检索结果-内蒙古大学图书馆

Thermal fault diagnosis of power equipment through improved instance segmentation and deep neural network temperature fitting

引用

Dianji yu Kongzhi Xuebao/electric Machines and Control 2025年第2期29卷 116-125页

作者： Zheng, Hanbo Hu, Junhao Li, Jinheng Liang, Yanshen Huang, Junjie Guangxi Key Laboratory of Power System Optimization and Energy Technology Guangxi University Nanning530004 China Electric Power Research Institute State Grid Hubei Electric Power Co. Ltd. Wuhan430077 China

The malfunctioning equipment displays anomalous temperatures at the fault location, posing a significant risk to the security and stability of the power system. To evaluate the thermal status of power equipment, a method for diagnosing thermal faults was proposed. This approach was implemented through instance segmentation and temperature fitting. Firstly, a dataset was constructed based on the infrared images of power equipment collected at the substation, and an improved instance segmentation model was developed. The enhanced model achieves a 3. 6% improvement in the mean average precision of masks and a 2. 5% improvement in the boxes, while the model’s floating point operation is maintained at only 12. 1 GFLOPs. Secondly, a method for fitting the temperature values of the equipment based on deep neural networks was proposed. This method achieved better fitting accuracy than other methods, with an R-square of 0. 999 7 and a fitting temperature deviation of approximately 3% . Finally, a method for automatically diagnosing thermal abnormalities was proposed in accordance with the current industrial guidelines. This algorithm was founded upon kernel density estimation for the obtainment of temperature parameters. The experimental findings indicate that our algorithm precisely detects and is alert to the fault breaker, thus increasing operational safety. © 2025 Editorial Department of electric Machines and Control. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Attention-based CNN-GRU Model for Resident Load Short-term Forecast 5

An Attention-based CNN-GRU Model for Resident Load Short-ter...

引用

5th IEEE Conference on energy Internet and energy system Integration, EI2 2021

作者： Wei, Shangfu Bai, Xiaoqing Key Laboratory of Guangxi Electric Power System Optimization and Energy-saving Technology Guangxi University Nanning China

ISBN: (纸本)9781665434256

Under the background of electricity market, accurate short-term forecast of residential load can effectively strengthen demand side management. However, the randomness and uncertainty of residential electricity consumption increase the difficulty of prediction. The traditional prediction models are facing with some problems that it is difficult to effectively extract high-dimensional features and important information is easy to lose when the length of the time series is too large. Based on these, the paper established an Attention-based CNN-GRU model for resident load short-term forecast. In this model, CNN plays a role in extracting the features of historical power consumption data, GRU neural network combined with Attention mechanism is used to model these extracted features dynamically. Real data of individual household electricity consumption is taken as an example, and simulation experiments are carried out in three scenarios of univariate single step, multivariate single step and multivariate multi-step prediction respectively. The results of the experiment demonstrate that the proposed model achieves reasonable accuracy and robustness. © 2021 IEEE

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on OPF control of three-phase four-wire low-voltage distribution network considering uncertainty

arXiv

引用

arXiv 2024年

作者： Wang, Rui Bai, Xiaoqing Huang, Shengquan Wei, Shoupu Guangxi Key Laboratory of Power System Optimization and Energy‑Saving Technology College of Electrical Engineering Guangxi University Nanning530004 China

As power systems become more complex and uncertain, low-voltage distribution networks face numerous challenges, including three-phase imbalances caused by asymmetrical loads and distributed energy resources. We propose a robust stochastic optimization (RSO) based optimal power flow (OPF) control method for three-phase, four-wire low-voltage distribution networks that consider uncertainty to address these issues. Using historical data and deep learning classification methods, the proposed method simulates optimal system behaviour without requiring communication infrastructure. The simulation results verify that the proposed method effectively controls the voltage and current amplitude while minimizing the operational cost and three-phase imbalance within acceptable limits. The proposed method shows promise for managing uncertainties and optimizing performance in low-voltage distribution networks. © 2024, CC BY.

关键词： energy resources

来源：评论

学校读者我要写书评

暂无评论

Small Signal Stability Assessment of power system Based on Sade-ELM Algorithm 5

Small Signal Stability Assessment of Power System Based on S...

引用

5th IEEE Conference on energy Internet and energy system Integration, EI2 2021

作者： Yang, Yude Zhang, Xiu Wen, Quan Key Laboratory of Power System Optimization and Energy Saving Technology Guangxi University School of Electric Power Engineering Guangxi University Nanning China

ISBN: (纸本)9781665434256

Along with the increasing scales of power system, the traditional numerical method to calculate the damping ratio of system to evaluate the small signal stability cannot meet the requirements of real-time analysis. Therefore, we propose a small signal stability assessment method for power system based on Extreme Learning Machine (ELM) optimized by Differential Evolution Algorithm with Strategy-Adaptation (SaDE). The node power, generator power and branch power are taken as inputs of the model in this method. Meanwhile, the minimum damping ratio of the system is taken as the output, and fits input data and output data. The results of 3-machine 9-node and 10-machine 39-node systems show that the method can estimate the minimum damping ratio of the system after off-line training of historical data without considering the change of control parameters. Compared with the prediction results of Back Propagation (BP) and ELM models, SaDE-ELM has the lowest error, the highest prediction accuracy and the strongest generalization ability. © 2021 IEEE

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Short-Term Reactive Load Forecasting Based on a Hybrid Machine Learning Model

Short-Term Reactive Load Forecasting Based on a Hybrid Machi...

