检索结果-内蒙古大学图书馆

An Improved Solov2 Based on Attention Mechanism and Weighted Loss Function for Electrical Equipment Instance Segmentation

引用

Computers, Materials & Continua 2024年第1期78卷 677-694页

作者： Junpeng Wu Zhenpeng Liu Xingfan Jiang Xinguang Tao Ye Zhang Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Ministry of EducationNortheast Electric Power UniversityJilin132012China School of Electrical Engineering Northeast Electric Power UniversityJilin132012China Baishan Power Supply Company State Grid Jilin Electric Power CoLtd.Jilin134300China

The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low *** of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation ***,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance *** results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 *** segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.

关键词： Deep learning electrical equipment attention mechanism weighted loss function

来源：评论

学校读者我要写书评

暂无评论

Constructing a Raman and surface-enhanced Raman scattering spectral reference library for fine-particle analysis

引用

Journal of Environmental Sciences 2022年第8期34卷 1-13页

作者： Hui Chen Fengkui Duan Kebin He Jingjing Du Zhenli Sun Suhua Wang Key Laboratory of Resources and Environmental System Optimization of Ministry of Education College of Environmental Science and EngineeringNorth China Electric Power UniversityBeijing 102206China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China State Key Laboratory of Environmental Chemistry and Ecotoxicology Research Center for Eco-Environmental SciencesChinese Academy of SciencesBeijing 100085China Guangdong Provincial Key Laboratory of Petrochemcial Pollution Processes and Control School of Environmental Science and EngineeringGuangdong University of Petrochemical TechnologyMaoming 525000 China

Fine particles associated with haze pollution threaten the health of over 400 million people in China. Owing to excellent non-destructive fingerprint recognition characteristics, Raman and surface-enhanced Raman scattering(SERS) are often used to analyze the composition of fine particles to determine their physical and chemical properties as well as reaction mechanisms. However, there is no comprehensive Raman spectral library of fine particles. Furthermore, various studies that used SERS for fine-particle composition analysis showed that the uniqueness of the SERS substrates and different excitation wavelengths can produce a different spectrum for the same fine-particle component. To overcome this limitation, we conducted SERS experiments with a portable Raman spectrometer using two common SERS substrates(silver(Ag) foil and gold nanoparticles(Au NPs)) and a 785 nm laser. Herein, we introduced three main particle component types(sulfate-nitrate-ammonium(SNA), organic material, and soot) with a total of 39 chemical substances. We scanned the solid Raman, liquid Raman, and SERS spectra of these substances and constructed a fine-particle reference library containing 105 spectra. Spectral results indicated that for soot and SNA, the differences in characteristic peaks mainly originated from the solid-liquid phase transition;Ag foil had little effect on this difference, while the Au NPs caused a significant red shift in the peak positions of polycyclic aromatic hydrocarbons. Moreover, with various characteristic peak positions in the three types of spectra, we could quickly and correctly distinguish substances. We hope that this spectral library will aid in the future identification of fine particles.

关键词： Raman Surface-enhanced Raman scattering(SERS) Spectral library Fine-particle

来源：评论

学校读者我要写书评

暂无评论

Surface-enhanced Raman scattering for mixing state characterization of individual fine particles during a haze episode in Beijing,China

引用

Journal of Environmental Sciences 2021年第6期33卷 216-224页

作者： Hui Chen Fengkui Duan Jingjing Du Ranhao Yin Lidan Zhu Jinlu Dong Kebin He Zhenli Sun Suhua Wang MOE Key Laboratory of Resources and Environmental System Optimization College of Environmental Science and EngineeringNorth China Electric Power UniversityBeijing 102206China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China State Key Laboratory of Environmental Chemistry and Ecotoxicology Research Center for Eco-Environmental SciencesChinese Academy of SciencesBeijing 100085China Guangdong Provincial Key Laboratory of Petrochemcial Pollution Processes and Control School of Environmental Science and EngineeringGuangdong University of Petrochemical TechnologyMaoming 525000China

