检索结果-南通市图书馆

High Voltage 2023年第2期8卷 368-379页

作者： Qianzhen Jing Jing Yan Yanxin Wang Xinyu Ye Jianhua Wang yingsan geng State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong UniversityXi'anChina

Convolutional neural networks(CNNs)have been widely used for gas-insulated switchgear(GIS)partial discharge(PD)pattern recognition due to their powerful feature extraction ***,there is commonly a scarcity of fault samples due to low insulation failure rate of GIS equipment,which degrades the diagnostic performance of these CNN networks when directly applied to small and unbalanced ***,we propose a novel auxiliary classifier generative adversarial network for GIS PD pattern recognition for small and unbalanced ***,we propose using synchrosqueezed wavelet transform to extract time-frequency characteristics of PD pulses and obtain a time-frequency image with high energy aggregation and timefrequency distribution ***,we propose an improved generative adversarial network with an auxiliary classier and self-attention mechanism,which can generate highquality PD samples for situations with few *** show that our proposed method can reach 95.75%recognition accuracy for small datasets,which is the highest among several comparable ***,the proposed method has excellent and stable recognition performance for various unbalanced datasets.

关键词： network pattern classifier

Vacuum Switching Technology for Future of Power Systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineering 2022年第6期8卷 164-177页

作者： Xiaofei Yao Jianhua Wang Shaogui Ai Zhiyuan Liu yingsan geng Zhiguo Hao State Key Laboratory of Electrical Insulation and Power Equipment Xi’an Jiaotong UniversityXi’an 710049China

Even though switching in vacuum is a technology with almost 100 years of history,its recent develop-ments are still changing the future of power transmission and distribution ***,current switch-ing in vacuum is an eco-friendly technology compared to switching in SF 6 gas,which is the strongest greenhouse gas according to the Kyoto ***,an eco-friendly natural medium,is promising for reducing the usage of SF 6 gas in current switching in transmission ***,switching in vacuum achieves faster current interruption than existing alternating current(AC)switching technolo-gies.A vacuum circuit breaker(VCB)that uses an electromagnetic repulsion actuator is able to achieve a theoretical limit of AC interruption,which can interrupt a short-circuit current in the first half-cycle of a fault current,compared to the more common three cycles for existing current switching *** can thus greatly enhance the transient stability of power networks in the presence of short-circuit faults,especially for ultra-and extra-high-voltage power transmission ***,based on fast vacuum switching technology,various brilliant applications emerge,which are benefiting the power *** include the applications in the fields of direct current(DC)circuit breakers(CBs),fault current lim-iting,power quality improvement,generator CBs,and so *** vacuum switching technology is promising for controlled switching technology in power systems because it has low variation in terms of opening and closing *** this controlled switching,vacuum switching technology may change the“gene”of power systems,by which power switching transients will become smoother.

关键词： Controlled switching Electromagnetic repulsion actuator Fast vacuum circuit breaker Fast vacuum switching technology Vacuum interrupter

GAN and CNN for imbalanced partial discharge pattern recognition in GIS

在线全文

学校读者我要写书评

暂无评论

High Voltage 2022年第3期7卷 452-460页

作者： Yanxin Wang Jing Yan Zhou Yang Qianzhen Jing Jianhua Wang yingsan geng State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong UniversityXi'anShaanxiChina School of Computer Science Xi'an Jiaotong UniversityXi'anShaanxiChina

The convolutional neural network(CNN)achieves excellent performance in pattern recognition owing to its powerful automatic feature extraction capability and outstanding classification ***,the actual samples obtained are unbalanced,and accurate diagnoses are difficult for the existing methods.A classification method for partial discharge(PD)pattern recognition in gas-insulated switchgear(GIS)that uses a generative adversarial network(GAN)and CNN on unbalanced samples is ***,a novel Wasserstein dual discriminator GAN is used to generate data to equalise the unbalanced ***,a decomposed hierarchical search space is used to automatically construct an optimal diagnostic ***,PD pattern recognition classification in GIS of the unbalanced samples is realised by the GAN and *** experimental results show that the GAN and CNN methods proposed in this study have a pattern recognition accuracy of 99.15%on unbalanced samples,which is significantly higher than that obtained by other ***,the method proposed in this study is more suitable for industrial applications.

