检索结果-内蒙古大学图书馆

Hierarchical annotation method for metal corrosion detection of power equipment

Journal of Southeast University(English Edition) 2021年第4期37卷 350-355页

作者： Zhang Baili Cao YongZhang Pei Zhang Zhao He Yina Zhong Mingjun School of Computer Science and Engineering Southeast UniversityNanjing 211189China State Key Laboratory of Smart Grid Protection and Control State Grid Electric Power Research InstituteNanjing 211106China NARI Group Corporation Nanjing 211106China Department of Computing Science University of AberdeenAberdeen AB243UEUK

To solve the ambiguity and uncertainty in the labeling process of power equipment corrosion datasets,a novel hierarchical annotation method(HAM)is ***,large boxes are used to label a large area covering the range of corrosion,provided that the area is visually continuous and adjacent to corrosion that cannot be clearly ***,in each labeling box established in the first step,regions with distinct corrosion and relative independence are labeled to form a second layer of nested ***,a series of comparative experiments are conducted with other common annotation methods to validate the effectiveness of *** experimental results show that,with the help of HAM,the recall of YOLOv5 increases from 50.79%to 59.41%;the recall of Faster R-CNN+VGG16 increases from 66.50%to 78.94%;the recall of Faster R-CNN+Res101 increases from 78.32%to 84.61%.Therefore,HAM can effectively improve the detection ability of mainstream models in detecting metal corrosion.

关键词： deep learning Faster R-CNN YOLOv5 object detection hierarchical annotation

来源：评论

学校读者我要写书评

暂无评论

Waveform Design for MIMO-OFDM Based Dual-functional Radar and Communication Systems

Waveform Design for MIMO-OFDM Based Dual-functional Radar an...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Tianchen Liu Liang Wu Zaichen Zhang Jian Dang Bingcheng Zhu Yin Yao Liu Dongsheng National Mobile Communications Research Laboratory Southeast University Nanjing P.R.China Purple Mountain Laboratory Nanjing P.R.China State Key Laboratory of Smart Grid Protection and Control NARI Group Co. Ltd Nanjing China

ISBN: (纸本)9781665450867

Dual-functional radar-communications (DFRC) technique has attracted substantial attention. The radiation power of radar system is usually very high, and it is usually not afforded by the communication receiver. To solve this problem, this paper proposes a waveform design scheme for the DFRC system based on multiple-input and multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) techniques. In the proposed scheme, a convex optimization problem is firstly formulated to derive the optimal covariance matrix of the transmit signals. Based on the optimal covariance matrix, a subcarrier and power allocation scheme is proposed to meet the power requirement of the DFRC system. Simulation results show that compared with the traditional OFDM based DFRC scheme, the proposed scheme can achieve almost the same target detection performance, and a much higher achievable data rate. Meanwhile, the proposed scheme can guarantee that the power radiated in the communication direction satisfies the communication power requirement.

关键词： Wireless communication OFDM Simulation Radar Receivers Object detection Convex functions

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Indoor Localization System in the NLOS Environment Based on Deep Learning and CSI Images

An Intelligent Indoor Localization System in the NLOS Enviro...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Lu Sun Liang Wu Zaichen Zhang Jian Dang Yulong Shen Gefeng Huang Liliang Ding National Mobile Communications Research Laboratory Southeast University Nanjing P.R.China Purple Mountain Laboratory Nanjing P.R.China State Key Laboratory of Smart Grid Protection and Control NARI Group Co. Ltd Nanjing China

ISBN: (纸本)9781665450867

With the rapid development of the smart service industry, indoor high-precision localization technology in the non-line-of-sight (NLOS) environment has attracted great interest. Fingerprint-based indoor localization has been widely employed due to its low hardware cost and high localization accuracy. In this paper, we propose an indoor intelligent localization system based on a 2-dimensional deep convolutional neural network (2D DCNN) and image fingerprints extracted from the channel state information (CSI). Simulation results show that the proposed localization system can achieve a high localization accuracy in the NLOS environment.

关键词： Location awareness Deep learning Wireless communication Simulation Signal processing algorithms Fingerprint recognition Signal processing

来源：评论

学校读者我要写书评

暂无评论

Thermochemical Energy Storage by Calcium Looping Process that Integrates Co2 power Cycle and H2o Steam power Cycle

SSRN

引用

SSRN 2022年

作者： Luo, Cong Xu, Yongqing Lu, Chuangao Wang, Guang Yan, Xiaopei Gao, Ge Lu, Bowen Wu, Fan Zhang, Liqi State Key Laboratory of Coal Combustion School of Energy and Power Engineering Huazhong University of Science and Technology Wuhan430074 China State Environment Protection Key Laboratory of Environmental Monitoring Quality Control China National Environmental Monitoring Centre Beijing100012 China State Grid Hebei Electric Power Research Institute Shijiazhuang050021 China

