Structural Reliability Analysis Based on Support Vector Machine and Dual Neural Network Direct Integration Method

Aiming at the reliability analysis of small sample data or implicit structural function,a novel structural reliability analysis model based on support vector machine(SVM)and neural network direct integration method(DNN)is proposed.Firstly,SVM with good small sample learning ability is used to train small sample data,fit structural performance functions and establish regular integration regions.Secondly,DNN is approximated the integral function to achieve multiple integration in the integration region.Finally,structural reliability was obtained by DNN.Numerical examples are investigated to demonstrate the effectiveness of the present method,which provides a feasible way for the structural reliability analysis.

Web-based spatiotemporal visualization of marine environment data

With long-term marine surveys and research,and especially with the development of new marine environment monitoring technologies,prodigious amounts of complex marine environmental data are generated,and continuously increase rapidly.Features of these data include massive volume,widespread distribution,multiple-sources,heterogeneous,multi-dimensional and dynamic in structure and time.The present study recommends an integrative visualization solution for these data,to enhance the visual display of data and data archives,and to develop a joint use of these data distributed among different organizations or communities.This study also analyses the web services technologies and defines the concept of the marine information gird,then focuses on the spatiotemporal visualization method and proposes a process-oriented spatiotemporal visualization method.We discuss how marine environmental data can be organized based on the spatiotemporal visualization method,and how organized data are represented for use with web services and stored in a reusable fashion.In addition,we provide an original visualization architecture that is integrative and based on the explored technologies.In the end,we propose a prototype system of marine environmental data of the South China Sea for visualizations of Argo floats,sea surface temperature fields,sea current fields,salinity,in-situ investigation data,and ocean stations.An integration visualization architecture is illustrated on the prototype system,which highlights the process-oriented temporal visualization method and demonstrates the benefit of the architecture and the methods described in this study.

Design of multisensory integration gripper system for Internet-based teleoperation

A layered architecture of muhisensory integration gripper system is first developed, which includes data acquisition layer, data processing layer and network interface layer. Then we propose a novel support-vector-machine-based data fusion algorithm and also design the gripper system by combining data fusion with CAN bus and CORBA technology, which provides the gripper system with outstanding characteristics such as modularization and intelligence. A multisensory integration gripper test bed is finally built on which a circuit board replacement job based on Internet-based teleoperation is achieved. The experimental results verify the validity of this gripper system design.

基于决策粗糙集的多源异构电网数据整合方法

为解决多源异构电网数据整合耗时较长的问题,提出应用决策粗糙集的数据整合模型。通过纵向融合、横向融合2个环节,完成多源异构电网数据的融合处理,再应用并行化正向最大匹配去冗算法,删除融合数据中存在的重复冗余信息;依托决策粗糙集对电网数据进行属性约简,去除具有干扰作用的噪声条件属性,再从约简决策表内提取模糊分类规则,实现电网数据的分类整合管理;创建基于数据关联度的整合数据修复方案,完成数据整合模型的设计。实验结果表明:应用所提模型对43700条多源异构电网数据进行整合处理,所需的数据整合时间为5.9 s,符合实时性要求。

基于高斯模型的电网业务数据分布式存储方法研究

常规的集中式数据存储方法在面对大规模、高频率的数据存储需求时,存储的效率相对较低,为此提出了基于高斯模型的电网业务数据分布式存储方法。通过分析电网业务数据特征,强化存储效率,实现对数据信息多层级增删处理;采用分层扩展存储及存储复验的方式,建立高斯电网业务数据分布式存储模型,完成数据存储。测试结果表明:设计方法的实际存储功率相对较高,内存占用率和CPU占用率明显更低,具有较好的存储性能。

A Low Cost Tax SOA Infrastructure in Grid Applications

Many high performance database servers are becoming idle with the tax data being integrated to country tax data centers. We make use of the idle servers to set up a provincial tax Grid based on open Grid service architecture （OGSA）. We put forward practical methods to integrate databases, to define and create basic modular Grid services and apply agent to manage Grid services. This technical innovation scheme is of a service-oriented architecture （SOA） and succeeds in averting resources waste. Tests proved that it greatly improves the quality of tax services.

