基于Hadoop和HBase的输变电设备数据聚合平台

输变电设备在运行中将产生大量的多态、异构数据,导致在数据集成和利用过程中出现信息孤岛问题,无法实现不同数据源内的数据信息共享互换。如何可靠获取、同步处理并对这些数据信息充分挖掘给电力系统中信息系统的建设及运行维护带来巨大压力。采用本体技术对多源异构数据进行聚合,可以向用户提供更具针对性的信息。针对电网中输变电设备全景信息数据的多源性、多态性、异构性,本文提出了基于Hadoop和HBase的输变电设备大数据聚合平台方案,搭载改进混合本体聚合方法,并设计了Map/Reduce分布式查询和推理流程。该平台采用标准化和开放性建模语言,屏蔽底层异构数据源,具有良好的可扩展性,可用于解决输变电设备数据信息的非结构化、共享性差、难以处理等问题。     

医联网应用中异源健康数据语义融合方法研究

医疗物联网及移动医疗应用中多种传感器采集的生命体征数据,以及各类健康医疗数据彼此之间存在语义异构性,导致智能医疗物联设备数据融合困难。针对这一问题,研究了基于开放关联数据的语义消歧方法。首先对设备数据进行本体建模,形成局部本体;然后利用图匹配算法将局部本体与开放医疗关联数据进行概念对齐,间接消除异源数据间的语义异构性;最后,在运动手环与体重计数据融合实验中,通过与开放关联数据源的关联匹配判定血压和体重等异构概念属于语义相关概念。实验结果表明,通过与开放关联数据源关联,可以实现局部本体语义扩展,进一步实现异源医联网设备数据融合。     

多尺度特征融合的多源异构遥感数据水体提取

针对现有遥感测绘水体提取方法在多源异构遥感数据的信息融合与深层特征提取方面存在的不足,提出了一种基于多尺度特征融合的多源异构遥感数据水体提取方法。首先,设计了一种基于多源异构遥感数据输入的网络模型结构解决多源异构遥感数据的多尺度特征融合问题;随后,提出了一种基于改进残差网络的高维卷积单元,对异构遥感数据进行深层特征提取,同时,构建了基于哨兵一号和哨兵二号卫星的全球水体大规模多源异构遥感数据库。对比实验结果表明,以人工遥感影像标注的水体区域分布真值为精度评价基准,所提出的多尺度特征融合算法的水体提取结果,准确率达到了90.12%,相比现有深度学习领域主流的U-Net图像分割模型方法,准确率提高了3.73%以上,有效提升了多源异构遥感数据的大范围水体提取准确性。     

针对动车组全生命周期集成管理的多源异构数据融合框架设计

随着我国动车组产业的不断发展,对动车组全生命周期数据的管理成为人们关注的焦点。首先,本文分析动车组全生命周期数据现状与存在问题;其次,针对动车组全生命周期多源异构数据的特点,提出一种利用动车组本体知识库的数据融合框架;最后,针对其中的模式匹配问题,提出一种基于组合模式相似度的模式匹配方法。实验结果表明,该方法对动车组多源异构数据的模式匹配结果良好,能够在很大程度上提高动车组多源异构数据融合的自动化程度。     

基于多源异构数据的高速列车状态智能检测系统

通过多类型传感器实时采集列车运行数据并将其回传至中央控制系统的过程中,多源数据间的差异性构成了数据的异构空间。由于现有检测系统的数据空间不具备异构属性,因此无法实现多源数据细微差异特征分析,造成高速列车状态检测误差偏大,对列车运行安全造成影响。为此设计基于多源异构数据的高速列车状态智能检测系统,基于多源异构数据重构系统硬件,并在软件算法设计上,采用多类型列车高速状态信息的多源异构协同处理与多源异构下的多源信息高精度融合识别两部分设计,实现提升检测精准度的效果。与两种差异化检测系统进行异常状态检测与稳定性的对比实验,结果表明,所提设计系统稳定性与列车状态检测精准度最好,说明其具备提升列车状态检测精度的能力。     

智能健康管理多源异构数据融合体系与方法

针对智能健康管理中对信息集成的要求,深入分析信息资源的异构特性,对基于多级多中心的多源异构数据融合方法进行研究,提出智能健康管理中多源异构数据的融合树体系结构,并介绍融合系统的设计、融合节点的组成以及具体的融合算法。对所采集的健康数据进行仿真测试,实验证明该体系可以获得较好的融合效果,实现对信息的有效集成,使管理效果更加优化。     

面向应急救援的多源数据融合技术

地震灾害发生后,为实现生命体的快速发现和科学救援,需要多源数据的辅助支撑.遥感数据、现场环境数据、危险设施分布数据、生命体征数据、生命探测设备运行状态数据以及历史数据,共同构成了应急救援场景下的多源异构数据集.本文面向应急救援领域的数据统一监管、多维分析等应用需求,深入研究多源异构数据的三维空间融合分析技术,提出了一种基于WebGL渲染技术的无插件三维空间融合方案,研制应急救援数据融合可视化系统,实现统一时空框架下应急救援场景所需多源异构数据的融合表达,辅助作业人员进行联动态势分析,帮助指挥人员进行指挥决策,大幅提高应急救援现场应用的工作时效.     

