检索结果-内蒙古大学图书馆

Adaptive Fault Detection Scheme Using an Optimized Self-healing Ensemble Machine Learning Algorithm

CSEE Journal of power and Energy systems 2022年第4期8卷 1145-1156页

作者： Levent Yavuz Ahmet Soran AhmetÖnen Xiangjun Li S.M.Muyeen Electrical and Computer Engineering Department in Abdullah Gül University Kayseri 38080Turkey Department of Electrical and Computer Engineering College of EngineeringSultan Qaboos UniversityAl-KhoudMuscat123Oman Department of Electrical Engineering Qatar UniversityDoha 2713Qatar State Key Laboratory of Control and Operation of Renewable Energy and Storage Systems China Electric Power Rescarch InstituteBeijing 100192China

This paper proposes a new cost-efficient,adaptive,and self-healing algorithm in real time that detects faults in a short period with high accuracy,even in the situations when it is difficult to *** than using traditional machine learning(ML)algorithms or hybrid signal processing techniques,a new framework based on an optimization enabled weighted ensemble method is developed that combines essential ML *** the proposed method,the system will select and compound appropriate ML algorithms based on Particle Swarm Optimization(PSO)*** this purpose,power system failures are simulated by using the PSCA D-Python *** of the salient features of this study is that the proposed solution works on real-time raw data without using any pre-computational techniques or pre-stored ***,the proposed technique will be able to work on different systems,topologies,or data *** proposed fault detection technique is validated by using PSCAD-Python co-simulation on a modified and standard IEEE-14 and standard IEEE-39 bus considering network faults which are difficult to detect.

关键词： Decision tree(DT) ensemble machine learning algorithm fault detection islanding operation k-Nearest Neighbor(kNN) linear discriminant analysis(LDA) logistic regression(LR) Naive Bayes(NB) self-healing algorithm

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Performance and Vibration Analysis of a Special-shaped External-rotor Machine 18

Electromagnetic Performance and Vibration Analysis of a Spec...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Dong, Ziwei Yan, Liang Lu, Zhang Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Beihang University Science and Technology on Aircraft Control Laboratory Beijing100191 China Tianmushan Laboratory Xixi Octagon City Yuhang District Hangzhou310023 China Beihang University Ningbo Institute of Technology Ningbo315800 China Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Hangzhou China

ISBN: (纸本)9798350312201

Permanent magnet synchronous machines have advantages such as small size, light weight, high efficiency, etc. It is more and more widely used in robots, electromagnetic propulsion, electric vehicles and so on. High power density and high torque density are urgent need for those applications. The electromagnetic design of machines mostly adopt multi-pole magnet patterns to reduce the stator yoke size. It helps to decrease the mass of the machine with the same power and improve the torque density. As the number of poles grows larger, the frequency and the core loss of per unit volume will also increase with the same speed, which can aggravate the heat problem of the machine. It is easy to generate the low-order vibration with high flux density. Therefore, the performance of a special-shaped external-rotor machine and comparisons with the traditional machine are analyzed in this paper. Numerical simulation is conduced to validated that the special-shaped magnet pattern can reduce the torque ripple, improve the torque output and power density. From the two-dimensional Fourier analysis of the radial electromagnetic force, it is found that the low-order amplitude of the special-shaped machine is greatly reduced, so the vibration can be avoided. Subsequently, the vibration simulation is carried out to indicate that the magnet pattern can satisfy low level in vibration and noise of the machine. © 2023 IEEE.

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

Location and capacity of distributed photovoltaic generation connected to distribution network based on multi-objective genetic algorithm 5

Location and capacity of distributed photovoltaic generation...