Quantitative Study on the Relationship between Arable Land and Its Influencing Factors in Southern Loess Plateau

With the Southern Loess Plateau as the object of study,we select the nonbiological factors( physical factors),biological factors and human factors that affect the landscape of arable land to build indicator system. Using GIS,we perform the visualization expression and hierarchical storage of influencing factors to build 1 km × 1 km integrated vector and raster database of arable land landscape pattern and its influencing factors. Using spatial regression analysis,we determine the quantitative relationship between arable land landscape and its influencing factors. The results show that the arable land in the Southern Loess Plateau is mainly distributed in the regions with high temperature,great average annual precipitation,high altitude,high soil N content,small slope,GDP per unit area of land,low ≥10℃ accumulated temperature,and short distance away from the rivers and roads. The study provides a scientific basis for clarifying the relationship between arable land landscape and its influencing factors.

Adaptive Fuzzy Sliding Mode Controller for Grid Interface Ocean Wave Energy Conversion

This paper presents a closed-loop vector control structure based on adaptive Fuzzy Logic Sliding Mode Controller (FL-SMC) for a grid-connected Wave Energy Conversion System (WECS) driven Self-Excited Induction Generator (SEIG). The aim of the developed control method is to automatically tune and optimize the scaling factors and the membership functions of the Fuzzy Logic Controllers (FLC) using Multi-Objective Genetic Algorithms (MOGA) and Multi-Objective Particle Swarm Optimization (MOPSO). Two Pulse Width Modulated voltage source PWM converters with a carrier-based Sinusoidal PWM modulation for both Generator- and Grid-side converters have been connected back to back between the generator terminals and utility grid via common DC link. The indirect vector control scheme is implemented to maintain balance between generated power and power supplied to the grid and maintain the terminal voltage of the generator and the DC bus voltage constant for variable rotor speed and load. Simulation study has been carried out using the MATLAB/Simulink environment to verify the robustness of the power electronics converters and the effectiveness of proposed control method under steady state and transient conditions and also machine parameters mismatches. The proposed control scheme has improved the voltage regulation and the transient performance of the wave energy scheme over a wide range of operating conditions.

基于区块链且可验证的智能电网多维数据聚合与分享方案

针对如何支持轻量级多维数据聚合,实现系统整体过程中多维数据的双端完整性验证,以及处理云服务器集中化等问题,提出了一种基于区块链且可验证的智能电网多维数据聚合与分享方案。首先,为了满足智能电网对电量数据细粒度分析的需求,利用掩蔽值和霍纳法则实现了隐私保护多维数据聚合。在此基础上,针对现有数据聚合方案在云存储数据与第三方分享方面存在的数据完整性验证问题,借用基于RSA的乘法同态承诺方案和同态哈希函数的同态性设计了一种新的签名算法,使云服务器不仅可以验证聚合数据的完整性,还可以验证数据分享阶段的完整性,即实现了云存储数据的双端可验证性,并且可以抵抗内部攻击。同时,提出了一种基于联盟链多链的聚合数据分享体系结构,有效地避免单机处理瓶颈和易受攻击等集中化问题。理论分析证明了所提方案的安全性。性能实验表明,所提方案比已有方案具有更低的计算和通信成本。

基于支持向量机的网格化电网负荷预测算法设计

针对电网负荷预测算法预测能力较差、效率偏低的问题,文中提出了一种PCA-PSO-SVM算法。其在经典粒子群算法的基础上引入主元分析法,使模型具有降低数据维度及算法冗余度的特性。同时通过改进的PCA-PSO算法对SVM模型的内置参数进行最优选取,从而使改进后的SVM模型具有最佳的分类性能。在实验测试中,采用PCA算法选取了91%贡献度内的6项数据特征进行样本数据训练。结果表明,相较于其他对比算法,该文算法预测结果的RMSE、MAE与MAPE误差值均为最小,证明其可对网格化电网负荷加以预测。此外,该算法还能提升传统算法的准确度,为电力负荷分配提供有力支持。