The nondestructive characterization of the mixing state of individual fine particles using the traditional single particle analysis technique remains a *** this study,fine particles were collected during haze events under different pollution levels from September 5 to 112017 in Beijing,China.A nondestructive surface-enhanced Raman scattering(SERS)technique was employed to investigate the morphology,chemical composition,and mixing state of the multiple components in the individual fine *** image and SERS spectral analysis results show that soot existing in the form of opaque material was predominant during clear periods(PM_(2.5)≤75μg/m^(3)).During polluted periods(PM_(2.5)>75μg/m^(3)),opaque particles mixed with transparent particles(nitrates and sulfates)were generally *** classical least squares analysis further identified the relative abundances of the three major components of the single particles:soot(69.18%),nitrates(28.71%),and sulfates(2.11%).A negative correlation was observed between the abundance of soot and the mass concentration of PM_(2.5).Furthermore,mapping analysis revealed that on hazy days,PM_(2.5)existed as a core-shell structure with soot surrounded by nitrates and *** mixing state analysis method for individual PM_(2.5)particles provides information regarding chemical composition and haze formation mechanisms,and has the potential to facilitate the formulation of haze prevention and control policies.

关键词： PM_(2.5) Surface-enhanced Raman scattering Individual fine particle Nitrate Sulfate Soot

来源：评论

学校读者我要写书评

暂无评论

Integrated Distribution Management System:Architecture,Functions,and Application in China

引用

Journal of Modern power systems and Clean Energy 2022年第2期10卷 245-258页

作者： Wenchuan Wu Penghua Li Bin Wang Yingshang Liu Tao Xu Hongwei Du Yan He the State Key Laboratory of Power Systems Department of Electrical EngineeringTsinghua UniversityBeijing 100084China the Electric Power Control Center of China Southern Power Grid Corporation GuangzhouChina the National Electric Power Control Center of State Grid Corporation of China BeijingChina NARI Technology Co. Ltd.NanjingChina Beijing Guoke Hengtong Technology Co. Ltd.BeijingChina

As massive distributed energy resources(DERs)are integrated into distribution networks(DNs)and the distribution automation facilities are widely deployed,the DNs are evolving to active distribution networks(ADNs).This paper introduces the architecture and main function modules of an integrated distribution management system(IDMS)and its applica-tions in *** system consists of three subsystems,including the real-time operation and control system(OCS),outage management system(OMS),and operator training simulator(OTS).The OCS has a hierarchical architecture with three levels,including the local controller for DER clusters,the optimization of DNs incorporated with multi-clusters,and the coordina-tion operation of integrated transmission&distribution(T&D)*** OMS is developed based on the geographical information system(GIS)and coordinated with *** in the OTS,both the ADN and its host transmission network(TN)are simulated to make the simulation results more *** main functions of the three subsystems and their interaction data flows are described and some typical application scenarios are also presented.

关键词： Active distribution network(ADN) integrated distribution management system(IDMS) operation and control system(OCS) outage management system(OMS) operator training simulator(OTS) geographical information system(GIS).

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Evaluation of Distributed PV Grid-Connected Based on Combined Weighting Weights and TOPSIS-RSR Method

引用

Energy Engineering 2024年第3期121卷 703-728页

作者： Yue Yang Jiarui Zheng Long Cheng Yongnan Zhu Hao Wu Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Ministry of Education(Northeast Electric Power University)Jilin132012China Siping Suburban Power Supply Company State Grid Jilin Electric Power Co.Ltd.Siping136000China

To effectively quantify the impact of distributed photovoltaic(PV)access on the distribution network,this paper proposes a comprehensive evaluation method of distributed PV grid connection combining subjective and objective combination of assignment and technique for order preference by similarity to an ideal solution(TOPSIS)—rank sum ratio(RSR)(TOPSIS-RSR)*** on the traditional distribution network evaluation system,a comprehensive evaluation system has been *** fully considers the new development requirements of distributed PV access on the environmental friendliness and absorptive capacity of the distribution grid and comprehensively reflects the impact of distributed PV grid *** analytic hierarchy process(AHP)was used to determine the subjective weights of the primary indicators,and the Spearman consistency test was combined to determine the weights of the secondary indicators based on three objective assignment *** subjective and objective combination weights of each assessment indicator were calculated through the principle of minimum *** the distance between the indicators to be evaluated and the positive and negative ideal solutions,the relative closeness ranking,and qualitative binning by TOPSIS-RSR method to obtain the comprehensive evaluation results of different *** setting up different PV grid-connected scenarios and utilizing the IEEE33 node simulation algorithm,the correctness and effectiveness of the proposed subject-object combination assignment and integrated assessment method are verified.