关键词： network pattern CNN

Breakdown of shield gaps in vacuum interrupters

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Voltage 2021年第4期6卷 693-701页

作者： Weigang Feng Zhiyuan Liu Hui Ma yingsan geng Jianhua Wang Lalian Li Dongli Bi State Key Laboratory of Electrical Insulation and Power Equipment Xi’an Jiaotong UniversityXi’anChina Shaanxi Baoguang Vacuum Electric Device Co. LtdBaojiChina

The objective of this paper is to determine how the high-voltage discharging metal vapour deposited on the nearby ceramic inner surface influences the breakdowns of gaps between centre shield and end shield in vacuum *** types of shield materials were selected,namely copper and stainless *** end curvature radius of the shield was 3 *** distance between the shields could adjust manually from 4 to 8 *** distance between the shields and ceramic was 3.5 *** negative polarity standard lightning impulse voltage(12/50μs)was repeated for 900 operations based on an up-and-down *** experimental results illustrated that the metal deposition layer on the inner surface of the ceramic en-velope significantly influenced the breakdown voltage of the shield *** a shield gap distance of d?4 mm,the breakdown voltage of the shield gap increased from an initial lower voltage to the saturation voltage by approximately 200 ***,the breakdown voltage decreased to a lower voltage range during only 50 operations,and the breakdown voltage maintained at this lower voltage range until the end of 900 ***,as the shield gap distance increased from d?4 to 6 mm and 8 mm,the breakdown voltage also maintained at this lower voltage range.A metal deposition layer was formed on the inner surface of ceramic by repetitive application of the lightning impulse *** analyse the influence of the metal deposition layer,the electric field distributions were calculated for the original vacuum interrupter and the vacuum interrupter with the metal deposition layer on the ceramic inner *** simulation results suggested that the metal deposition layer took part in the breakdown path between the shield gaps and deteriorated the insulation performance.

关键词： ceramic vacuum operations

Effect of barrier thickness of Polytetrafluoroethylene on the Direct Current breakdown characteristics of liquid nitrogen

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Voltage 2022年第5期7卷 982-991页

作者： Bin Xiang Lei Gao Jiahui Zhang Qi Zhang Zhiyuan Liu yingsan geng Jianhua Wang Youping Tu Department of Electrical Engineering Xi'an Jiaotong UniversityXi'anChina Laboratory of Alternate Electrical Power System with Renewable Energy Source North China Electric Power UniversityBeijingChina

When high-temperature superconducting(HTS)tapes in high voltage DC HTS devices are quenched,amounts of thermal bubbles are generated in liquid nitrogen(LN_(2))that will reduce the insulation strength *** when resistive-type superconducting fault current limiters meet a short-circuit fault,the insulation strength of the LN_(2)decreased significantly due to the thermal bubbles and electrothermal *** insulating barriers can improve the insulation strength of the LN_(2).The objective of this study is to obtain the effect of barrier thickness on the DC dielectric breakdown characteristics of LN_(2).Insulating barrier Polytetrafluoroethylene with three different thicknesses were *** types of electrodes such as rod-plane,needle-plane,and planeplane were *** results showed that the barriers can increase the negative and positive breakdown voltage both with and without thermal bubbles in a slightly nonuniform field(SNF)and non-uniform field(NF).For the SNF,the DC breakdown voltage is higher when the barrier is *** effect of the barrier thickness in the NF is lower than that in the SNF *** the NF,the positive breakdown voltage is higher when the barrier is thicker.

关键词： barrier characteristics insulation

Study on the influencing factors to reduce the recovery time of superconducting tapes and coils for the DC superconducting fault current limiter applications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Voltage 2022年第3期7卷 483-495页

作者： Bin Xiang Wenqing Wang Hongxu Li Lei Gao Zhiyuan Liu yingsan geng Jianhua Wang Youping Tu Department of Electrical Engineering State Key Laboratory of Electrical Insulation and Power EquipmentXi'an Jiaotong UniversityXi'anChina State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijingChina

Superconducting fault current limiters(SFCLs)are important in improving the stability of electrical power ***,the existing resistive-type DC SFCL has a long re-covery time,which cannot meet the requirements of power system ***,it is necessary to investigate the methods of reducing recovery time of *** the simulations on superconducting tapes,there is a lack of investigation about the effects of design factors of superconducting tapes and coils such as material,thickness,coil radius,coil winding method on recovery *** objective of this study is to obtain the effects of material and geometric properties of superconducting tapes and coils on recovery characteristics and obtain methods to reduce the recovery *** recovery times under different conducting currents are also compared by simulations and exper-iments to verify simulation *** maximum error is below 40%and most of the cases have an error below 10%.Besides,by increasing tape thickness,the recovery time can be reduced by 22%.Tape materials and coil winding methods can be designed ac-cording to the auto-reclosure and current-limiting requirements of the power *** research provided directions for the design of superconducting tape and super-conducting coil for resistive-type DC SFCLs.

