检索结果-内蒙古大学图书馆

Edge detection in Wind Turbine Power System based DFIG Using Fault detection and Isolation FDI

IFAC-PapersOnLine 2018年第24期51卷 674-679页

作者： Boufertella, Ahmed Chafouk, Houcine Boudour, Mohamed Chibah, Arezki Centre de Développement des Energies Renouvelables Algiers16340 Algeria Normandy University UNIROUEN ESIGELEC IRSEEM Rouen76000 France Laboratory of electrical and industrial systems LSEI U.S.T.H.B Algiers Algeria

The interest for the renewable energy has increased in the past decades, and every country have at less one renewable energy installation either for testing or for residential applications. These installations are under constant monitoring because of the intermittency of the principal source for the energy production (wind, sun radiation…). In this paper, we expose the Page-Hinkley test for the detection of a change in current and DC link in a wind power conversion system. © 2018

关键词： Fault detection Asynchronous generators Edge detection Electric power generation Statistical methods Turbogenerators Wind power Wind turbines detection algorithm DFIG Fault detection and isolation Power conversion systems Renewable energies Renewable energy installations Residential application Wind turbine power

来源：评论

学校读者我要写书评

暂无评论

Real-time detection of Steel Strip Surface Defects Based on Improved YOLO detection Network

引用

IFAC-PapersOnLine 2018年第21期51卷 76-81页

作者： Li, Jiangyun Su, Zhenfeng Geng, Jiahui Yin, Yixin Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education School of Automation & Electrical Engineering University of Science and Technology Beijing Beijing100083 China School of Automation & Electrical Engineering University of Science and Technology Beijing Beijing100083 China

The surface defects of steel strip have diverse and complex features, and surface defects caused by different production lines tend to have different characteristics. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. Aiming at detecting surface defects of steel strip, we established a dataset of six types of surface defects on cold-rolled steel strip and augmented it in order to reduce over-fitting. We improved the You Only Look Once (YOLO) network and made it all convolutional. Our improved network, which consists of 27 convolution layers, provides an end-to-end solution for the surface defects detection of steel strip. We evaluated the six types of defects with our network and reached performance of 97.55% mAP and 95.86% recall rate. Besides, our network achieves 99% detection rate with speed of 83 FPS, which provides methodological support for real-time surface defects detection of steel strip. It can also predict the location and size information of defect regions, which is of great significance for evaluating the quality of an entire steel strip production line. © 2018

关键词： Surface defects Cold rolling Convolution Metal cladding Neural networks Signal detection Steel sheet Strip metal Surface properties Convolutional neural network Defect detection detection algorithm detection networks End to end solutions Generalization performance Real time detection Steel strip

来源：评论

学校读者我要写书评

暂无评论

detection of Parametric Roll Resonance using Bayesian Discrete-Frequency Model Selection ⁎

引用

IFAC-PapersOnLine 2018年第29期51卷 444-449页

作者： Kennedy, Justin M. Ford, Jason J. Perez, Tristan Valentinis, Francis Electrical Eng. & Comp. Sc Queensland University of Technology Brisbane Australia Institute for Future Environments Queensland University of Technology Brisbane Australia Defence Science and Technology Group Australian Department of Defence Australia

This paper explores the use of two discrete-frequency models and a probabilistic Bayesian model selection procedure to detect the inception of parametric resonance in ships. We exploit knowledge of the coupling between roll and pitch due to the restoring forces arising from the shape of the hull to propose a single and a double discrete-frequency model. These models are then used within a Bayesian framework to compute the posterior distribution of the frequencies and amplitudes of the two models and this information is used for model selection. The latter is based on the computation of the probability that each one of the models is correct given the data analysed within a past window of samples. The algorithm is tested with data from a scale-model experiment for both regular and irregular sea states. The results indicate the proposed detector is effective in accusing the inception of parametric resonance. © 2018

关键词： Frequency estimation Bayesian networks Inference engines Ocean currents Parametric devices Resonance Bayesian inference Bayesian model selection detection algorithm Discrete frequencies Parametric rolls Posterior distributions Scale model experiment Statistical inference

来源：评论

学校读者我要写书评

暂无评论

Statistical Approach to detection of Attacks for Stochastic Cyber-Physical Systems

引用

IFAC-PapersOnLine 2018年第25期51卷 178-183页

作者： Marelli, Damián Sui, Tianju Fu, Minyue School of Automation Guandong University of Technology China French-Argentinean International Center for Information and Systems Sciences National Scientific and Technical Research Council Argentina Department of Control Science and Engineering Dalian University of Technology China School of Electrical Engineering and Computer Science University of Newcastle Australia

We study the problem of detecting an attack on a stochastic cyber-physical system. We start by proposing a detection criterion based on checking the statistics of the Kalman prediction error. To show the importance of the proposed criterion, we study certain attacking schemes which can be effectively detected by this criterion, but not by checking simpler conditions based on commonly used statistics. We then use the proposed criterion to derive a detection algorithm. This algorithm is based on a statistical confidence test, giving a confidence level for detecting an attack. We present simulation results to illustrate the performance of this algorithm. © 2018

