检索结果-内蒙古大学图书馆

5th International Conference on Computing and Big Data, ICCBD 2022

作者： Zhang, Yong Zhang, Jiaqing Zhang, Jianhua Xing, Weijie Xcmg Fire-fighting Safety Equipment Co. Ltd. Xuzhou China State Grid Anhui Electric Power Research Institute Anhui Province Key Laboratory of Electric Fire and Safety Protection Hefei China School of Information and Control Engineering China University of Mining and Technology Xuzhou China

ISBN: (纸本)9781665457163

Aiming at the low accuracy of flame detection in complex environment, a new flame detection method based on improved YOLOv3 and gray thermograph is proposed. For the insufficient thermograph of actual flame data sets, a temperature filling algorithm based on radial basis function is proposed. Based on the open data sets, the actual flame image and thermograph are added to build the initial flame data sets, which improves the model training efficiency and generalization performance. The obtained flame gray scale thermograph and R, G, B image are combined to form a four-channel data and input into the improved YOLOv3 network convolution network layer to obtain the multi-channel characteristics of the data. The experimental results on public and self-built data sets show that the algorithm combines gray thermal image to expand image data and improves the detection accuracy of flame recognition. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Flow-Appearance Fusion Defect Detection Method for Substation Equipment in Multi-Scene

A Flow-Appearance Fusion Defect Detection Method for Substat...

引用

Chinese Automation Congress (CAC)

作者： Qingwei Zhang Jing Wang Peng Wang Wenhao Zhou 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 Zhejiang University Hangzhou China

ISBN: (纸本)9781665426480

In the daily maintenance process of substation, the defect detection of substation equipment is a critical problem. This task is challenging considering of the variety of defects, the rarely sample of various defects and the complex environment. This paper presents a flow-appearance fusion defect detection method for substation equipment in multiple scenes, which contains a Siamese optical flow module and a defect location module. The Siamese optical flow module is a pretrained optical flow network, which is utilized to obtain forward and backward optical flow between the normal image and the detect image. The optical flow represents the common changing features of different types of defects in multiple scenes. The defect location module utilizes MI-darknet53 to realize the extraction and fusion of appearance and flow features. Then the extracted multiscale features are used to build the feature pyramid network (FPN), which combines semantic defect information in high level and geometric defect information in low level. Finally, FPN is utilized to predict object-level defect areas in three different scales. Experiments show that our proposed method has good reliability and superior performance in the defect detection for the dataset of multi-scene substation equipment.

关键词： Substations Automation Semantics Maintenance engineering Feature extraction Reliability Data mining

来源：评论

学校读者我要写书评

暂无评论

In-situ Monitoring of Maximum and Average Chip Junction Temperature within Multichip IGBT Power Modules Using Kelvin Emitter Voltage

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Yang, Jianxiong Ran, Li Che, Yanbo Du, Mingxing Tianjin University of Technology Tianjin Key Laboratory of Control Theory and Applications in Complicated System Tianjin300384 China Chongqing University State Key Laboratory of Power Transmission Equipment and System Security and New Technology School of Electrical Engineering Chongqing400044 China University of Warwick School of Engineering CoventryCV4 7AL United Kingdom Tianjin University Key Laboratory of Smart Grid of Ministry of Education School of Electrical and Information Engineering Tianjin300072 China

Parallel configurations of power chips within a multichip IGBT power module (M-IGBT-PM) are employed to meet the required current and power ratings. When the internal chips of an M-IGBT-PM experience uneven temperature distributions and package aging, it becomes challenging to determine the maximum and average temperatures of the chips within the module. This paper investigates the relationship between four transient thermal-sensitive electrical parameters (T-TSEPs) derived from the Kelvin emitter voltage and the chip junction temperature, while establishing relevant mathematical models. It compares the sensitivity and linearity of these four T-TSEPs, and also assesses the influence of external gate resistance, bus voltage, and load current on each of them. A key innovation in this paper is the proposal of a method for monitoring the maximum and average temperatures across the chips within the M-IGBT-PM, which is not influenced by the load current. The experimental results suggest that the temperature derived from the quasi-turn-on delay time is a good approximation of the maximum chip temperature, whereas the temperatures predicted by the other T-TSEPs are nearer to the average temperature. © 2025 IEEE.

