基于Microsoft时序算法的电容器组电容预测及预警  

Capacitance Prediction and Pre-warning of Capacitor Bank Based on Microsoft Time Sequence Algorithm

作　　者：段晓波[1] 高晶晶[2] 胡文平[1] 周文[1] 齐林海 

机构地区：[1]国网河北省电力公司电力科学研究院,河北石家庄050021 [2]华北电力大学,北京102206

出　　处：《电力电容器与无功补偿》2017年第1期22-27,34,共7页Power Capacitor & Reactive Power Compensation

摘　　要：准确预测电容器组在一段时间内的电容,分析其变化趋势,对并联电容器组的安全使用、延长寿命有很重要的意义。本文提出一种基于Microsoft时序算法,采用电能质量监测数据的10 k V侧并联电容器组电容预测模型,并在此基础上设计了并联电容组电容趋势分析及预测预警系统。通过该系统,用户不仅能够监测电容器组的运行状态,为电容器组故障分析提供可靠依据,而且可以预测电容器组电容值的变化趋势,并实现其寿命预警。实际运行效果验证了该模型的可行性与准确性。Accurate capacitance prediction of capacitor bank within a time period and its variation trend analysis are of great importance for safe operation and life extension of shunt capacitor bank. In this paper,a kind of capacitance prediction model of shunt capacitor bank at 10 kV side based on the Microsoft time sequence algorithm and with adoption of power quality monitoring data is proposed and,on this basis,the capacitance trend analysis and prediction as well as pre-warning system is designed. The user,throughout this system,can be able to not only monitor the operation condition of capacitor bank,provide reliable evidence,but also predict the capacitance variation trend of the capacitor bank as well as achieve its life pre-warning. Both the feasibility and accuracy of the model is verified by the actual operation result.

关 键 词：并联电容器组 趋势预测 预警 Microsoft时序算法 电能质量监测系统 

分 类 号：TM53[电气工程—电器]