引用

2022 power system and Green energy Conference, PSGEC 2022

作者： Qi, Le Chen, Mingyuan Song, Jifeng Zhang, Minyu Zheng, Wenbin Shang, Qinghua Power Dispatching Control Center of Guangxi Power Grid Co. Ltd Nanning China Guangxi University Key Laboratory of Guangxi Electric Power System Optimization and Energy-Savig Technology Nanning China

ISBN: (数字)9781665499934

ISBN: (纸本)9781665499934

With the improvement of people's living standards and the access to new energy sources such as rooftop photovoltaics, the variety of electricity consumption on the customer side has increased dramatically, placing high demands on the reactive power compensation configuration, regulation, and control capabilities at all levels of the distribution network. Predicting reactive loads directly impacts the quality of power supply and is also an integral part of reactive power optimization in the grid. With the popularity of smart energy measurement devices, large-scale historical reactive load data is uploaded to the dispatch control system. This paper proposes a hybrid reactive load prediction model based on a machine learning framework. Appropriate error parameters are selected, and the model is compared with a traditional time series prediction model to verify that the model can achieve better prediction results. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Direct Vehicle-to-Vehicle energy Trading with Online Charging-Hailings: A Novel Business Model for Emergency Charging of electric Vehicles

SSRN

引用

SSRN 2024年

作者： Wang, Rui Jiang, Aihua Tian, Junyang Wang, Yifeng Guangxi Key Laboratory of Power System Optimization and Energy Saving Technology Guangxi University Guangxi Province Nanning530004 China Power Dispatching Control Center of Guangxi Power Grid Guangxi Province Nanning530023 China

Amid the escalating number of electric Vehicles (EVs), the current infrastructure of public charging stations is ill-equipped to handle the mass charging demands of these vehicles, leading to a pressing issue of range anxiety that necessitates immediate resolution within the EV industry. This paper integrates the operating model of Online Ride-Hailings with the direct Vehicle-to-Vehicle (V2V) energy trading model, introducing a novel business model with Online Charging-Hailings (OCHs). This model positions OCHs as the principal energy providers and targets EV users as the primary service recipients aiming to furnish EV users with emergency energy supply services through V2V interactions. The architecture underpinning this model is a cloud-edge-end collaborative framework designed for the operational service platform. It employs the Gale-Shapley matching game algorithm and takes user satisfaction into account to establish an order-taking mechanism. Furthermore, the model utilizes a Vehicle-to-Grid technology and a Demand Response strategy to develop a charging optimization mechanism tailored for OCHs. Under this framework, EV users can simply send a charging request via their mobile devices to reserve V2V charging services. Simulation outcomes suggest that the proposed business model effectively facilitates emergency charging for EVs, mitigates range anxiety for users, lowers charging costs for OCHs, and enhances operator profitability, making it suitable for large-scale applications. © 2024, The Authors. All rights reserved.

关键词： Emergency services

来源：评论

学校读者我要写书评

暂无评论

In situ reconstruction induced oxygen-deficient multiphase Cu based species hybridized with Ni single atoms as tandem platform for CO_(2) electroreduction

引用

Nano Research 2024年第5期17卷 3888-3894页

作者： Juzhe Liu Yuheng Wang Pengpeng Mo Feng Yang Kaiqi Jiang Zhixiang Cheng Yuxuan Liu Zhiyi Sun Zheng Liu Yimei Zhang Wenxing Chen The Key Laboratory of Resources and Environmental System Optimization Ministry of EducationCollege of Environmental Science and EngineeringNorth China Electric Power UniversityBeijing 102206China Energy&Catalysis Center School of Materials Science and EngineeringBeijing Institute of TechnologyBeijing 100081China State Key Laboratory of Environmental Criteria and Risk Assessment Chinese Research Academy of Environmental SciencesBeijing 100012China SEPA Key Laboratory of Eco-Industry Chinese Research Academy of Environmental SciencesBeijing 100012China

Tandem catalysis,capable of decoupling individual steps,provides a feasible way to build a high-efficiency CO_(2) electro-conversion system for multicarbons(C_(2+)).The construction of electrocatalytic materials is one of focusing ***,we fabricated a single atom involved multivalent oxide-derived Cu composite material and found it inclined to reconstruct into oxygen-deficient multiphase Cu based species hybridized with monatomic Ni on N doped C *** this prototype,rapid CO generation and C-C coupling are successively achieved on NiN4 sites and surface amorphized Cu species with defects,resembling a micro-production *** this way,the in situ formed tandem catalyst exhibited a high Faradaic efficiency(FE)of~78%for C_(2+)products along with satisfactory durability over 50 ***,the reconstruction-induced amorphous layer with abundant asymmetric sites should be favorable to improve the ethanol selectivity(FE:63%),which is about 10 times higher than that of the non-tandem Cu-based contrast *** work offers a new approach for manipulating tandem catalyst systems towards enhancing C_(2+)products.