Effects of different CaO-based raw materials, and various organic acid modification on the conversion of CaO heat carriers in close-loop calcium looping process coupled thermochemical energy storage(CaLP-TCES) system are investigated. Besides, a novel CaLP-TCES system that integrates CO2 cycle and H2O steam cycle to make full use of the energy in the system was proposed. Natural CaO-based heat carriers underwent drastically deactivation over the CaLP-TCES cycles. Compared with other natural materials, limestone presented the best cyclic carbonation conversion, which retained 14.2% of conversion rate, while glycine modification doubled the conversion rate of it. The efficiency of the CaLP-TCES system presented "S" type growth with the increase of carbonation conversion and carbonation temperature, while it showed a parabolic growth with the increase of pressure ratio. In addition, the global system efficiencies in the fullday time mode are always ~72% higher than that in daytime mode. Hence, the glycine-limestone would be a promising heat carrier for the CaLP-TCES system, and CaLP-TCES in fullday time mode is more applicable for the concentrated solar power. 850 ℃ might be a good option for carbonation process, and the higher carbonation conversion rate and pressure ratio would be more benefit for the global system efficiency. © 2022, The Authors. All rights reserved.

关键词： Carbonation

来源：评论

学校读者我要写书评

暂无评论

Reverse Impact of Capacity Markets for a Renewable-Dominated power System

SSRN

引用

SSRN 2024年

作者： Tao, Junyi Li, Ran Chen, Sijie Qu, Hui Xiang, Yue Key Laboratory of Control of Power Transmission and Conversion Ministry of Education Shanghai Non-Carbon Energy Conversion and Utilization Institute Shanghai Jiao Tong University Shanghai200240 China College of Smart Energy Shanghai Jiao Tong University Shanghai200240 China State Grid Shanghai Municipal Electric Power Company Shanghai200122 China College of Electrical Engineering Sichuan University Chengdu610065 China

Many deregulated electricity markets worldwide have adopted capacity remuneration mechanisms (CRMs) to ensure capacity adequacy. Although these mechanisms have served many countries well in the last two decades, they may be unable to serve a low-carbon power system with high penetration of variable renewable energy (VRE). This paper investigates the impact of CRMs on generation risk under different VRE penetrations. We argue that state-of-the-art CRMs like reliability options (ROs), can only reduce the financial risks for renewables when the VRE penetration stays low. It will reversely amplify renewables’ risks and hinder their growth as their penetration increases. The reason is that in a renewable-dominated power system, scarcity hours are triggered not only by demand peaks but also by VRE troughs, in which case renewables have to pay the penalty of non-delivery. We modelled stylized long-term equilibrium using the UK data to quantify this effect. Our research finds that compared with the optimized benchmark, existing CRMs like scarcity pricing (SP) and ROs are unable to lead to the optimal low-carbon generation mix, but for different reasons. The SP mechanism invests sufficient VRE but lacks incentives for controllable devices like energy storage. Meanwhile, the ROs mechanism hinders the investment in VRE but encourages the investment of storages to reduce the scarcity hours. © 2024, The Authors. All rights reserved.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Energy Storage Planning and Economic Dispatch of Microgrid Considering power to Gas 12

Energy Storage Planning and Economic Dispatch of Microgrid C...

引用

12th IEEE PES Asia-Pacific power and Energy Engineering Conference, APPEEC 2020

作者： Gu, Jiaqi Mei, Fei Lu, Jixiang Lu, Jinjun Yang, Bo Hohai University College of Energy and Electrical Enginering Nanjing China Nari Group Corporation State Key Laboratory of Smart Grid Protection and Control Nanjing China China Electric Power Research Institute Nanjing China

ISBN: (纸本)9781728157481

New energy has been vigorously promoted for its advantages such as cleanliness, large reserves and renewability. Recently, power-to-gas (P2G) technology has provided a new idea for energy conversion, which helps to improve energy efficiency. In view of the current high penetration rate of photovoltaics, the impact of three measures with regard to energy conversion, energy storage configuration and demandside response on the economics of the microgrid and the optimal scheduling of the microgrid are explored. Firstly, a microgrid scheduling model with P2G device is built;Secondly, a bi-level planning model for the economic cost of the microgrid scheduling is presented. The upper layer will be based on absolutely accommodation of photovoltaics as the prerequisite to conFigure the optimal energy storage capacity;Then lower layer performs optimized scheduling under the upper model to ensure the economy of the microgrid. Finally, a comparison example is used to analyze the optimal energy storage capacity in different scenarios and an optimized scheduling scheme is given. © 2020 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

A Flow-Guided Anomaly Detection Method For Substation Equipment in Changing Scenarios

A Flow-Guided Anomaly Detection Method For Substation Equipm...