关键词： Insulated gate bipolar transistors (IGBT)

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prognosis of Power Semiconductor Devices Based on On-state Resistance Time Series Data and Deep Learning

Remaining Useful Life Prognosis of Power Semiconductor Devic...

引用

2023 7th International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE)

作者： Xiaolong Zhang Lin Zheng Heng Tian Li Liu Qun Ma Huafeng Wang Chong Gao State Key Laboratory of Advanced Power Transmission Technology State Grid Smart Grid Research Institute Co. Ltd. Beijing China Beijing Kedong Power Control System Co. Ltd. Beijing China State Grid Electric Power Research Institute Co. Ltd. Nanjing China State Grid Zhoushan power supply company Zhoushan China

Power semiconductor devices are the essential core components of modern power electronic equipment. Predicting the remaining useful life (RUL) of power semiconductor devices can help formulate reasonable maintenance strategies for power electronic equipment, thereby improving the availability of energy conversion systems. This article proposes a deep learning method for predicting the RUL of power semiconductor devices, which uses on-state resistance as a critical state parameter. A long short-term memory (LSTM) neural network (NN) model and a convolutional neural network (CNN) model are used to predict the on-state resistance time series data trend. NN models can predict a short section of future data with past data input. The RUL of power semiconductor devices is estimated through curve fitting based on past and predictive data. The proposed method is validated using the power MOSFET accelerated aging dataset from NASA, and the validation results show that the performance of the proposed method is superior to that of existing methods, such as extended Kalman filtering (EKF) and particle filtering (PF).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Integration and Learning of Measurement Data in Active Distribution Power Networks for Load Flow Estimation Considering Incomplete Information

Deep Integration and Learning of Measurement Data in Active ...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Ruisheng Diao Aihua Zhou Ruiyuan Zeng Anqi Wang Xiaofeng Shen Jingde Shun Hua Gu State Key Laboratory of Clean Energy Utilization ZJU-UIUC Institute Zhejiang University Haining Zhejiang China State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute Co. LTD. Nanjing Jiangsu China ZJU-UIUC Institute Zhejiang University Haining China Qingpu Power Supply Company Stage Grid Shanghai Municipal Electric Power Company Shanghai China

To reach the goals of carbon peaking by 2030 and carbon neutrality by 2060 in China, a growing penetration of PV generation is integrated into the modern distribution power grid, causing challenges in operating the grid to meet security requirements due to the increased dynamics and stochastics. A deep neural network (DNN)-based method is proposed in this paper for estimating load flow solutions in active distribution power networks that typically suffer from incomplete measurements. Adaptive DNN models are trained from massive historical observations obtained from actual measurements or high-fidelity simulations, whose hyperparameters are tuned automatically. Comprehensive case studies are conducted on the IEEE 123-node feeder model with renewable generation considering various levels of missing information as inputs, which validate the effectiveness and robustness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Multi-Source Data Clustering and Analysis Method for AC/DC Hybrid Power grid Planning with Increased Complexity

An Intelligent Multi-Source Data Clustering and Analysis Met...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Tu Lan Aihua Zhou Ruisheng Diao Fangyuan Sun Ruiyuan Zeng Xiaofeng Shen Chenhong Huang Zhen Zheng ZJU-UIUC Institute Zhejiang University Haining Zhejiang China State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute Co. LTD. Nanjing Jiangsu China State Key Laboratory of Clean Energy Utilization ZJU-UIUC Institute Zhejiang University Haining Zhejiang China Qingpu Power Supply Company Stage Grid Shanghai Municipal Electric Power Company Shanghai China

