检索结果-内蒙古大学图书馆

Fault-tolerant control of a smart PV-grid hybrid system

IET RENEWABLE POWER GENERATION 2019年第13期13卷 2451-2461页

作者： Tiar, Mourad Betka, Achour Drid, Said Abdeddaim, Sabrina Sellali, Mehdi Medjmadj, Slimane Univ Biskra Dept Elect Engn LGEB Lab Biskra Algeria Batna Univ Dept Elect Engn LSPIE Lab Batna Algeria Univ Ctr Bordjbouarreridj Dept Elect Engn UFAS Lab Automat El Anasser Algeria

This study deals with a fault-tolerant control of a smart PV-grid plant. The small scale system is dedicated to a stationary alternative current load and it consists of a photovoltaic module, supported by a single-phase grid. To ensure a smart permutation between the two proposed operation modes, a fuzzy logic-based power management algorithm is designed and implemented. In case of a sub-system failure, a fault-tolerant control technique is adopted to maintain the service continuity. In this study, two scenarios are proposed. The first concerns a load current sensor failure, where a material redundancy is adopted through the use of two observers, selected via a voting algorithm. The second deals to sense the system ability to maintain the service continuity in the worst case, where a grid black-out (grid-off) is planned. In this scenario, an additional functioning mode is added to reconfigure the control strategy. To prove the effectiveness of the proposed algorithms, the obtained experimental results with a given load profile are presented and commented.

关键词： fuzzy logic power generation control photovoltaic power systems fault tolerant control continuous systems discrete systems observers smart power grids operation modes fuzzy logic-based power management algorithm sub-system failure fault-tolerant control technique service continuity load current sensor failure system ability grid black-out smart PV-grid hybrid system smart PV-grid plant stationary alternative current load photovoltaic module single-phase grid smart permutation small scale system voting algorithm load profile observers functioning mode

来源：评论

学校读者我要写书评

暂无评论

Research on deep learning garbage classification system based on fusion of image classification and object detection classification

引用

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2023年第3期20卷 4741-4759页

作者： Yang, Zhongxue Bao, Yiqin Liu, Yuan Zhao, Qiang Zheng, Hao Bao, YuLu Nanjing XiaoZhuang Univ Sch Informat Engn Nanjing 211171 Peoples R China Jinling Univ Sci & Technol Business Sch Nanjing 211199 Peoples R China Schulich Sch Business Dept Informat Syst Toronto ON Canada Nanjing RuiHuaTeng Intellectual Property Co Ltd Nanjing 211175 Peoples R China

With the development of national economy, the output of waste is also increasing. People's living standards are constantly improving, and the problem of garbage pollution is increasingly serious, which has a great impact on the environment. Garbage classification and processing has become the focus of today. This topic studies the garbage classification system based on deep learning convolutional neural network, which integrates the garbage classification and recognition methods of image classification and object detection. First, the data sets and data labels used are made, and then the garbage classification data are trained and tested through ResNet and MobileNetV2 algorithms, Three algorithms of YOLOv5 family are used to train and test garbage object data. Finally, five research results of garbage classification are merged. Through consensus voting algorithm, the recognition rate of image classification is improved to 2%. Practice has proved that the recognition rate of garbage image classification has been increased to about 98%, and it has been transplanted to the raspberry pie microcomputer to achieve ideal results.

关键词： remote upgrade load balancing genetic algorithm power monitoring terminal voting algorithm

来源：评论

学校读者我要写书评

暂无评论

Building knowledge for substation-based decision support using rough sets

引用

IEEE TRANSACTIONS ON POWER DELIVERY 2007年第3期22卷 1372-1379页

作者： Hor, Ching-Lai Crossley, Peter A. Watson, Simon J. Univ Manchester Sch Elect & Elect Engn Elect Energy & Power Syst Grp Manchester M13 9PL Lancs England Univ Loughborough AMREL CREST Loughborough LE11 3TU Leics England

This paper describes a new technique based on rough sets to extract decision rules from large volumes of data captured by protection, control, and monitoring intelligent electronic devices. The methodology correctly identifies faults from large datasets and could be used to assist operators in their decision-making processes. Building knowledge for a fault diagnostic system is a time-consuming and costly process. The quality of a knowledge base can sometimes be hampered by a large number of superfluous decision-making rules that can lead to an unnecessarily large knowledge base system and inefficient or even detrimental rule maintenance. The methodology proposed cannot only induce decision rules efficiently but can also reduce the size of the knowledge base without causing loss of useful information. Results can be used by an expert system to generate supervisory automation and to support operators, for example, during an emergency situation. This methodology involves the generation of human-machine interface alarms. These can then be used for diagnosis of the type and cause of a fault event to give suggestions for network restoration and post-emergency repair. A Power Systems Computer Aided Design/Electromagnetic Transients including dc simulator has been used to investigate the effect of faults and switching actions on the protection and control equipment associated with a typical distribution network. The fundamental ideas of rough set theory are discussed, followed by a rule assessment method that is outlined using an illustrative example.