引用

5th IEEE Advanced Information Management, Communicates, Electronic and Automation control Conference, IMCEC 2022

作者： Qing, Song Xie, Tuo Bai, Qingjun Li, Pai Institute of Water Resources and Hydro-Electric Engineering Xi'An University of Technology Xi'an710048 China China Electric Power Research Institute State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems Beijing102401 China

ISBN: (纸本)9781665479677

In order to further improve the ecological environment in desert areas and actively respond to the development of the 'dual carbon' policy, numerous distributed photovoltaics have been connected to the distribution network in recent years. Network loss caused a greater impact. For the location and capacity planning of distributed photovoltaic access to the distribution network, this paper proposes a distributed photovoltaic location and capacity model that considers investment costs, distribution network losses, voltage stability, and environmental protection costs. The improved multi-objective genetic algorithm is used to solve the optimization model, which is verified by example simulation. After the optimized configuration, the power supply quality and network loss of the distribution network are significantly improved, which verifies the feasibility of the model. This research provides a certain reference and reference for the location and capacity determination of the distribution network with distributed photovoltaics. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

The Correlation Mechanism that Micro-Structure Parameters of ZnO Varistor to the Macroscopic Electrical Characteristics

The Correlation Mechanism that Micro-Structure Parameters of...

引用

International Conference on Electrical Materials and power Equipment (ICEMPE)

作者： Pengfei Meng Jingke Guo Long Zhao Wenhao Lu Zheng Liu Shan Li Kai Zhou Jun Hu College of Electrical Engineering Sichuan University Chengdu China State Grid Linyi power supply company STATE GRID Corporatio of China Linyi China High Voltage Technology Department Extra High Voltage Power Transmission Company of CSG Guangzhou China State Key Laboratory of Intense Pulsed Radiatio Simulation and Effect Northwest Institute of Nuclear Technology Xi’an China State Key Laboratory of Control and Simulation of Power System and Generation Equipment Tsinghua University Beijing China

As the core part of metal oxide arresters, ZnO varistor plays an important part in suppressing the overvoltage of power systems. With the development of UHV technology, the residual voltage and energy capacity of ZnO varistors have put forward higher requirements. The research is carried out from the perspective of material calculation, studied the correlation mechanism between micro-structure parameters and various macroscopic electrical characteristics of ZnO varistor based on Voronoi network. And the microstructure parameters such as grain size and size inhomogeneity were calculated and studied. The study simplified the optimization problem with multiple variates and objectives, into the one with two categories of variates and two categories of objectives. And then proposed specific strategies. The research provides important theoretical basis for improving the performance of ZnO varistors, and witch is of great significance for the design and manufacture of high-performance lightning arresters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Short-Term Wind power Forecasting for Multiple Farms with Alternating Temporal and Graph Convolutional Networks

Short-Term Wind Power Forecasting for Multiple Farms with Al...

引用

Electrical Engineering and Green Energy (CEEGE), International Conference on

作者： Guoqing Li Jianfeng Che Dagui Liu State Grid Xinjiang Electric Power Corporation Urumqi PR China State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems China Electric Power Research Institute Beijing PR China

Accurate wind power forecasting (WPF) is very important for stable and reliable power grid integration. Existing WPF approaches make predictions based on numerical weather prediction (NWP) of a single wind farm, where the spatial and temporal correlations among geographically adjacent wind farms are not considered. In this paper, we propose a novel WPF approach for multiple farms by integrating temporal convolution networks (TCN) and graph convolution networks (GCN). Abstracting the set of multiple wind farms into a graph, spatial information is aggregated with GCN on the irregular non-Euclidean mesh defined by the graph. For each farm, temporal information is fused via TCN. With alternating temporal and graph convolution layers, features are extracted from inputs and integrated for forecasting. As demonstrated by experimental results on data from a set of wind farms in Ningxia, China, the proposed WPF for multiple farms performs much better than existing approaches for a single farm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impedance Modeling and Stability Analysis of Grid-forming Converters

Impedance Modeling and Stability Analysis of Grid-forming Co...

