基于时间序列的分布式光伏电站发电数据采集方法

由于当前方法对发电数据进行采集时,没有对发电数据的缺失值进行修复,存在缺失数据修复前数据采集精度差、与实际采集数据相差多的问题。该文提出一种基于时间序列的分布式光伏电站发电数据采集方法。根据光伏电站受到的不同影响,构建了负荷异常值类型的时间序列模型,利用该模型对异常数据负荷点进行剔除,由于剔除后的数据存在缺失值,因此对其进行修复;根据修复结果,采用BP神经网络对发电数据进行采集。实验结果表明,通过对该方法进行缺失数据修复前后对比测试、不同方法与实际指标数据采集测试,验证了该方法的有效性强、实用性高。

基于时空特征深度融合的双馈式风力发电机故障早期预测

风力发电机组监控与数据采集(SCADA)系统记录了机组运行参数,包含丰富的运行状态变化信息,为风力发电机组的健康状态识别提供了数据来源。提出一种基于自注意力机制级联的时空特征深度融合网络模型(SC-TSFN),模型采用空洞卷积层增大感受野,提取不同变量之间的空间特征,通过双向长短期记忆网络学习空间特征前后时间依赖性,自注意力机制突出关键变量空间特征权重以及动态调节局部与全局时间特征信息。对2.0 MW风电机组10 min间隔SCADA数据分析结果表明,该方法实现了风力发电机故障的早期预测并消除了误报。

An Automatic Dust Removal Device Based on SCM for Solar Panels

This paper introduces a set of automatic dust removal device for street lamp solar panels. The device realizes the automatic dust removal for street lamp solar panels by three steps consisting of data acquisition, automatic control and mechanical dust removal. Our scheme is as follows, according to the comparison between the actual power generation and the relatively ideal condition of power generation of solar panels, we selectively conduct dust removal operation to panels. The paper demonstrates the feasibiliW of the technology based on the example of street lamp solar panels （40w）. According to the calculation, the solar panels equipped with our device will greatly improve the power generation efficiency of solar panels, which means there will be 32 more degrees generated every year. Extension and application of the technique device will be beneficial for the improvement of solar panels power generation efficiency and the extension of the service life of the panels.