关键词： Computer crime Cyber Physical System Embedded systems Error statistics Linear systems Statistics Stochastic systems Testing Attack detection detection algorithm detection of attacks Integrity attacks Statistical approach Statistical confidence Statistical hypothesis testing System security

来源：评论

学校读者我要写书评

暂无评论

detection of hydrated dust storms on Modis images in western and southwestern Iran

引用

NATURAL HAZARDS 2023年第2期117卷 1273-1289页

作者： Rostami, Dana Lashkari, Hassan Mohammadi, Zainab Shahid Beheshti Univ SBU Fac Earth Sci Dept Phys Geog Tehran Iran

Dust storms have many direct and indirect effects on the environment, climate and air quality. In recent years, dust storms in the western and southwestern of Iran have increased significantly and had destructive effects on the residents of this area. The aim of this study is to develop a multi-spectral algorithm for detecting hydrated dust storms on MODIS images in western and southwestern of Iran. A multi-spectral algorithm was developed using a combination of visible and thermal bands of the MODIS sensor to detect hydrated dust. The studied dust storms events are based on the precipitation at synoptic stations in western and southwestern Iran during synoptic code 06 weather conditions. Based on the spectral and statistical analysis, the brightness temperature difference index of bands 31 and 32 (with a threshold greater than zero) was chosen for the algorithm along with the brightness temperature difference index of the bands 20 and 31 (with a threshold greater than 17) and the logarithm of reflectance bands 1 and 4 (with a threshold greater than - 1.8). A multispectral algorithm was also designed utilizing the above information. The results of the multi-spectral algorithm were validated with MODIS true color images and MODIS optical depth. Validation results revealed that the multi-spectral algorithm is suitable for monitoring hydrated dust in the study area. Results revealed that the multi-spectral algorithm is suitable for monitoring hydrated dust in the study area. Therefore, this method can be used to monitor and predict hydrated dust in this area to reduce potential risks.

关键词： Hydrated dust MODIS detection algorithm Remote sensing

来源：评论

学校读者我要写书评

暂无评论

detection of Quasiperiodic Textures with the Use of Two-Dimensional Power Spectrum Characteristics

引用

OPTOELECTRONICS INSTRUMENTATION AND DATA PROCESSING 2015年第2期51卷 103-109页

作者： Gruzman, I. S. Petrova, K. Yu. Novosibirsk State Tech Univ Pr Karla Marksa 20 Novosibirsk 630073 Russia Branch Samsung Elect Co Ltd Co Moscow 127018 Russia

An algorithm for detecting quasiperiodic textures is proposed, which is based on specific features of two-dimensional spectra obtained by using the discrete Fourier transform. The power spectra of the fragments are analyzed independently of each other, which provides the computational effectiveness of the detection algorithm. Examples demonstrating the use of the detection algorithm in the problem of image segmentation into two texture classes (periodic and nonperiodic) are presented. It is shown that the algorithm stably operates with significant deformations in the lattice of periodic textures.

关键词： detection algorithm quasiperiodic texture power spectrum Bravais lattice texture element

来源：评论

学校读者我要写书评

暂无评论

A detection Method of WLAN Security Mechanisms Based on MAC Frame Resolution

引用

Wuhan University Journal of Natural Sciences 2017年第2期22卷 93-102页

作者： LI June YUAN Kai ZHOU Liang HAN Lifang LI Ling WANG Zhihao LIU Yinbin HUANG Wenbin Key Laboratory of Aerospace Information Security and Trusted Computing of Ministry of Education Wuhan 430072HubeiChina School of Computer Wuhan UniversityWuhan 430072HubeiChina School of Electrical Engineering Wuhan UniversityWuhan 430072HubeiChina China Electric Power Research Institute Beijing 100192China

Security mechanism detection is not only an important content of vulnerabilities evaluation but also the foundation of key strength test for wireless local area network （WLAN）. This paper analyzes the specifications of WLAN security mechanisms and points out the defects in design of security mechanisms detection algorithm based on the standards. By capturing and analyzing a large number of Beacon frames from different vendor＇s access points （APs）, we summarize the relevant fields and information elements in a Beacon frame, and present their values or status when an AP is set to every specific security mechanism. A detection algorithm of WLAN security mechanisms is proposed based on the experimental study result and the pseudo code of a reference implementation for the algorithm is designed. The validity of the algorithm is illustrated by examples, which shows it can detect every WLAN security mechanism accurately.

