共查询到20条相似文献,搜索用时 171 毫秒
1.
鉴于目前电力大数据总量大、数据复杂度高、价值密度低等,基于模糊ISODATA聚类算法研究了商场、宾馆酒店、办公等典型城市负荷用电特性,建立了城市负荷的建筑类型、总能耗、照明与插座用能、空调用能、动力用能、特殊和其他用能的数据维度模型用以辅助分类决策,并在不同维度、数量级的样本数据下与传统聚类算法的性能进行比较。同时与传统的基于日负荷曲线的分类方法准确率进行对比。结果表明,基于模糊ISODATA算法的城市用电行为分析模型聚类效果好、精度高,适用于当前高维度、大规模的电力大数据的分类,并在一定程度上能够克服当前电力大数据负荷分类中聚类数目设置难、易陷入局部最优等问题。研究成果可用于指导工程实践。 相似文献
2.
为有效分析开关柜的各种监测数据,减轻状态评估工作量,提出一种基于自适应粒子群优化和最小二乘向量机分析(PSO-LSSVM)的多维开关柜数据状态评估方法。首先对开关柜的多维历史监测数据进行分类,提取有效数据构建数据集,并利用K最近邻法(KNN)填补缺失数据,针对已有的开关柜历史评估结果,采用最小二乘支持向量机算法进行数据分析和训练,引入自适应粒子群算法,实现算法参数的优化,最终获得多维数据的开关柜评估模型。经实际数据检验,此评估方法能有效分析历史监测所累积的大规模数据,评估准确率较高,可有效筛选出需检修的开关柜,减轻了开关柜评估工作量,具有一定的实际应用意义。 相似文献
3.
多维数据分析可从多个角度对数据进行观察和处理,将业务型数据转化为管理型数据以获得有用信息,从而为管理决策部门提供有效支持.在数据库管理系统(SQL Server 2008)平台上应用多维数据分析方法,提出了基于火电行业环境影响评价应用方案的不同阶段:需求分析、业务关系数据库构建、多维数据仓库构建、多维数据集构建、前端报表展示,并以基于已入库的火电项目指标库为分析对象,给出了不同时期、不同区域电力建设项目的分布、投资、资源消耗、污染物排放等多维分析结果,使用户可从多角度、多侧面分析火电行业建设和发展情况,为环境管理和决策提供科学快捷的决策数据支持. 相似文献
4.
针对多能源系统中不同种类能源负荷特征提取及预测问题,提出基于特征聚类的多能源系统负荷预测方法,利用灰色关联分析系统理论对多种类能源负荷预测模型中的环境因素输入属性进行主控因素关联度分析,分别得到电、气、热、冷负荷受环境因素影响的关联度,利用卷积神经网络提取负荷数据和关联度输入数据的特征向量,利用K-means聚类算法对给定特征向量进行聚类,建立多种类能源负荷的特征聚类模型。算例结果表明,文章所提出的基于特征聚类的多能源系统负荷预测方法,能够有效提高不同种类能源负荷的预测精度。 相似文献
5.
6.
基于模糊神经网络的凝汽器故障诊断系统研究 总被引:10,自引:0,他引:10
该文根据凝汽设备的结构特点和工作特点,从理论上分析了影响凝汽器低真空各种原因,并结合现场工程师的直觉经验,建立了凝汽器低真空的故障知识库。同时,还建立了基于模糊神经模型的故障诊断系统,对凝汽器故障进行诊断。该诊断系统是由无监督自学习网络和模糊运算构成,除了能识别已经训练过的故障,还能识别未训练过的故障,并且聚类能力强,速度快,因此很符合复杂系统的故障诊断。 相似文献
7.
8.
9.
基于智能事例推理技术的凝汽器在线监测和故障诊断系统 总被引:1,自引:0,他引:1
提出了基于知识库和事例推理技术相结合的双背压凝汽器状态监测与故障诊断的方法.通过对凝汽器常见故障特点以及凝汽器主要功能的分析,结合现场经验,建立了以凝汽器真空故障为最高层次的"征兆一原因"层次化结构模型,并由此建立了层次化结构知识库,用于新事例初始化故障智能定位.提出了节点搜索法的事例检索新方法,缩短了事例平均检索时间.介绍了凝汽器在线状态监测与故障诊断系统的体系结构和工作流程.通过某600 MW机组凝汽器现场运行数据和凝汽器故障诊断实例,验证了该方法的有效性,表明系统具有较强的实用价值. 相似文献
10.