关键词： circuit breakers (CBs) discernibility fault section estimation relays rough sets rules discovery voting algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-Vehicle Tracking and Counting Framework in Average Daily Traffic Survey Using RT-DETR and ByteTrack

引用

IEEE ACCESS 2024年 12卷 121723-121737页

作者： Gladiensyah Bihanda, Yusuf Fatichah, Chastine Yuniarti, Anny Inst Teknol Sepuluh Nopember Dept Informat Surabaya 60117 Indonesia

The average daily traffic survey is essential for repairing and maintaining road sections. This method is generally conducted using a semi-manual approach that counts vehicles using CCTV. This approach is not effective or efficient because of the potential for human error. This paper have three contributions as follows. First, this paper proposes a framework by applying the RT-DETR architecture for vehicle detection and ByteTrack for vehicle tracking and counting in an average daily traffic survey. Second, this paper proposes a multi-vehicle voting algorithm to filter false identification of the same vehicle during the tracking process prior to vehicle counting. Third, to demonstrate the robustness of the proposed frameworks, we evaluated its performance using seven CCTV camera videos taken from diverse scenes during the day and night. RT-DETR Resnet 101, which is trained in an average daily traffic survey dataset, outperforms all object detection architectures with mAP@50 value of 0.992 and mAP@50-95 value of 0.891. RT-DETR Resnet101 also achieve best F1-score among all object detectors with value of 0.91. This framework using a combination of RT-DETR and ByteTrack also succeeded in counting vehicles with various video backgrounds, with an average counting accuracy value above 83% for all conditions. We compare the effect of using a multi-vehicle voting algorithm with and without showed that counting accuracy increased for each combination with an average increase value of 0.78. RT-DETR also has best performance compared to another object detection methods in detecting vehicles experiencing motion blur, especially in nighttime video scenes. In addition, ByteTrack roles in tracking vehicle objects show its robustness to handle occlusion and vehicle ID switch.

关键词： Surveys Road traffic Videos Cameras Tracking Prediction algorithms Traffic control Multi-vehicle tracking counting framework average daily traffic survey RT-DETR ByteTrack voting algorithm

来源：评论

学校读者我要写书评

暂无评论

Containing smartphone worm propagation with an influence maximization algorithm

引用

COMPUTER NETWORKS 2014年第PartB期74卷 103-113页

作者： Peng, Sancheng Wu, Min Wang, Guojun Yu, Shui Cent South Univ Sch Informat Sci & Engn Changsha 410083 Hunan Peoples R China Zhaoqing Univ Sch Comp Sci Zhaoqing 526061 Peoples R China Deakin Univ Sch Informat Technol Burwood Vic 3125 Australia

In recent years, wide attention has been drawn to the problem of containing worm propagation in smartphones. Unlike existing containment models for worm propagation, we study how to prevent worm propagation through the immunization of key nodes (e.g., the top k influential nodes). Thus, we propose a novel containment model based on an influence maximization algorithm. In this model, we introduce a social relation graph to evaluate the influence of nodes and an election mechanism to find the most influential nodes. Finally, this model provides a targeted immunization strategy to disable worm propagation by immunizing the top k influential nodes. The experimental results show that the model not only finds the most influential top k nodes quickly, but also effectively restrains and controls worm propagation. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Smartphones Worm containment Influence maximization Social relationship graph voting algorithm Immunization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Ensemble Undersampling-Boost: A novel learning framework for imbalanced data

引用

JOURNAL OF SYSTEMS AND SOFTWARE 2017年 132卷 272-282页

作者： Lu, Wei Li, Zhe Chu, Jinghui Tianjin Univ Sch Elect Informat Engn Tianjin 300072 Peoples R China

As one of the most challenging and attractive problems in the pattern recognition and machine intelligence field, imbalanced classification has received a large amount of research attention for many years. In binary classification tasks, one class usually tends to be underrepresented when it consists of far fewer patterns than the other class, which results in undesirable classification results, especially for the minority class. Several techniques, including resampling, boosting and cost-sensitive methods have been proposed to alleviate this problem. Recently, some ensemble methods that focus on combining individual techniques to obtain better performance have been observed to present better classification performance on the minority class. In this paper, we propose a novel ensemble framework called Adaptive Ensemble Undersampling-Boost for imbalanced learning. Our proposal combines the Ensemble of Undersampling (EUS) technique, Real Adaboost, cost-sensitive weight modification, and adaptive boundary decision strategy to build a hybrid algorithm. The superiority of our method over other state-of-the-art ensemble methods is demonstrated by experiments on 18 real world data sets with various data distributions and different imbalance ratios. Given the experimental results and further analysis, our proposal is proven to be a promising alternative that can be applied to various imbalanced classification domains. (C) 2017 Elsevier Inc. All rights reserved.

