system Neural-network models Leakage detection Ensemble learning

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：