检索结果-南通市图书馆

Fault Diagnosis of Power Transformers Using Graph Convolutional Network

在线全文

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2021年第2期7卷 241-249页

作者： Wenlong Liao Dechang Yang yusen wang Xiang Ren Department of Energy Technology Aalborg UniversityAalborg 9220Denmark College of Information and Electrical Engineering China Agricultural UniversityBeijing 100083China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology-StockholmSE-10044Sweden North China Electric Power Research Institute Co. Ltd.Beijing 100045China

Existing methods for transformer fault diagnosis either train a classifier to fit the relationship between dissolved gas and fault type or find some similar cases with unknown samples by calculating the similarity *** accuracy is limited,since they are hard to learn from other algorithms to improve their own *** improve the accuracy of transformer fault diagnosis,a novel method for transformer fault diagnosis based on graph convolutional network(GCN)is *** proposed method has the advantages of two kinds of existing ***,the adjacency matrix of GCN is utilized to fully represent the similarity metrics between unknown samples and labeled ***,the graph convolutional layers with strong feature extraction ability are used as a classifier to find the complex nonlinear relationship between dissolved gas and fault *** back propagation algorithm is used to complete the training process of *** simulation results show that the performance of GCN is better than that of the existing methods such as convolutional neural network,multi-layer perceptron,support vector machine,extreme gradient boosting tree,k-nearest neighbors and Siamese network in different input features and data volumes,which can effectively meet the needs of diagnostic accuracy.

关键词： Power transformer fault diagnosis graph convolutional network similarity metrics

Scenario Generation for Cooling,Heating,and Power Loads Using Generative Moment Matching Networks

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2022年第6期8卷 1730-1740页

作者： Wenlong Liao yusen wang Yuelong wang Kody Powell Qi Liu Zhe Yang Department of Energy Technology Aalborg UniversityAalborg 9220Denmark School of Electrical Engineering and Computer Science KTH Royal Institute of TechnologyStockholmSE-10044Sweden State Grid Tianjin Chengxi Electric Power Supply Branch Tianjin 300100China Department of Chemical Engineering University of UtahUT 84112America Key Laboratory of Smart Grid of Ministry of Education Tianjin UniversityTianjin 300072China

Scenario generations of cooling,heating,and power loads are of great significance for the economic operation and stability analysis of integrated energy *** this paper,a novel deep generative network is proposed to model cooling,heating,and power load curves based on generative moment matching networks(GMMNs)where an auto-encoder transforms highdimensional load curves into low-dimensional latent variables and the maximum mean discrepancy represents the similarity metrics between the generated samples and the real *** training the model,the new scenarios are generated by feeding Gaussian noises to the scenario generator of the *** the explicit density models,the proposed GMMN does not need to artificially assume the probability distribution of the load curves,which leads to stronger *** simulation results show that the GMMN not only fits the probability distribution of multiclass load curves very well,but also accurately captures the shape(e.g.,large peaks,fast ramps,and fluctuation),frequency-domain characteristics,and temporal-spatial correlations of cooling,heating,and power ***,the energy consumption of generated samples closely resembles that of real samples.

关键词： Deep learning generative moment matching networks integrated energy systems scenario generations

A Review of Graph Neural Networks and Their Applications in Power Systems

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2022年第2期10卷 345-360页

作者： Wenlong Liao Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Yuelong wang yusen wang the Department of Energy Technology Aalborg UniversityAalborgDenmark the State Grid Tianjin Chengxi Electric Power Supply Branch TianjinChina the School of Electrical Engineering and Computer Science KTH Royal Institute of TechnologyStockholmSweden

Deep neural networks have revolutionized many machine learning tasks in power systems,ranging from pattern recognition to signal *** data in these tasks are typically represented in Euclidean ***,there is an increasing number of applications in power systems,where data are collected from non-Euclidean domains and represented as graph-structured data with high-dimensional features and interdependency among *** complexity of graph-structured data has brought significant challenges to the existing deep neural networks defined in Euclidean ***,many publications generalizing deep neural networks for graph-structured data in power systems have *** this paper,a comprehensive overview of graph neural networks(GNNs)in power systems is ***,several classical paradigms of GNN structures,e.g.,graph convolutional networks,are *** applications in power systems such as fault scenario application,time-series prediction,power flow calculation,and data generation are reviewed in ***,main issues and some research trends about the applications of GNNs in power systems are discussed.