In order to better analyze the response characteristics of an AC/DC hybrid power grid with increased complexity following various types of disturbances, this paper proposes an intelligent method for clustering dynamic responses of multi-source data obtained from actual measurements or high-fidelity simulators. Base cases for AC/DC hybrid power grid planning students are created first, and a list of high-impact contingencies is searched using a graph algorithm. Then, the electromechanical-electromagnetic hybrid simulation method is adopted to create multi-source simulation data in terms of dynamic voltage, frequency, etc. An unsupervised learning algorithm and cluster analysis are then conducted to extract key features of dynamic response characteristics of the AC/DC hybrid power grid and create specific cluster labels. Advanced analysis, e.g., fast evaluation of risks from multi-source steady-state data, can then be enabled for further analysis. The proposed approach's effectiveness is verified on the actual AC/DC power grid model in East China.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Developing Characteristics of Oil-immersed Transformer Internal Fault with Dignostic Method Using Convergence Patterns of Free Gas

Developing Characteristics of Oil-immersed Transformer Inter...

引用

Electrical Engineering (CIYCEE), IEEE China International Youth Conference on

作者： Yucheng Zhang Zhiguo Hao Yuping Zheng Shuyan Pan Boyu Li Zhongxin Xue Jinzhao Deng School of Electrical Engineering Xi’an Jiaotong University Xi’an China State Key Laboratory of Smart Grid Protection and Operation Control Nanjing China

ISBN: (纸本)9781665400657

Light gas protection only operates when gas within the transformer collection chamber reaches threshold volume. Such criterion failed to reflect transformer conditions accurately due to the lack of understanding for defect developing process and corresponding gas generation- convergence pattern, which has led to lower protection reliability and has caused several transformer explosions. To address current problem, an experimental tank with structure resembling that of a power transformer is set up, inside which the needle-plate oil-pressboard breakdown model is planted. Experimental results indicate that throughout fault development, voltage drops became more frequent until arcing occurs, so is HFCT signal; meanwhile gas generation rate increases through slight partial discharge, spark discharge and arcing stage, the collected gas volume corresponds with patterns above. The purpose of this study is to clarify the defect developing process and the gas generation-convergence pattern for oil-immersed transformer internal fault in guidance for a more reliable protection method.

关键词： Surface discharges Windings Oil insulation Discharges (electric) Reliability Sparks Plastics

来源：评论

学校读者我要写书评

暂无评论

New Intelligent Sensing Terminal System Architecture of Internet of Things

New Intelligent Sensing Terminal System Architecture of Inte...

引用

International Conference on Internet of Things, Communication and Intelligent Technology, IoTCIT 2022

作者： Zhou, Lidan Li, Jing Yao, Gang Wang, Hongyu Li, Jian Liu, Siyang Nie, Yongjie School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai Minhang District200240 China Wiscom System Co. LTD. Nanjing China State Key Laboratory of Power Transmission Equipment and System Security and New Technology Chongqing University Chongqing400044 China Electric Power Research Institute Yunnan Power Grid Co. Ltd. Yunnan Kunming650217 China Yunnan Key Laboratory of Green Energy Electric Power Measurement Digitalization Control and Protection Yunnan650217 China

ISBN: (纸本)9789819904150

In view of the fragmentation of the functions, forms and basic software and hardware of the existing IoT terminals, we propose an IoT intelligent sensing terminal system architecture, in which the intelligent sensing layer collects external data and information and transmits it to the computing fusion collaboration layer for data processing, fusion and task collaboration. The local application layer generates processing results and interacts with the cloud application layer through the communication layer. The new intelligent sensing terminal system of the IoT has an integrated local four-tier architecture, which can meet the needs of the large-scale development of the IoT. In addition, it can work uniformly under the control of the cloud, or complete the underlying tasks independently. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

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

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：