关键词： fault winding conducting

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于组件的P2P分布实时数据交换体系结构

计算机工程 2005年第17期31卷 100-101,107页

作者：徐宏王建华耿英三西安交通大学电气学院西安710049

提出并实现了一种基于组件/XML的P2P分布实时数据交换系统PeXChange,系统使用XML实现面向多接口的通用数据交换,通过多事件通道和主动发现失效结点实现系统负载均衡和容错处理,采用基于角色的访问控制机制以加强系统的安全性和可管理性... 详细信息

提出并实现了一种基于组件/XML的P2P分布实时数据交换系统PeXChange,系统使用XML实现面向多接口的通用数据交换,通过多事件通道和主动发现失效结点实现系统负载均衡和容错处理,采用基于角色的访问控制机制以加强系统的安全性和可管理性。PeXChange在设计和实现上采用组件的大粒度对象化设计范型,具有较好的可扩展性、安全性和容错性。广域网络环境下系统运行表明,PeXChange能够以对等模式提供高质量实时数据交换和共享,各Peer结点在异种数据模式映射、系统负载均衡与容错处理等方面能够满足企业级应用需求。

关键词： P2P 组件数据交换

低压断路器中电弧运动磁流体动力学模型的仿真研究

在线全文

学校读者我要写书评

暂无评论

西安交通大学学报 1999年第10期33卷 6-9页

作者：陈旭陈德桂耿英三西安交通大学西安710049

根据低压断路器开断时电弧起弧的物理过程，建立了以磁流体动力学（ＭＨＤ）为基础的电弧模型．根据气流场，结合热场、磁场与电流分布，对低压断路器的电弧运动过程进行了数值模拟研究，经对磁场在电弧初始运动阶段对电弧运动的影响... 详细信息

根据低压断路器开断时电弧起弧的物理过程，建立了以磁流体动力学（ＭＨＤ）为基础的电弧模型．根据气流场，结合热场、磁场与电流分布，对低压断路器的电弧运动过程进行了数值模拟研究，经对磁场在电弧初始运动阶段对电弧运动的影响进行数值分析，结果表明：电弧在磁场中运动得更快，并且可以更有效地被冷却．

关键词：低压断路器电弧仿真磁流体动力学断路器

An Advanced Adaptive Backstepping Control Method for STATCOM

在线全文

学校读者我要写书评

暂无评论

An Advanced Adaptive Backstepping Control Method for STATCOM

基于特征融合度量学习的高压断路器机械故障诊断

第26届中国控制与决策会议

作者： Zhang Chao Zhang Aimin Zhang Hang Wang nan Ren zhigang Huang jingjing geng yingsan School of Electrical Engineering Xi'an Jiaotong University School of Electronics and Information Engineering Xi'an Jiaotong University

ISBN: (纸本)9781479937097

An innovative approach to high robustness and anti-interference performance for static synchronous compensator（STATCOM） control systems is proposed to address the problems including parameter uncertainties and external disturbances which often deteriorate system performance significantly. Improvement is made in three aspects. Firstly, the adaptive backstepping control has been adopted to design the state-feedback control law and improve the transient stability of the STATCOM recursively. Secondly, In order to reduce high degree of coupling between the states and the estimation error, the adaptive law and the state-feedback control law are designed separately by using the immersion and invariance adaptive（I＆I adaptive） control. Thirdly, the dissipation inequality is constructed between energy storage function and an energy supply function in each step. This can get a certificate theoretically that the energy is dissipated and the robustness of the control system. Moreover, the compared simulations show that more rapid speed response and stronger robustness can be obtained by the proposed approach than other advanced algorithms under the same conditions.

关键词： Static Synchronous Compensator(STATCOM) adaptive backstepping I&I adaptive dissipation inequality

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

仪器仪表学报 2022年第9期43卷 98-105页

作者：王艳新闫静王建华耿英三西安交通大学电力设备电气绝缘国家重点实验室西安710049

数据驱动的深度学习方法在高压断路器机械故障诊断中取得了一定的成效,然而这些方法实现优异性能的前提是可获取海量训练样本,在现场数据匮乏场景下其诊断性能明显下降。为此,提出了一种新颖的特征融合度量学习模型用于现场小样本高压... 详细信息

数据驱动的深度学习方法在高压断路器机械故障诊断中取得了一定的成效,然而这些方法实现优异性能的前提是可获取海量训练样本,在现场数据匮乏场景下其诊断性能明显下降。为此,提出了一种新颖的特征融合度量学习模型用于现场小样本高压断路器机械故障诊断。首先构建了特征融合卷积神经网络,有效提升了可鉴别特征提取能力。然后以K近邻算法作为度量学习器实现小样本数据的匹配和分类。最后通过改进中心损失进一步提升特征表示的分辨能力,并通过情景训练从实验室构建的大样本集中学习可迁移知识。实验结果表明,本文方法在每类支持集样本数为5时便可达到94.58%的诊断精度,相对于卷积神经网络提升了63.71%。同时,得益于情景训练方式本文方法有效避免了非平衡样本的问题。

关键词：特征融合卷积神经网络度量学习故障诊断小样本高压断路器