关键词： Machine learning power system deep neural network graph neural network artificial intelligence

基于IHD的光伏系统直流电弧故障检测技术研究

在线全文

学校读者我要写书评

暂无评论

自动化应用 2024年第13期65卷 141-145页

作者：张秦康王禹森杨景贻中国矿业大学(北京)机械与电气工程学院北京100083

串联电弧故障是导致光伏系统电气火灾的重要诱因,因此,电弧故障检测成为热点研究领域之一。现有检测方法主要是利用电弧本身的物理特征和电弧电流的时频域特征2个方面实现对电弧故障的检测,其中,基于直流电弧故障电弧的时频域特征的检... 详细信息

串联电弧故障是导致光伏系统电气火灾的重要诱因,因此,电弧故障检测成为热点研究领域之一。现有检测方法主要是利用电弧本身的物理特征和电弧电流的时频域特征2个方面实现对电弧故障的检测,其中,基于直流电弧故障电弧的时频域特征的检测方法在分布式光伏发电系统的应用中场景复杂、组件繁多,正常的开关动作、负载突变都可能导致误判,且阈值无法随环境自适应变化,用于识别串联电弧故障的特征量普适性较差。针对该问题,提出了一种利用改进豪斯多夫维数的直流串联电弧故障检测方法,其具有普适性较强、运算量少的优点。豪斯多夫维数在分形维数理论中占重要地位,其通常用于测量具有分形特征的数据集维数。首先对电弧故障时采集的线路电流信号进行快速傅里叶变换,选取故障特征最明显的特征频段,滤波处理并归一化后作为输入,得到改进豪斯多夫维数计算结果,根据其值即可判别是否存在直流串联电弧,该方法平均准确率可达98.1%。

关键词：直流串联电弧分布式光伏发电电弧检测改进豪斯多夫维数

一种利用ConvGRU解决交通流量预测问题的方法

在线全文

学校读者我要写书评

暂无评论

小型微型计算机系统 2024年第10期45卷 2355-2361页

作者：王玉森景志勇卫琳高宇飞石磊王清贤陶永才王向杰郑州大学网络空间安全学院郑州450002 郑州大学计算机与人工智能学院郑州450001 郑州轻工业大学软件学院郑州450001 嵩山实验室郑州450003

准确的交通流量预测可协助交通管理部门工作,减少交通压力.但现有方法对交通流时间特征与空间特征学习不充分,将二者割裂讨论,忽视了时间与空间的动态相关性.针对以上问题,本文提出了基于ConvGRU的多时间尺度时空卷积交通流预测方法(MTS... 详细信息

准确的交通流量预测可协助交通管理部门工作,减少交通压力.但现有方法对交通流时间特征与空间特征学习不充分,将二者割裂讨论,忽视了时间与空间的动态相关性.针对以上问题,本文提出了基于ConvGRU的多时间尺度时空卷积交通流预测方法(MTSTC),设计浅层时空卷积模块对数据中的时空相关性进行初步提取;提出以ConvGRU为核心特征提取器的深层时空卷积模块,对数据的时空特征进行更深层次挖掘;并从3种时间尺度范围的数据中提炼交通流的周期性特征;结合注意力机制设计了时空注意力模块辅助模型训练,提升模型收敛速率.在公开数据集PEMS04和PEMS08上进行实验验证,结果表明采用MAE和RMSE评价指标时,本文方法的准确率相较基线方法在两个数据集上提升了3.23%~5.64%.

关键词：交通流量预测时空卷积模块注意力机制 ConvGRU

Data-driven Missing Data Imputation for Wind Farms Using Context Encoder

同方期刊数据库

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2022年第4期10卷 964-976页

作者： Wenlong Liao Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Dechang Yang yusen wang Department of Energy Technology Aalborg UniversityAalborgDenmark College of Information and Electrical Engineering China Agricultural UniversityBeijingChina School of Electrical Engineering and Computer Science KTH Royal Institute of TechnologyStockholmSweden

High-quality datasets are of paramount importance for the operation and planning of wind ***,the datasets collected by the supervisory control and data acquisition(SCADA)system may contain missing data due to various factors such as sensor failure and communication *** this paper,a data-driven approach is proposed to fill the missing data of wind farms based on a context encoder(CE),which consists of an encoder,a decoder,and a *** deep convolutional neural networks,the proposed method is able to automatically explore the complex nonlinear characteristics of the datasets that are difficult to be modeled *** proposed method can not only fully use the surrounding context information by the reconstructed loss,but also make filling data look real by the adversarial *** addition,the correlation among multiple missing attributes is taken into account by adjusting the format of input *** simulation results show that CE performs better than traditional methods for the attributes of wind farms with hallmark characteristics such as large peaks,large valleys,and fast ***,the CE shows stronger generalization ability than traditional methods such as auto-encoder,K-means,k-nearest neighbor,back propagation neural network,cubic interpolation,and conditional generative adversarial network for different missing data scales.