集成型车载充电系统并网模式模型预测控制策略

相较于传统车载充电系统,集成型车载充电系统(integrated onboard charger system,IOCS)在成本、功率密度等方面具备显著优势。文中基于六相永磁电驱系统设计了一台IOCS,并研究了模型预测电流控制(model predictive current control,MPCC)算法在该系统并网模式下的应用。首先,分析所提IOCS的电路拓扑并建立数学模型,同时介绍传统MPCC的实施流程。然后,针对传统MPCC计算量大、稳态性能差等不足,提出一种基于占空比优化的MPCC(MPCC based on duty cycle optimization,DCO-MPCC)策略。一方面,减少备选电压矢量数量,降低电流预测环节带来的计算负担;另一方面,提出一种占空比优化技术,改善系统稳态性能。最后,通过实验验证了所提算法的有效性与优越性。实验结果表明,DCO-MPCC策略能够显著提升系统稳态性能并减少算法计算量。充电与车网互动(vehicle to grid,V2G)工况下,网侧电流总谐波畸变(total harmonic distortion,THD)分别降低6.18%与5.92%,算法运行时间减少17.54μs。

Interactive data styling and multifocal visualization for a multigrid web-based Digital Earth

Globe-based Digital Earth(DE)is a promising system that uses 3D models of the Earth for integration,organization,processing,and visualization of vast multiscale geospatial datasets.The growing size and scale of geospatial datasets present significant obstacles to interactive viewing and meaningful visualizations of these DE systems.To address these challenges,we present a novel web-based multiresolution DE system using a hierarchical discretization of the globe on both server and client sides.The presented web-based system makes use of a novel data encoding technique for rendering large multiscale geospatial datasets,with the additional capability of displaying multiple simultaneous viewpoints.Only the data needed for the current views and scales are encoded and processed.We leverage the power of GPU acceleration on the client-side to perform real-time data rendering and dynamic styling.Efficient rendering of multiple views allows us to support multilevel focus+context visualization,an effective approach to navigate through large multiscale global datasets.The client–server interaction as well as the data encoding,rendering,styling,and visualization techniques utilized by our presented system contribute toward making DE more accessible and informative.

大数据技术下智能电网关键技术研究

大数据技术不仅改变了人们的工作与生活方式,而且在智能电网领域得到了推广应用。目前,传统的数据处理技术已经难以满足新时代的发展需求。利用大数据技术可以实时监测设备的运行状态,通过建立预测模型预测可能会发生的设备故障,以便能够及时进行维护和修复。为了有效满足社会需求,推动电力行业发展,需要将智能电网与大数据技术相结合,开发一个更稳定、更有效、更安全的电力系统,实现电力企业的可持续发展。

基于集成卷积神经网络的电网负荷数据分类

针对电力行业数据来源分散且维度较高,存在大量噪声,导致负荷数据分类非常困难的问题,提出了一种基于集成卷积神经网络的电网负荷数据分类方法。采用加权平均移动法生成负荷曲线,并降维处理电网负荷数据。构建双向激励函数,应用集成卷积神经网络训练降维数据集,区分正常数据和噪声数据。应用加权平均学习法通过构建新的网络对个体网络集成,建立集成学习后的数据集。利用不确定样本属性的验证、训练步骤,实现电网负荷数据分类。通过实验结果可知,该方法在电网负荷测量所属单元数值为0~1区间内的负荷数据分类结果为最优。

电网多源异构缺失数据最优投影整合算法研究

电网多源异构数据分散性较强,导致数据随机缺失问题严重,影响电网整体运行的管理质量。研究了一种电网多源异构缺失数据最优投影整合算法。首先,引入拉格朗日差值方法填充电网多源异构数据中的缺失值。其次,采用经验模态分解方法消除电网多源异构数据中的噪声。最后,建立投影指标函数,将高维电网多源异构数据经过投影处理后转变为一维的投影值。计算模糊聚类迭代适应度,利用混沌文化差分进化算法寻找电网多源异构数据的最优投影方向,完成缺失数据的整合。试验结果表明,所提算法的数据去噪效果较好,去噪后电网多源异构数据并未出现失真现象,并且能够在提高整合精度的同时确保算法运行的稳定性。所提算法数据整合精度受数据缺失的影响较小。该研究能够提高电网多源异构数据的质量,有助于提高电网运行管理水平。