关键词： IEEE 802.11 security mechanism detection algorithm MAC frame resolution vulnerabilities evaluation

来源：评论

学校读者我要写书评

暂无评论

Software-Assisted detection Methods for Secondary ESD Discharge During IEC 61000-4-2 Testing

引用

IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY 2018年第4期60卷 1129-1136页

作者： Marathe, Shubhankar Maghlakelidze, Giorgi Rezaei, Hossein Pommerenke, David Hertz, Mike Missouri Univ Sci & Technol EMC Lab Rolla MO 65401 USA Teledyne LeCroy New York NY 10977 USA

When an electrostatic discharge (ESD) event reaches a nongrounded metallic part within a product, the voltage of this metal with respect to ground will increase. If the isolation to the ground is insufficient, a secondary ESD event can occur. As secondary ESD often leads to system upset or damage, and to poorly reproducible results, it is important to detect the occurrence of secondary ESD. If the discharge current is monitored using an oscilloscope, the test equipment may miss the secondary discharge waveform. This is because the time delay between the primary and secondary discharge events can vary between nanoseconds to milliseconds. Present oscilloscopes do not offer functionality to autodetect a secondary discharge event. The goal of this study is to analyze different types of secondary discharge events acquired with various measurement setups and identify waveform parameters for software-assisted detection methods. A learning sequence is proposed for identifying secondary ESD events starting from low ESD gun test voltages. The data are analyzed with respect to the waveform parameters such as the vertical threshold of the rising edge, the dI/dt of the current waveform, and total charge delivered, which enable automatic detection of secondary ESD while monitoring the discharge waveform at the ESD gun tip.

关键词： Current clamp detection algorithm electrostatic discharge (ESD) oscilloscope secondary discharge sequence mode acquisition

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5s Network for Multi-scale safety Helmet detection 11

Improved YOLOv5s Network for Multi-scale safety Helmet Detec...

引用

11th International Conference on Communications, Circuits and Systems (ICCCAS)

作者： Zhao, Lin Zhang, Dalong Liu, Yifa Guo, Junli Shi, Zhanhao Zhengzhou Univ Inst Cyberspace Secur Zhengzhou Peoples R China Shandong Agr & Engn Univ Inst Informat Sci & Engn Jinan Peoples R China

ISBN: (纸本)9781665469890

A safety helmet detection model has been developed based on the original YOLOv5 network model, which addresses the problems of low accuracy and poor robustness for small targets in complex natural environments. Firstly, we add the layer to detect small targets, resulting in the shallow detection scale, which makes the model better able to detect small objects. Secondly, introducing the transformer self-attention module in the backbone network, which can extract global features with rich semantic information, improves the detection performance. Thirdly, The Ghost module demands fewer parameters and less computational complexity for features to be generated, reducing the pressure to learn model parameters. Finally, the loss function EIoU Loss is applied to improve the detection accuracy and accelerate the convergence of the model. Experimental results show that the average accuracy means (MAP), accuracy rates (P), and recall rates (R) of the improved algorithm are increased by 1.2%, 0.4%, and 0.2%, respectively while reducing the model size, which proves that the algorithm is more effective than the original algorithm at detecting safety helmets.

关键词： safety helmet small targets YOLOv5 algorithm detection algorithm

来源：评论

学校读者我要写书评

暂无评论

detection of Defects in Laser Powder Deposition (LPD) Components by Pulsed Laser Transient Thermography

Detection of Defects in Laser Powder Deposition (LPD) Compon...

引用

Conference on Thermosense - Thermal Infrared Applications XXXV

作者： Santospirito, S. P. Slyk, Kamil Luo, Bin Lopatka, Rafal Gilmour, Oliver Rudlin, John Kingston Comp Consultancy Ltd 28-30 Worship St London EC2A 2AH England Polkom Badania Spzoo Tarasy Business Ctr Lumen PL-00120 Warsaw Poland Warsaw Univ Technol Inst Control & Ind Elect PL-00661 Warsaw Poland TWI Ltd Cambridge CB21 6AL England

ISBN: (纸本)9780819494962

detection of defects in Laser Powder Deposition (LPD) produced components has been achieved by laser thermography. An automatic in-process NDT defect detection software system has been developed for the analysis of laser thermography to automatically detect, reliably measure and then sentence defects in individual beads of LPD components. A deposition path profile definition has been introduced so all laser powder deposition beads can be modeled, and the inspection system has been developed to automatically generate an optimized inspection plan in which sampling images follow the deposition track, and automatically control and communicate with robot-arms, the source laser and cameras to implement image acquisition. algorithms were developed so that the defect sizes can be correctly evaluated and these have been confirmed using test samples. Individual inspection images can also be stitched together for a single bead, a layer of beads or multiple layers of beads so that defects can be mapped through the additive process. A mathematical model was built up to analyze and evaluate the movement of heat throughout the inspection bead. Inspection processes were developed and positional and temporal gradient algorithms have been used to measure the flaw sizes. Defect analysis is then performed to determine if the defect(s) can be further classified (crack, lack of fusion, porosity) and the sentencing engine then compares the most significant defect or group of defects against the acceptance criteria - independent of human decisions. Testing on manufactured defects from the EC funded INTRAPID project has successful detected and correctly sentenced all samples.

关键词： laser thermography defect detection Laser Powder Deposition (LPD) additive processes automation defect quantification process control software detection algorithm

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：