关键词： Distributed PV grid-connected comprehensive evaluation evaluation indicator system combined subjective and objective empowerment TOPSIS-RSR method

来源：评论

学校读者我要写书评

暂无评论

Transient Voltage Stability Assessment Method based on gcForest

Transient Voltage Stability Assessment Method based on gcFor...

引用

2021 International Conference on Electrical, Electronics and Computing Technology, EECT 2021

作者： Zhiyuan, Sun Mingpo, L.I. Jie, Zhang Binjiang, Hu Guo, Qi Yihua, Zhu Guangxi Power Grid Electrical Power Research Institute China State Key Laboratory of HVDC Electric Power Research Institute CSG China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System China CSG Key Laboratory of Power System Simulation

Aiming at the fact that the traditional method cannot quickly and accurately judge the power system transient voltage stability, and the deep neural network method needs many sample data sets and has a large number of hyperparameters, a power system transient voltage stability assessment method based on deep forest (gcForest) is proposed. gcForest effectively extracts features through ensemble learning, multi-layer feature transformation, and dynamically adjusting the number of model layers. Finally, this method is applied to transient voltage stability assessment of an electrolytic aluminium load-intensive area in Guangxi power Grid. The results show that the method has high accuracy, the feasibility and effectiveness of this method are verified. This method can assist dispatchers to judge the transient voltage stability of the power grid. © Published under licence by IOP Publishing Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Application and Practice of Digital Twin Technology in Monitoring Status of power Equipment in Converter Valve Hall

Application and Practice of Digital Twin Technology in Monit...

引用

2023 International Conference on Intelligent Communication and Computer Engineering, ICICCE 2023

作者： Yongsheng, He Baojia, Deng Zongxiang, Lu Shiling, Zhang Liangjun, Dai State Grid Chongqing Electric Power Company Electric Power Research Institute China State Key Lab of Control and Simulation of Power Systems and Generation Equipment Deptartment of Electrical Engineering Tsinghua University China

ISBN: (纸本)9798350395617

The internal power equipment of ultrahigh voltage converter valve hall is numerous and complex in structure, involving the various information elements such as the temperature and vibration. Moreover, the gas inside ultra-high voltage converter bushing is SF6 gas. Under the current over-load condition of the converter bushing, SF6 gas will decompose. This article focuses on the SF6 gas equipment inside the ultrahigh pressure converter valve hall as the research object, and analyzes specific types and content of SF6 gas decomposition products. In order to effectively detect gas content in the digital twin model of the converter transformer bushing, the new portable SF6 gas chromatograph, laser detection technology and device for HF gas, and partial discharge detection technology research using the acoustic electric coupling method are carried out, providing the effective means for onsite detection of hidden faults in operating equipment. Research has shown the digital twin technology can effectively detect the absorption spectra of gases such as O2, H20, CO, CO2, CF4, SO2, H2S, SOF2, and SO2F2. On the other hand, through digital twin partial discharge detection technology, it is effectively found that the SO2 inside the UHV converter sleeve is 29μL/L, H2S is 4μL/L, CO is 36μL/L, HF=0, detected SO2 and H2S components, determined as the insulation heating defect. The research results of paper provide theoretical and data support for operation status monitoring of SF6 gas insulated power equipment inside the ultra-high voltage converter valve hall. © 2023 IEEE.