基于图卷积网络的多源本体相似度计算方法

在信息时代,数据量呈指数式增长,而不同数据源存在难以统一表示的异构问题,给数据共享、重用造成不便。语义网络的迅速发展,使本体映射成为解决该问题的有效手段,其核心是本体相似度计算,提出了一种基于图卷积网络的计算方法。将本体建模为异构图网络,再使用图卷积网络学习文本嵌入规则,得到全局统一表示,完成多源数据的融合。实验结果表明,所提方法计算准确性高于其他传统方法,有效地提高了多源数据融合的准确度。     

D-S证据下的高铁信号系统异构数据融合

针对当前高速铁路信号系统数据信息多源异构问题,提出一种新的高铁信号异构数据融合框架设计方案.利用本体思想和D-S证据理论方法,对底层数据信息进行特征融合,减少数据冗余,提高数据质量,优化决策效率,进行实验验证.实验结果表明:该方法在一定规模数据量时,计算速度快且准确率高,所提出的新的异构数据融合架构可行,融合算法有效.     

基于时序挖掘的异构网络多源目标数据融合方法研究

异构网络存在多源目标数据,因此需要融合其中的重复性数据、同属性数据,但由于传统方法构建的模型跟踪效果较差,导致挖掘技术遗失了部分数据特征,影响多源目标数据融合,因此研究基于时序挖掘的异构网络多源目标数据融合方法.该方法利用构建的跟踪模型,搜索异构网络全局多源目标;并对搜索结果进行标准化处理后,规约标准数据;采用时序挖掘...     

基于退化状态空间划分的风电机组视情维修决策

风场的运维成本约占其收入的三分之一之多,风电机组的最优维修问题一直是风电系统降低运维成本的主要途径.针对同一风场多台风力机组成的系统,制定基于状态检测的视情机会维修策略,提出基于退化状态空间划分的多设备系统状态维修决策建模方法,在此基础上建立维修成本最小的解析模型,以决策风力机最优的状态检测周期和维修阈值.实验结果表明,基于状态监测的风力机视情维修机会方案可以很好地节约系统运维成本.     

A research on intelligent fault diagnosis of wind turbines based on ontology and FMECA

Clean energy is an increasing concern as more and more countries pay attention to environmental protection, which brings the rapid development of wind power. More new wind farms and new wind turbines have been put into operation, this caused the problem that the diagnostic knowledge is lacking and diagnostic efficiency is low for new employed maintenance personnel. In order to meet the demands of fault diagnosis of wind turbines, a method of intelligent fault diagnosis based on ontology and FMECA (Failure Mode, Effects and Criticality Analysis) is proposed in this paper. In the proposed method, the FMECA of wind turbines is selected as the knowledge source, and deep knowledge and shallow knowledge extracted from this source are represented by ontology modeling. And then, the diagnosis knowledge base of wind turbines can be established. Reasoning on this knowledge base by virtue of JESS (Java Expert Shell System) rule engine, maintenance personnel can find the causes of faults of a wind turbine quickly, and choose the proper solutions. This method realizes the knowledge sharing between product design enterprises and wind farms. The knowledge base which combines the deep knowledge and the shallow knowledge can improve the capability of fault diagnosis and provide better supports for diagnostic decision making.     

Fault diagnosis for wind turbines based on LSTM and feature optimization strategies

High penetration of renewable energy is the development trend of the future power system. As one of the clean energy sources, wind power generation has an increasing share in the energy market. However, due to the harsh working environment, the high fault rate and poor accessibility of the wind farms, resulting in the difficult maintenance process and high cost. This article proposes a fault diagnosis (FD) method based on long short-term memory (LSTM) and feature optimization strategies for wind turbines (WTs), thus reducing the operation and maintenance costs of WTs. First, Pearson correlation coefficient analysis is performed on the collected data features to remove redundant features, and wavelet transform is adopted to remove the redundant data, so as to optimize the fault features and fault data. Then the selected features samples are used to train LSTM-based FD model. Finally, the actual production data is adopted to verify the proposed method. The proposed method can effectively locate the faults, and provide data support for wind farms, thus improving the reliability, safety, and economic benefits of wind farms.     

基于SCADA参量关联互信息自编码的风电机组故障检测方法

针对风力发电机组数据采集与监视控制系统(supervisory control and data acquisition,SCADA)监测参量间的耦合关联性,提出基于多参数耦合关联互信息编码的风电机组故障检测方法.该方法构建了SCADA数据的耦合关联矩阵,采用互信息变分自编码器对关联矩阵进行编码重构;将SCADA参量关联矩阵的重构误差作为机组健康评估指标,结合指数加权移动平均模型的迭代更新,对机组实时故障阈值进行自适应设置.两个风场的风电机组SCADA数据分析结果表明,所提方法充分利用了SCADA数据的耦合关联结构信息,能有效提高风电机组故障检测的准确性及对环境工况的鲁棒性.     