引用

IEEE Transportation Electrification Conference and Expo (ITEC)

作者： Rui Zhao Xiaofeng Yang Ange Wei Jin Zhang State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems China Electric Power Research Institute Beijing China School of Electrical Engineering Beijing Jiaotong University Beijing China

ISBN: (数字)9798350317664

ISBN: (纸本)9798350317671

Grid-forming converters can provide inertial and damping support for high-penetration renewable energy grids. However, inadequate tuning of grid parameters may lead to system instability due to variations in grid strength. In this paper, based on harmonic linearization theory, the positive and negative sequence impedance models of grid-forming converters are derived. Then the suitability of grid-forming strategies in weak grids is discussed in conjunction with the Nyquist stability criterion. Additionally, the impact of grid-forming power loop parameters on system stability is revealed, aiming to provide theoretical support for the optimization design of grid-forming converter parameters. Finally, a time-domain simulation model of the grid-forming converter is constructed to validate the theoretical research under typical system parameters.

关键词： Damping Renewable energy sources Analytical models Stability criteria power system stability Harmonic analysis Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Two-level Day-ahead Optimal Scheduling of Distributed Energy Storage System 4

Two-level Day-ahead Optimal Scheduling of Distributed Energy...

引用

4th IEEE China International Electrical and Energy Conference, CIEEC 2021

作者： Wang, Maochun Li, Pai Sang, Zhencheng Fan, Yue Li, Qing Zhou, Wei State Grid Qinghai Electric Power Company QingHai China China Electric Power Research Institute State Key Laboratory of Operation and Control of Renewable Energy Storage Systems Beijing China

ISBN: (纸本)9781728171494

Stochastic characteristics of wind and photovoltaic (PV) power causes great challenge for power system operations. Distributed energy storage system (DESS) can mediate the intermittent renewable energy. This paper proposes a two-level optimization method for DESS scheduling. Firstly, DESSs are aggregated in a virtual power plan (VPP) and participates the power scheduling as a whole, the power schedules of DESSs are obtained with the proposed two-level optimization method. Secondly, in the upper-level optimization model, a two-stage stochastic unit commitment model is established with considering power uncertainties, and thermal units as well as VPP of DESS are optimized to maximize the power generation of renewable energy. And then, in the lower-level optimization model, an optimization model is proposed to schedule each DESS in order to minimize the total life loss cost of DESSs. Case studies are inducted based on actual data of a provincial power grid. The effectiveness and practicability of the proposed method is verified by the testing results. © 2021 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Hybrid Energy Storage Optimization Configuration Model for Reducing Thermal power Frequency Modulation Loss

Multi-Objective Hybrid Energy Storage Optimization Configura...

引用

International Conference on power System Technology (powerCON)

作者： JunHui Li ZhenZhuo Zhao ZhiQiang Zhao HaoJun Liu CuiPing Li Zhi Li CaiQi Jia XingXu Zhu Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin China State Grid Hami Power Supply Company Hami City Xinjiang Uygur Autonomous Region China

The TPU (Thermal power Unit) equipped with HESS (Hybrid Energy Storage System) can effectively increase of FM (Frequency Modulation) performance of the unit and decrease the FM loss of the thermal power unit. The difficulty of rational allocation of ES (Energy Storage) is how to improve the FM performance of TPU and reduce the life cycle cost of ES. Therefore, the paper establishes a multi-objective hybrid energy storage optimization configuration model aimed at reducing the FM loss of thermal power. Firstly, a double-layer control policy of thermal power-hybrid energy storage is proposed. The first layer is the thermal power-hybrid energy storage AGC instruction allocation strategy based on EMD (Empirical Mode Decomposition). The second layer is a hybrid energy storage control strategy with flywheel ES priority action and lithium battery second response. Then, a multi-objective optimal configuration model considering the difference between life cycle cost and benefit and AGC comprehensive evaluation index Kp is established. It uses the multi-objective PSO (Particle Swarm Optimization) algorithm based on TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) to solve the model, which can avoid contingency of traditional multi-objective PSO in determining optimum solution in the Pareto solution set. Finally, based on the simulation analysis of power plant operation data in North China, the results verify the availability and feasibility of the established model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clustering and Equivalent Modeling Method for Direct-Drive Wind Farms Based on Particle Swarm Neural Network

Clustering and Equivalent Modeling Method for Direct-Drive W...