关键词： Sulfur hexafluoride

来源：评论

学校读者我要写书评

暂无评论

Multi-task learning and single-task learning joint multi-energy load forecasting of integrated energy systems considering meteorological variations

引用

Expert systems with Applications 2025年 288卷

作者： Nantian Huang Shicheng Ren Jianfei Liu Guowei Cai Liang Zhang Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education (Northeast Electric Power University) Jilin 132012 Jilin Province China School of Electrical Engineering Northeast Electric Power University Jilin 132012 Jilin Province China The Economic and Technical Research Institute of State Grid Inner Mongolia Eastern Electric Power Company Hohhot 010010 Inner Mongolia Province China

Accurate multi-energy load forecasting is pivotal for achieving supply–demand balance and enabling economic dispatch in Integrated energy systems (IES). However, prediction accuracy is significantly compromised by meteorological fluctuations, seasonal coupling variations, and multi-energy interactions affecting multi-energy loads. This study proposes a joint multi-energy load forecasting framework integrating meteorological variation rate features with multi task learning (MTL) and single task learning (STL). First, historical load variation rates and meteorological variation rates are calculated, with rapid maximal information coefficient (RapidMIC) employed to identify dominant meteorological variation rates influencing multi-load fluctuations. Subsequently, a weighted average of correlation analysis method quantifies both linear and nonlinear impacts of meteorological variation rates on load fluctuations, enabling precise screening of critical meteorological input features. Second, addressing potential accuracy degradation in MTL models caused by coupling strength disparities among multi-energy loads, a joint forecasting method based on MTL-STL is proposed to enhance prediction precision. Furthermore, a loss function optimization strategy combining homoscedastic uncertainty (HU) and dynamic weight averaging (DWA) achieves real-time weight allocation in MTL. Finally, validation through case studies on IES at Arizona state University (ASU) and an industrial park in Gansu Province, China demonstrates the model’s effectiveness and generalizability: Across all seasons, MAPE values for electricity, cool, and heating loads remain stable within 1.068%-3.022%, 1.877%-5.331%, and 1.697%-3.999% respectively.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Research on three-phase four-leg matrix converter based more electric aircraft wing ice protection system

Research on three-phase four-leg matrix converter based more...

引用

作者： Huang, Songtao Xu, Lie Guo, Yougui Li, Yongdong Deng, Wenlang School of Information and Engineering Xiangtan University Xiangtan China State Key Laboratory of Control and Simulation of Power Systems and Generation Equipments Tsinghua University Beijing China

In this study, a new three-phase four-leg matrix converter (TFMC) topology is proposed, and the three-dimensional space vector modulation (3DSVM) strategy is used to realise the output with the three-phase unbalanced load. Aiming at the situation that the icing area of the more electric aircraft on the wing is larger than the icing area in the belly, wing ice protection system is constructed by using the TFMC. Through the real-time detection of the heating element temperature and icing condition by the sensor installed in the wing and belly position, working temperature and three-phase output power of TFMC can be set reasonably. In order to save fuel consumption and reduce operating costs, the key point is to reduce the power transmission in belly position. Finally, simulation and experiment verify the correctness of the proposed 3DSVM strategy and realise the TFMC output with unbalanced three-phase load. © 2018 Institution of Engineering and Technology. All rights reserved.

关键词： Matrix converters

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Multi-Object Rearrangement

Large-Scale Multi-Object Rearrangement

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Huang, Eric Jia, Zhenzhong Mason, Matthew T. State Grid Liaoning Electric Power Co Ltd Shenyang China Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin China

ISBN: (纸本)9781538660263

This paper describes a new robotic tabletop rearrangement system, and presents experimental results. The tasks involve rearranging as many as 30 to 100 blocks, sometimes packed with a density of up to 40%. The high packing factor forces the system to push several objects at a time, making accurate simulation difficult, if not impossible. Nonetheless, the system achieves goals specifying the pose of every object, with an average precision of +/- 1 mm and +/- 2 degrees. The system searches through policy rollouts of simulated pushing actions, using an Iterated Local Search technique to escape local minima. In real world execution, the system executes just one action from a policy, then uses a vision system to update the estimated task state, and replans. The system accepts a fully general description of task goals, which means it can solve the singulation and separation problems addressed in prior work, but can also solve sorting problems and spell out words, among other things. The paper includes examples of several solved problems, statistical analysis of the system's behavior on different types of problems, and some discussion of limitations, insights, and future work.

关键词： Planning Task analysis Grasping Robots Annealing Trajectory Markov processes

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：