引用

Chinese Automation Congress (CAC)

作者： Qingwei Zhang Jing Wang Peng Wang Wenhao Zhou Yingxuan Li Chunhui Zhao State Key Laboratory of Smart Grid Protection and Control NARI Technology Development Company Limited Nanjing China Stale Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China

ISBN: (纸本)9781665426480

The anomaly detection for substation equipment is of great significance to maintain the safe operation of substations. With the development of deep learning, many anomaly detection methods based on deep convolutional neural networks (CNN) have been proposed. However, the challenge lies in the diversity of the environment and the variety of anomaly types in the substation. This paper proposes a Flow- Guided Anomaly Detection Method, which contains a data augmentation module and a flow-guided feature fusion module. The data augmentation module utilizes CycleGAN to transfer the style of the images to adapt to changing scenarios, such as different illumination and season conditions. The flow-guided feature fusion module extracts the optical flow between the test image and the template image by a pre-trained FlowNet, which represents the change information between the image pair and is universal for different anomaly types. Then the appearance information and change information of the image are aggregated to obtain the fused feature, which contains more semantic information. Finally, the fused feature is utilized to accurately detect a wider range of abnormal types. Experiments show that our proposed method has superior performance in anomaly detection for substation equipment and is more robust to changing scenarios.

关键词： Deep learning Adaptation models Substations Fuses Semantics Lighting Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Maximum Capacity Assessment for Multi-paralleled grid-connected Inverters using Global-Admittance based Harmonic Stability Analysis

Maximum Capacity Assessment for Multi-paralleled Grid-connec...

引用

Sustainable power and Energy Conference (iSPEC)

作者： Ming Yang Fusuo Liu Yu Wang Wu Cao School of Electrical Engineering Southeast University Nanjing China State Key Laboratory of Smart Grid Protection and Control Nari Group Corporation Nanjing China

ISBN: (纸本)9781665414401

With the increasing demand for the renewable energy, the stability of the multi-paralleled grid-connected inverters is the important factor for evaluation the capacity of the inverters connected to power grid. In this paper the maximum capacity assessment for multi-paralleled grid-connected inverters using global-admittance based harmonic stability analysis is proposed. The stability analysis method with global admittance has clear physical concept and is convenient for real-time analysis and calculation. The global admittance method is illustrated first. The inverters are sorted by the capacity. The inverters sequence can be divided into two groups based on the stable critical point obtained by the global admittance method. The group with large capacity is taken as a unit. The stability of the combinations formed by this unit and other inverters in the other group is analyzed further. So the maximum capacity of the grid-connected inverters can be assessed. The application example is used to illustrate and verify the proposed method in this paper.

关键词： Renewable energy sources Systems operation Stability criteria power system stability Harmonic analysis Inverters power grids

来源：评论

学校读者我要写书评

暂无评论

Design of real-time message synchronization cross smart grid dispatching system 4

Design of real-time message synchronization cross smart grid...

引用

4th IEEE Conference on Energy Internet and Energy System Integration, EI2 2020

作者： Xu, Chunlei Liu, Tong Lei, Baolong Peng, Hui State Grid Jiangsu Electric Power Co. Ltd. Nanjing China NARI Technology Co. Ltd. Xi'an China NARI Technology Co. Ltd. State Key Laboratory of Smart Grid Protection and Control Nanjing China

ISBN: (纸本)9781728196060

In the integrated operation mode of the smart grid dispatching and control system, there is a large amount of real-time data such as important alarms and manual operations that need to be shared between systems. How to synchronize these real-time data across systems with high reliability and performance becomes a problem to be solved. This paper studies the application scenarios of cross-system message synchronization and proposes a scheme based on redundant dual networks, including hardware and software architecture. The key technologies and important functions were implemented, reliability and throughput verifications were performed, and the expected results were achieved. © 2020 IEEE.

关键词： smart power grids

来源：评论

学校读者我要写书评

暂无评论

DC fault ride-through for wind power integration via MMC-HVDC based on precise control of energy storage configured inside wind farm

DC fault ride-through for wind power integration via MMC-HVD...

引用

Renewable power Generation and Future power Systems Conference 2023 (RPG 2023 UK)

作者： Y. Sun Y. Guo F. Fan J. Fan G. Li Z. Wang X. Wu Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education (Northeast Electric Power University) Jilin People's Republic of China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin People's Republic of China Department of Electronic and Electrical Engineering University of Strathclyde Glasgow UK State Grid Smart Grid Research Institute Beijing People's Republic of China

The modular multilevel converter-based high voltage direct current (MMC-HVDC) overhead lines transmission scheme is the preferred option for wind power integration, though it is susceptible to DC faults. To ensure the connection of a wind farm (WF) to the grid during DC faults, this paper proposes a coordinated control strategy for DC fault ride-through (FRT) based on the energy storage system configured inside the WF for wind power integration through a bipolar MMC-HVDC. In the case of an instantaneous DC fault, the non-fault pole is regulated to operate at full power state to maximise wind power transmission. The exceedance of available wind power outputs over the transmission capacity of the non-fault pole is then accurately allocated to the internal energy storage units (ESUs) of wind generators (WGs) in order to ensure the power balance of the system and reduce the state of charge variance of ESUs as soon as possible. In order to reduce the energy capacities of ESUs required to store the excessive wind power in the event of a permanent DC fault, the method of step-by-step removing WGs is adopted to ensure the system power remaining balanced when the internal ESUs of the disconnected WGs are out of operation. The model is developed and carried out on the PSCAD/EMTDC simulation platform to verify the effectiveness of the proposed control strategies.

关键词：

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：