考虑样本类别不平衡的电网故障事件智能识别方法

电网中不同设备的故障概率存在差异,影响智能诊断技术的准确性.为解决此问题,提出了一种基于代价敏感学习和模型自适应选择融合的电网故障事件智能识别方法.首先,利用Word2vec模型将预处理后的电网告警信息向量化,并搭建2个双向长短期记忆网络作为基础分类器;然后,设计代价敏感损失函数,将交叉熵损失函数与代价敏感损失函数分别应用于2个分类器中;最后,提出一种模型自适应选择融合法,融合上述分类器,得到故障事件识别结果.实际数据测试表明,所提方法能够有效降低故障事件识别中样本类别不平衡的影响.     

基于改进自注意力机制生成对抗网络的智能电网GPS欺骗攻击防御方法

为了避免全球定位系统欺骗攻击(GSA)对相量测量装置造成的危害,提出了一种基于改进自注意力机制生成对抗网络(SAGAN)的智能电网GSA防御方法.首先,通过引入深度学习参数,构建了改进网络-物理模型,利用历史数据计算得到当前时刻的量测值.然后,在SAGAN的生成器和判别器网络中分别融入一个时间注意力模块,提出了一种用于实现网络-物理模型的改进SAGAN防御方法.通过训练改进SAGAN,得到一对判别器和生成器,利用判别器检测采集的量测值是否遭受GSA,当检测到攻击时,利用生成器生成的数据替换欺骗数据,从而实现智能电网对GSA的主动防御.最后,基于IEEE 14节点和IEEE 118节点系统进行仿真测试,结果验证了所提方法的可行性和有效性.     

冲压成形仿真过程中有限元网格模型的建立

网格模型对冲压成形模拟的精度和效率影响极大 ,文中阐述了有限元网格模型建立的方法 ,并从单元尺寸、单元类型、自适应网格再划分技术等方面论述了如何解决精度与效率的问题。     

Dynamic replica placement and selection strategies in data grids— A comprehensive survey

Data replication techniques are used in data grid to reduce makespan, storage consumption, access latency and network bandwidth. Data replication enhances data availability and thereby increases the system reliability. There are two steps involved in data replication, namely, replica placement and replica selection. Replica placement involves identifying the best possible node to duplicate data based on network latency and user request. Replica selection involves selecting the best replica location to access the data for job execution in the data grid. Various replica placement and selection algorithms are available in the literature. These algorithms measure and analyze different parameters such as bandwidth consumption, access cost, scalability, execution time, storage consumption and makespan. In this paper, various replica placement and selection strategies along with their merits and demerits are discussed. This paper also analyses the performance of various strategies with respect to the parameters mentioned above. In particular, this paper focuses on the dynamic replica placement and selection strategies in the data grid environment.     

Smart pricing scheme: A multi-layered scoring rule application

Defining appropriate pricing strategy for smart environment is important and complex task at the same time. It holds the primal fraction in Demand Response (DR) program. In our work, we devise an incentive based smart dynamic pricing scheme for consumers facilitating a multi-layered scoring rule. The proposed strategy characterizes both incentive based DR and price based DR programs facilities. This mechanism is applied between consumer agents (CA) to electricity provider agent (EP) and EP to Generation Company (GENCO). Based on the Continuous Ranked Probability Score (CRPS), a hierarchical scoring system is formed among these entities, CA–EP–GENCO. As CA receives the dynamic day-ahead pricing signal from EP, it will schedule the household appliances to lower price period and report the prediction in a form of a probability distribution function to EP. EP, in similar way reports the aggregated demand prediction to GENCO. Finally, GENCO computes the base discount after running a cost-optimization problem. GENCO will reward EP with a fraction of discount based on their prediction accuracy. EP will do the same to CA based on how truthful they were reporting their intentions on device scheduling. The method is tested on real data provided by Ontario Power Company and we show that this scheme is capable to reduce energy consumption and consumers’ payment.     