关键词： Classification Imbalanced data sets Real Adaboost voting algorithm Adaptive decision boundary Ensemble Undersampling

来源：评论

学校读者我要写书评

暂无评论

A LOOSELY COUPLED DISTRIBUTED SYSTEM FOR RELIABLY STORING DATA

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 1985年第5期11卷 446-454页

作者： BERNSTEIN, AJ Department of Computer Science State University of New York

A multiple copy data storage algorithm is presented that is designed specifically for reliability in a broadcast environment. The algorithm exploits redundancy and is meant for systems in which duplication cost is outweighed by the need for added reliability. The purpose of the algorithm is not to provide transaction concurrency control, but to handle the problem of the mutual consistency of the copies. It is a loosely coupled algorithm in that it is designed to function even though not all copies of the data need agree and not all processors may be functioning properly. voting is used to distinguish outdated or erroneous copies from correct ones. An important aspect of the proposed algorithm is that if no errors have occurred, the redundancy is largely transparent to the procedures that access the data, requiring no additional communication. Extra messages are needed when errors are detected in copies of stored information; this is done by combining the null message technique with the broadcast technology. A Markov analysis is performed to model the system's failure behavior.

关键词： voting algorithm Broadcast Network Markov Analysis Multiple Copy Database Redundancy Reliability Stable Storage

来源：评论

学校读者我要写书评

暂无评论

A voted based random forests algorithm for smart grid distribution network faults prediction

引用

ENTERPRISE INFORMATION SYSTEMS 2020年第4期14卷 496-514页

作者： Lin, Rongheng Pei, Zixiang Ye, Zezhou Wu, Budan Yang, Geng Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Zhejiang Univ Sch Mech Engn State Key Lab Fluid Power & Mechatron Syst Hangzhou Zhejiang Peoples R China

In this paper, we focus on fault prediction in the smart distribution network. modified version of voted random forest algorithm (VRF) is proposed for enhancing the predicting accuracy of the faults. We change the decision process by redesigning the voting algorithm by introducing multiple SVM models for voting model training. Based on the trained models, a simple NSGA algorithm is applied to find the best voting model. Results showed that the new algorithm could improve the accuracy and recall rate of the fault prediction, especially for the recall rate of the negative samples.

关键词： Random forests (RF) voting algorithm fault prediction smart distribution network

来源：评论

学校读者我要写书评

暂无评论

Vibration-Based Terrain Classification for Autonomous Vehicles

引用

Journal of Beijing Institute of Technology 2017年第4期26卷 440-448页

作者： Kai Zhao Mingming Dong Zhiguo Wang Yanxi Han Liang Gu School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China Beijing North Vehicle Group Corporation Beijing 100072 China

A method for terrain classification based on vibration response resulted from wheel-terrain interaction is presented. Four types of terrains including sine,gravel,cement and pebble were *** vibration data were collected by two single axis accelerometers and a triaxial seat pad accelerometer,and five data sources were utilized. The feature vectors were obtained by combining features extracted from amplitude domain,frequency domain,and time-frequency domain. The ReliefF algorithm was used to evaluate the importance of attributes; accordingly,the optimal feature subsets were selected. Further,the predicted class was determined by fusion of outputs provided by five data sources. Finally,a voting algorithm,wherein a class with the most frequent occurrence is the predicted class,was employed. In addition,four different classifiers,namely support vector machine,k-nearest neighbors,Nave Bayes,and decision tree,were used to perform the classification and to test the proposed method. The results have shown that performances of all classifiers are ***,the proposed method is proved to be effective.

关键词： ReliefF algorithm terrain classification vibration voting algorithm

来源：评论

学校读者我要写书评

暂无评论

A Redundant FPGA Based Controller for Subsea Blowout Preventer Stack

引用

JOURNAL OF COMPUTERS 2012年第10期7卷 2446-2453页

作者： Liu, Zengkai Liu, Yonghong Cai, Baoping Wang, Fei Chen, Zhili Tian, Xiaojie Wang, Yazhou China Univ Petr Coll Mech & Elect Qingdao Peoples R China

A redundant Field Programmable Gate Array (FPGA) based controller for subsea Blowout Preventer (BOP) is presented. Triple modular redundancy technique is used for architecture design, since high reliability is a necessary requirement for subsea BOP control system. A multiprocessor system is developed to enhance reliability of the processors and performance of the system. In addition, the shared memory method is applied to interchange information between the processors. One processor is responsible for communication, while the others run application programs. The proposed system has been implemented using three FPGA development boards, which are connected to each other through RS-232 serial ports. Besides, the voting algorithms for discrete input, analog input and discrete output are proposed. Functional simulation of the output voting is performed by using the Quartus II Simulator software. The results demonstrate that the proposed controller is able to tolerate faults, which means it has extremely high reliability.

关键词： FPGA TMR multiprocessor system voting algorithm subsea blowout preventer

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：