关键词： Data-driven missing data imputation wind farm deep learning context encoder

Scenario Generations for Renewable Energy Sources and Loads Based on Implicit Maximum Likelihood Estimations

在线全文

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2022年第6期10卷 1563-1575页

作者： Wenlong Liao Birgitte Bak-Jensen Jayakrishnan Radhakrishna Pillai Zhe Yang yusen wang Kuangpu Liu AAU Energy Aalborg UniversityAalborgDenmark School of Electrical Engineering and Computer Science KTH Royal Institute of TechnologyStockholmSweden

Scenario generations for renewable energy sources and loads play an important role in the stable operation and risk assessment of integrated energy *** paper proposes a deep generative network based method to model time-series curves,e.g.,power generation curves and load curves,of renewable energy sources and loads based on implicit maximum likelihood estimations(IMLEs),which can generate realistic scenarios with similar patterns as real *** training the model,any number of new scenarios can be obtained by simply inputting Gaussian noises into the data generator of *** proposed approach does not require any model assumptions or prior knowledge of the form in the likelihood function being made during the training process,which leads to stronger applicability than explicit density model based *** extensive experiments show that the IMLEs accurately capture the complex shapes,frequency-domain characteristics,probability distributions,and correlations of renewable energy sources and ***,the proposed approach can be easily generalized to scenario generation tasks of various renewable energy sources and loads by fine-tuning parameters and structures.

关键词： Renewable energy source scenario generation implicit maximum likelihood estimation(IMLE) deep learning generative network

复杂染料废水降解过程中生物炭对Aeromonas hydrophila菌的影响

在线全文

学校读者我要写书评

暂无评论

天津城建大学学报 2024年第2期30卷 125-132页

作者：张浩范晓丹李腾王屿森天津城建大学环境与市政工程学院天津300384 天津城建大学环境与市政市级实验教学示范中心天津300384

生物降解复杂染料废水过程中细菌活性是有效降解的关键。本研究分离驯化出染料废水降解菌,并对其进行形态学特征和系统发育的分析鉴定,将生物炭及Fe_(2)O_(3)/生物炭(Fe-BC)分别与菌构建复合体系,研究降解过程中生物炭和Fe-BC对菌的影... 详细信息

生物降解复杂染料废水过程中细菌活性是有效降解的关键。本研究分离驯化出染料废水降解菌,并对其进行形态学特征和系统发育的分析鉴定,将生物炭及Fe_(2)O_(3)/生物炭(Fe-BC)分别与菌构建复合体系,研究降解过程中生物炭和Fe-BC对菌的影响。结果表明,该降解菌为Aeromonashydrophila(嗜水气单胞菌菌属),生物炭-菌和Fe-BC-菌体系中降解脱色率分别提高18%和75%,降解脱色过程符合准一级动力学模型。在Fe-BC-菌体系中,Fe-BC可以促进菌细胞的代谢和细胞间的物质传递,使得参与代谢的N、P、S、Ca、Na及Fe等元素含量增加,并促使细胞产生胞外分泌物。Fe^(2+)参与菌降解复杂有机物的过程,降解产物主要有N-2-(3,4-二羟苯基)-乙基甲胺、2,3-二氢-1,3-二氧-1H-异吲哚-5-羧酸(含C=O)及甲氧基乙酸甲酯(含C—O)。生物炭与Fe-BC可以提高嗜水气单胞菌的生物活性,完成对复杂染料废水的降解脱色.

关键词：氧化铁生物炭微生物细菌染料废水降解

Strategic Scheduling of PEV Charging Load:A Non-Cooperative Game Model

在线全文

学校读者我要写书评

暂无评论

Strategic Scheduling of PEV Charging Load:A Non-Cooperative ...