11.
12.
针对双背压凝汽器,提出了基于历史数据的实际可达最佳值的凝汽器真空目标值确定方法,并提出了凝汽器运行状态的评估指标,作为凝汽器运行状态的一种量化方法.将影响凝汽器真空的因素分为内部因素和外部因素,从外部因素出发,建立了最小二乘支持向量回归模型,用于凝汽器真空实时在线监测,为运行人员提供了当前外部环境下凝汽器真空目标值;通过对凝汽器运行状态的量化评估,为凝汽器的检修提供了依据.通过某600MW机组双背压凝汽器运行数据实例,表明了该模型对双背压凝汽器真空目标值的确定具有较好的效果,该方法具有一定的实用价值. 相似文献
13.
14.
15.
16.
17.
The formation and behavior of fog during partial condensation of humid air in a vertical tube bundle condenser has been investigated. For this purpose a special glass condenser has been constructed which allows to measure the aerosol parameters everywhere along the cooling tubes using an optical aerosol measurement system. At the operation conditions adjusted in the present work fog occurs only in the presence of foreign nuclei by heterogeneous nucleation. It is shown, that the total mass of fog being formed was not influenced by the number concentration of foreign nuclei. The formation of fog occurs immediately after the first contact of the humid air with the cooling wall due to local supersaturation. After the fog has been formed in the entry of the condenser, a strong decrease of fog particles has been observed further down with the total amount of fog being constant. The effect of various process settings on the resulting aerosol parameters has been investigated. Both simple and rigorous one-dimensional calculations and complex multi-dimensional simulations using CFD were carried out for the interpretation of experimental data. Although the multi-dimensional simulations showed strong local effects the one-dimensional models were suitable to predict the conditions for fog formation. 相似文献
18.
A fractal permeability model for bi-dispersed porous media 总被引:7,自引:0,他引:7
In this paper a fractal permeability model for bi-dispersed porous media is developed based on the fractal characteristics of pores in the media. The fractal permeability model is found to be a function of the tortuosity fractal dimension, pore area fractal dimension, sizes of particles and clusters, micro-porosity inside clusters, and the effective porosity of a medium. An analytical expression for the pore area fractal dimension is presented by approximating the unit cell by the Sierpinski-type gasket. The pore area fractal dimension and the tortuosity fractal dimension of the porous samples are determined by the box counting method. This fractal model for permeability does not contain any empirical constants. To verify the validity of the model, the predicted permeability data based on the present fractal model are compared with those of measurements. A good agreement between the fractal model prediction of permeability and experimental data is found. This verifies the validity of the present fractal permeability model for bi-dispersed porous media. 相似文献
19.
20.
Model‐based fault detection for generator cooling system in wind turbines using SCADA data
下载免费PDF全文
![点击此处可从《风能》网站下载免费的PDF全文](/ch/ext_images/free.gif)
In this work, an early fault detection system for the generator cooling of wind turbines is presented and tested. It relies on a hybrid model of the cooling system. The parameters of the generator model are estimated by an extended Kalman filter. The estimated parameters are then processed by an appropriate statistical change detection algorithm in order to detect faults in the cooling system. To validate the method, it has been tested on 3 years of historical data from 43 turbines. During the testing period, 16 faults occurred; 15 of these were detected by the developed method, and one false alarm was issued. This is an improvement compared with the current system that gives 15 detections and more than 10 false alarms. In some cases, the method detects the fault a long time before the turbine reports an alarm. A further advantage of the method is that it is based on supervisory control and data acquisition data that are available for the operator of all modern turbines. Thereby, the method can be implemented without the need to modify or install additional components in the turbines. Copyright © 2015 John Wiley & Sons, Ltd. 相似文献