Iterative modeling of wind turbine power curve based on least‐square B‐spline approximation

Power curve plays a vital role in design, operation, control, and condition monitoring of wind turbines. Especially, it provides necessary information for wind farm maintenance decisions, allowing for not only comparison among the same type of wind turbines installed in different places, but also the same one at different time stamps. A standardized power curve iterative modeling procedure of wind turbines is proposed based on actual supervisory control and data acquisition (SCADA) data for performance evaluation in an online manner with guaranteed smoothness. The data are firstly preprocessed for anomaly detection by following normalization correction and then sliced into different wind speed bins. The least‐square B‐spline approximation method is iteratively implemented for power curve construction based on dominant points selected from the bin centroids, and turbulence intensity correction and outlier detection are conducted iteratively for refining identification results. Finally, the test results based on actual operating SCADA data demonstrate better performance in comparison with two counterparts.     

基于FIR神经网络的风电场虚拟风速传感器

风电机组风速传感器易发故障,故障可能导致机组安全风险和发电量损失。针对现行的故障处理方法因与机组控制策略紧密耦合而日益面临挑战,提出了一种基于数据处理的虚拟风速传感器原理与方法：由风电场上风向测量风速计算下风向推算风速,用推算风速取代故障传感器。着重讨论了基于FIR神经网络的推算风速计算方法和计算模型,探讨了系统实现的关键技术。实验证明了虚拟传感器的误差在机组控制系统可接受的程度内。提出的方法独立于机组自身属性,具有普遍适用性,可部署在任意类型的场,在物理传感器故障时向机组提供风速信号,支撑风电机组持续安全运行。     

Wind Farm Layout Design Using Cuckoo Search Algorithms

Wind energy has emerged as a strong alternative to fossil fuels for power generation. To generate this energy, wind turbines are placed in a wind farm. The extraction of maximum energy from these wind farms requires optimal placement of wind turbines. Due to complex nature of micrositing of wind turbines, the wind farm layout design problem is considered a complex optimization problem. In the recent past, various techniques and algorithms have been developed for optimization of energy output from wind farms. The present study proposes an optimization approach based on the cuckoo search (CS) algorithm, which is relatively a recent technique. A variant of CS is also proposed that incorporates a heuristic-based seed solution for a better performance. The proposed CS algorithms are compared with genetic and particle swarm optimization (PSO) algorithms, which have been extensively applied to wind farm layout design. Empirical results indicate that the proposed CS algorithms outperformed the genetic and PSO algorithms for the given test scenarios in terms of yearly power output and efficiency.     

Wind Farm Layout Design Using Cuckoo Search Algorithms

ABSTRACT

Wind energy has emerged as a strong alternative to fossil fuels for power generation. To generate this energy, wind turbines are placed in a wind farm. The extraction of maximum energy from these wind farms requires optimal placement of wind turbines. Due to complex nature of micrositing of wind turbines, the wind farm layout design problem is considered a complex optimization problem. In the recent past, various techniques and algorithms have been developed for optimization of energy output from wind farms. The present study proposes an optimization approach based on the cuckoo search (CS) algorithm, which is relatively a recent technique. A variant of CS is also proposed that incorporates a heuristic-based seed solution for better performance. The proposed CS algorithms are compared with genetic and particle swarm optimization algorithms which have been extensively applied to wind farm layout design. Empirical results indicate that the proposed CS algorithms outperformed the genetic and particle swarm optimization algorithms for the given test scenarios in terms of yearly power output and efficiency.     

海上风电场虚拟电子围栏技术的研究与应用

海上风电场在基建期与运维期,各类船舶随意的抛锚对风机、海缆的安全造成极大隐患,而风电场离岸距离远,环境恶劣,人员出海受到各类因素的制约。针对这些问题,提出海上风电场虚拟电子围栏技术,将海面超视距通信原理应用到实际工程,结合海上风电场数字化模型可以立体形象展示风电场升压站、风机及虚拟的电子围栏。在工程实践中对风电场及海缆周边划分虚拟电子围栏,对风电场周边往来的船舶严密监控,解决船舶抛锚对风机、海缆造成的安全隐患,全天候保障海上风电场的基建期与运维期安全。船舶在风电场周边抛锚、穿越,可以导出包含船舶MMSI(海上移动业务识别)在内的闯入记录,极大减少人员出海需求,减少风电场运维成本。     

Optimized design of patrol path for offshore wind farms based on genetic algorithm and particle swarm optimization with traveling salesman problem

With the rapid expansion of global offshore wind power market, the research on improving the full life cycle income and reducing the construction and operation and maintenance costs has attracted the attention of scholars in the industry. In view of the different aging degree and maintenance cycle of wind turbines, this paper studies the optimized design of patrol path for offshore wind farms based on genetic algorithm (GA) and particle swarm optimization (PSO) with traveling salesman problem (TSP). Firstly, the problem of patrol routing planning in offshore wind farms is described as the traveling salesman problem of shortest route optimization. Secondly, the GA and PSO algorithms are simulated and verified separately, and the patrol path distance is taken as the objective function. Finally, through simulation experiments, the optimized patrol path performances of PSO and GA are compared, which can help to find a shortest route and reduce the operation and maintenance costs.