关键词： tandem catalysis single atom reconstruction amorphous CO_(2)reduction reaction

来源：评论

学校读者我要写书评

暂无评论

Electrochemical extraction of strontium from molten salts using reactive zincand aluminum electrodes

引用

International Journal of Minerals,Metallurgy and Materials 2025年第4期32卷 892-901页

作者： Yongcheng Zhang Taiqi Yin Lei Zhang Xiaochen Zhang Tao Bo Xiaoli Tan Mei Li Wei Han Zhejiang Key Laboratory of Data-Driven High-Safety Energy Materials and Applications Ningbo Institute of Materials Technology and EngineeringChinese Academy of SciencesNingbo 315201China College of Materials Science and Chemical Engineering Harbin Engineering UniversityHarbin 150001China MOE Key Laboratory of Resources and Environmental System Optimization College of Environmental Science and EngineeringNorth China Electric Power UniversityBeijing 102206China Qianwan Institute of CNITECH Ningbo 315336China

Herein, the electrochemical behaviors of Sr on inert W electrode and reactive Zn/Al electrodes were systematically investig-ated in LiCl–KCl–SrCl2molten salts at 773 K using various electrochemical methods. The chemical reaction potentials of Li and Sr on re-active Zn/Al electrodes were determined. We observed that Sr could be extracted by decreasing the activity of the deposited metal Sr onthe reactive electrode, although the standard reduction potential of Sr(II)/Sr was more negative than that of Li(I)/Li. The electrochemicalextraction products of Sr on reactive Zn and Al electrodes were Zn13Sr and Al4Sr, respectively, with no codeposition of Li *** on the density functional theory calculations, both Zn13Sr and Al4Sr were identified as stable intermetallic compounds with Zn-/Al-rich phases. In LiCl–KCl molten salt containing 3wt% SrCl2, the coulombic efficiency of Sr in the Zn electrode was ~54%. The depolar-ization values for Sr on Zn and Al electrodes were 0.864 and 0.485 V, respectively, exhibiting a stronger chemical interaction between Znand Sr than between Al and Sr. This study suggests that using reactive electrodes can facilitate extraction of Sr accumulated while elec-trorefining molten salts, thereby enabling the purification and reuse of the salt and decreasing the volume of the nuclear waste.

关键词： strontium reductive extraction molten salt depolarization effect reactive electrode

来源：评论

学校读者我要写书评

暂无评论

Non-contact gaseous microplasma electrode as anode for electrodeposition of metal and metal alloy in molten salt

引用

Chinese Chemical Letters 2024年第4期35卷 166-169页

作者： Junhan Luo Qi Qing Liqin Huang Zhe Wang Shuang Liu Jing Chen Yuexiang Lu Institute of Nuclear and New Energy Technology Tsinghua UniversityBeijing 100084China The MOE Key Laboratory of Resources and Environmental System Optimization College of Environmental Science and EngineeringNorth China Electric Power UniversityBeijing 102206China Nuclear Research Institute for Future Technology and Policy Seoul National UniversitySeoul 08826Republic of Korea

Microplasma based on glow discharge could act as a non-contact gaseous electrode and has attracted much attention in both fundamental research and application. Herein, with microplasma as the anode,the electrodeposition process of a series of metal and metal alloys in molten salt has been systemically studied. Four metal cations with different valence states, silver(Ag~+), nickel(Ni^(2+)), copper(Cu^(2+)), and iron(Fe^(3+)), could all be reduced on the solid cathode with high current efficiency and the corresponding metal products were of high purity. The electrodeposition of aluminum-lanthanum(Al-Ln) alloy on the aluminum cathode was also successfully carried out with microplasma as the anode, and the same alloy was obtained by using the conventional anode electrode. These results indicated that microplasma anode based on non-contact direct-current(DC) glow discharge is a promising electrode to be applied in molten salt electrolysis.

关键词： Microplasma Anode Molten salt Electrodeposition Al-Ln alloy

来源：评论

学校读者我要写书评

暂无评论

Optimal Topology Design of Remote Low Voltage AC Distribution systems

Optimal Topology Design of Remote Low Voltage AC Distributio...

引用

IEEE Green energy and systems Conference (IGESC)

作者： Ratha Taing Xiaocong Li Guangxi Key Laboratory of Power System Optimization and Energy Technology Guangxi University Nanning China

This paper addresses the AC low voltage distribution system by proposing the optimal topology in a remote village for 25 years of planning. The minimum distance algorithm is employed to find the nearest loads to electric poles with the given coordinates. Then, those loads and the closest electric pole are assigned as a cluster. Next, the minimum-spanning-tree (MST) is used to define the shortest connection of clusters. After that, phase ABC repeated is used to balance the three phases system. Thereafter, the load flow is performed with respect to the constraint. Thus, the conductor size is defined. Finally, the cost of the distribution system (CAPEX, OPEX, and TOTEX) is calculated. The result shows that the proposed algorithm has energy losses that are lower than the overall energy losses of the system.

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：