基于决策粗糙集模型的电网多源异构数据整合

针对传统整合方法受干扰数据的影响,导致配电网多源异构数据整合时误差大,效率低等问题,提出基于决策粗糙集模型的电网多源异构数据整合方法。通过对电网数据属性、存储方式、读写方法等预处理,结合贝叶斯估计方法,剔除含有噪声不确定性数据;通过粗糙隶属函数甄别真值,构建决策粗糙集模型过滤数据,划分区域;按照贝叶斯决策过程,确定数据所在集合,过滤掉冗余数据,以防止误判;构建多源异构数据整合模型,利用人工神经网络的单层次分割算法,将结构化数据与非结构化数据融合,以此完成数据整合。实验结果表明,该方法获取的最佳数据整合点的标幺值为0.73,与实际整合点数据一致,可将全部数据整合到一起,表明所提方法具有良好整合效果。

基于混合深度学习的短期风电预测研究

针对现有风电预测精度低的问题,提出了一种基于IEMD和混合深度学习模型的超短期风力发电预测模型。首先,提出基于IEMD对原始风电数据进行分解,从而分解出电力高频、中频、低频及其趋势特征。其次,基于最小二乘支持向量机对电力中频、低频及其趋势特征进行预测,并基于LSTM网络预测风电高频特征。最后,根据特征叠加规则,获得最终预测结果。实验阶段,以中国某电力公司发布的风电数据集进行实验,所提模型MAPE、MAE、RMSE等指标更优,实验结果验证了所提模型的可行性和有效性。该模型为混合智能电网智能化服务以及新能源调度规划的应用发展提供了一定借鉴作用。

电网运行风险可视化监视方法研究

针对电网运行状态监视问题,研究设计了一种新型的电网运行风险可视化监视方法。首先,设计了通过采集电网中电力设备运行数据来监视电网运行状态的新型设备,并在常规采样电路中加入了采样保持电路和稳压电路,以实现全天候电网运行监视的目的;其次,通过数据融合方式识别电网的运行状态,基于归一法和小波分析法处理庞大的电网运行数据,并利用数据网络的概率密度函数判别电网是否发生故障;最后,对运行数据进行递归处理使数据可视化。试验表明该方法不仅具有很强的故障识别能力,其故障定位误差也控制在5%左右。

Pre-Processing,Quality Assurance,and Use of Global Atmospheric Motion Vector Observations in CRA

Assimilation of atmospheric motion vectors(AMVs)is important in the initialization of the atmospheric state in numerical weather prediction models,especially over oceans and at high latitudes where conventional data are sparse.This paper presents a detailed description of the pre-processing,quality assurance,and use of global AMVs in China’s first generation of the 40-yr(1979-2018)CRA global atmospheric reanalysis product.A new AMV archive is integrated from near real-time operational Global Telecommunication System data and reprocessed AMV datasets released or produced mainly during 2014-2016 according to a priority principle.To avoid the misuse of data with systematic quality problems,the observations of all 18 types of AMVs from 54 satellites are pre-evaluated over the whole time series.The pre-evaluation system developed by the CRA team is based on the NCEP Gridpoint Statistical Interpolation(GSI)three-dimensional variational assimilation system and the ERA-Interim reanalysis product.The AMVs in the new AMV archive are denser than the AMVs prepared for the Climate Forecast System Reanalysis product,the bias and root-mean-square values are smaller,and the time series are steadier.The new AMV archive is assimilated in the CRA product based on the NCEP GSI assimilation procedure and quality control configuration with reference to the pre-evaluation results.This is the first time that the reprocessed AMVs from Fengyun-2 satellites from June 2005 to July 2017 are assimilated in a reanalysis product.The assimilation features inspire confidence in the accuracy and stability of these data.The mean root-mean-square values of the observation minus analysis infrared,water vapor,and visible AMV were 1.5-3.4,2.7-3.6,and 1.3-2.1 m s-1,respectively.This experience of integrating,pre-evaluating,and assimilating AMV observations is valuable for the next generation of reanalysis products.

网络化配网调度生产作业模式的创新与实践

通过试点打造网络化配网调度生产作业新模式,以“智能化成票、全链条管控、在线化防误、网络化下令”为抓手,深入开展多维信息配网调度保障技术研究;采用有机融合多维数据、升级技术装备、优化业务流程、再造作业模式等举措,解决业务协同不畅、调度台工作繁重、工作效率不高、安全管控水平较低等问题,构建安全、高效、可控的配网调控体系,实现电网检修及操作业务“质”的飞跃。