一种电网综合展现可视化系统的设计与应用

笔者在分析一种电网信息综合展现可视化系统建设目标和设计思路的基础上,详细阐述该系统的总体架构、业务架构、数据架构、技术架构、部署架构设计。该系统由智能信息集成模块、视频监控模块和综合展现可视化模块三部分组成,基于先进的多层架构体系和SOA构架模型,以ETL、数据挖掘、视频、GIS、图形图像技术为依托,实现电网信息视频、温湿度、风速、雨量气象环境、负荷、潮流等电网运行信息以及安防消防等各类辅助决策信息有逻辑的、互联互通的、交互的和实时的可视化展现,满足业务运行和对外展示的可视化需求,建成电网公司“汇集信息、全面监控、专业联动、统一展现”的电网信息综合展现可视化系统。该系统支持视频、GIS专题图和图形图表等多种展现方式,适用于不同的需求场景,在海南电网公司的实际应用结果证明了其可行性。     

智能电网隐私保护技术的分析研究

融合各种新兴的技术,智能电网的出现给电力系统带来了很大的变革。但和所有新兴事物一样,智能电网也将面临新的风险,尤其是用户侧的风险。面对智能电网用户侧风险,如何保护用户隐私权,是亟待解决的问题,也是文中研究的重点。首先分析了智能电网带来的风险,尤其是用户侧面临的风险;接着,介绍了智能电网隐私保护,对智能电网隐私保护特点进行了详细的解读;最后,结合电力系统,对我国智能电网隐私保护进行了思考,对未来的工作给出了建议。     

Study of a downward gas jet in a two–dimensional fluidized bed

The study of a downward gas jet was performed in a two–dimensional (2–D) fluidized bed of sand particles under conditions of minimum fluidization and at atmospheric pressure and room temperature. The jet shifted through a cyclic sequence of left–central–right–central–left positions. The probability of the left and right jets was 40% each, while the less stable central jet occurred only 20% of the time. Discrete probability distributions of jet presence for each of the three jet configurations and an overall distribution are presented. They show that jets are dominant along the external walls of the nozzle. The depth of the downward jet increased with air flowrate in agreement with the correlation from Massimilla and Russo (1973).     

大开口高承载网格加筋壳的设计与工艺

本文采用有限元法计算了承受高轴压和外压作用下的大开口复合材料纵横密加筋壳的稳定性，得出不同铺层角度、不同受力工况下的大开口圆柱壳的临界载荷，并采用1：1试验件进行试验验证，将计算值与实验值进行了比较；对大开口复合材料纵横密加筋壳的缠绕工艺进行了研究，解决了大开口网格加筋壳开口补强的一次成型技术和密筋及开口部分的多丝嘴、无增量、非线性机械化缠绕成型工艺技术。     

Designing multilayered wire‐grid polarizers using a monochromatic recursive convolution finite‐difference time‐domain algorithm

Multilayered wire‐grid polarizers (WGP) find application as low‐reflection polarizers in projection‐type liquid crystal display devices. A multilayered WGP is formed by adding thin layers on top of the metal ridges of an ordinary WGP. The ordinary WGP consists of a periodic array of parallel metal ridges, where the period of the array and the width of any individual metal ridge are typically less than the wavelength of the incident light. Such WGPs are often used as efficient polarizers. However, in certain applications, it is important to reduce the reflection from the WGP while preserving the polarization efficiency. One of the ways to achieve this goal is to add thin layers on top of the metal ridges of the ordinary WGP. The reduction in reflection from the multilayered WGP depends on the number and material of these additional layers. In this paper, we describe a design method for multilayered WGPs based on an effective medium theory, thin‐film computation method and a monochromatic recursive convolution finite‐difference time‐domain algorithm. The goal of design process is to identify suitable materials and thicknesses for the additional thin layers needed to lower the reflection appreciably. The design method is explained with the help of bilayered WGPs.