引用

Energy, power and Electrical Engineering (EPEE), International Conference on

作者： Liang Tu Libin Huang Haiping Guo Binjiang Hu Jingyue Zhang Hui Luo China Southern Power Grid State Key Laboratory of HVDC Electric Power Research Institute Guangzhou China National Energy Power Grid Technology R&D Centre China Southern Power Grid Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System China Southern Power Grid Guangzhou China China Southern Power Grid CSG Key Laboratory for Power System Simulation Electric Power Research Institute Guangzhou China National Energy Power Grid Technology R&D Centre Guangzhou China

ISBN: (数字)9798331518066

ISBN: (纸本)9798331518073

In the realm of large-scale integration of wind farms or clusters into power grids, the fault transient characteristics of these grids have experienced significant transformations. Unfortunately, the prevalent single-machine equivalent models are inadequate in accurately depicting the fault transient behavior of wind farms or clusters. Moreover, their simulation computations are exceedingly intensive, resulting in suboptimal simulation efficiency. To address these challenges, this paper introduces a clustering and equivalent modeling approach tailored for direct-drive wind farms, leveraging the capabilities of a particle swarm neural network. Initially, a transient model for direct-drive wind turbines is formulated, and fault characteristic influence factors are established through theoretical analysis. These factors encompass the distance between the wind turbine and the point of common coupling (PCC), the implementation of DC-side current limiting measures, wind speed, and reactive power at the outlet. Following this, the Euclidean distance of the influence factor set is computed, and the initial cluster centers of wind turbines are derived using an enhanced max-min distance method. Ultimately, an equivalent clustering model is formulated by utilizing the influence factors and initial cluster centers as the training set. simulation outcomes reveal that, in comparison to the single-machine equivalent model, this method enhances simulation efficiency by a range of ${6 2 \%}$ to ${6 7 \%}$ and reduces the steady-state error in fault current simulation by ${0 . 8 \%}$ to ${1 . 9 \%}$.

关键词： Training Computational modeling Wind speed Current measurement Wind farms Data models Wind turbines Steady-state Transient analysis Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Short-term wind power forecast with turning weather based on DBSCAN-RFE-LightGBM

引用

Renewable Energy 2025年 251卷

作者： Wu, Zhenlong Fan, Xinyu Bian, Guibin Liu, Yanhong Zhang, Xiaoke Chen, YangQuan School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Zhengzhou University Luoyang471000 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Electric Power Research Institute of State Grid Henan Electric Power Company Zhengzhou450052 China Lab Department of Mechanical Engineering School of Engineering University of California MercedCA95343 United States

At present, the wind power prediction technology is becoming more and more mature, however, the turning weather brings a decrease in prediction accuracy due to its suddenness and instability. In this paper, a wind power prediction method considering the turning period and non-turning period respectively is proposed to weaken the adverse effects caused by turning weather. Firstly, the prediction effects of multiple models are compared, density-based spatial clustering of applications with noise (DBSCAN) is selected as the outlier processing method, recursive feature elimination (RFE) is used as the feature selection method, and Light gradient boosting machine (LightGBM) is used for prediction. The combined prediction method based on DBSCAN-RFE-LightGBM can reduce the influence of abnormal data and redundant features and improve the prediction effect. Then, the sliding window is set to detect the turning period. Considering that the turning weather is an emergency and does not happen frequently, the amount of data is small, which leads to the inability to train the model well. Generative adversarial networks (GAN) are applied to expand the turning period data. The LightGBM is trained and predicted by using the expended turning period data. Finally, the time-division prediction results are merged. Using the data collected from wind farms for short-term power prediction experiments, the time-segment prediction method proposed in this paper with GAN reduces MAE by 1.913 and RMSE by 3.351 on a single unit compared with the non-differentiated period. © 2025 Elsevier Ltd

关键词： Merging

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：