基于模糊理论和时间序列分析的开关柜在线健康状态评估与预测辅助系统研究

发布时间：2018-01-07 00:34

本文关键词：基于模糊理论和时间序列分析的开关柜在线健康状态评估与预测辅助系统研究　出处：《安徽师范大学》2016年硕士论文　论文类型：学位论文

【摘要】：开关柜作为电网系统中最关键和最复杂的设备之一,在保证电网系统的安全可靠上发挥着重要作用。但总会因为凝露、局部放电、绝缘老化、电弧光以及触头发热等一系列异常状况的发生,严重影响设备的使用寿命,甚至会诱发重大事故,造成生命财产的损失。从目前开关柜运行、维护的实际情况看,开关柜中的很多隐患都不能被实时监控,事故发生后也不能进行取证和重新推演事故发生过程;另外,在日常运行过程中,尚未对开关柜的健康状态进行科学评估,更未对其状态的变化趋势做适度预测。针对上述问题和需求,本文研究并设计了一套基于模糊理论和时间序列分析的开关柜在线健康状态评估与预测辅助系统,对开关柜的重要运行状态参数进行实时在线监测,并根据实时监测到的最新状态数据对开关柜的健康状态进行全面综合评估,同时利用系统监测采集到的历史数据对开关柜的状态变化趋势进行预测,实现了对开关柜的状态评估和事故预警,方便了巡检人员实时了解开关柜的健康状态和发展趋势,为设备检修提供重要的参考信息。首先,基于预警动态修正权重的模糊综合评判法,建立了开关柜健康状态综合评估模型,实验结果表明本文建立的评估模型符合电力行业的实际标准和需求。然后,基于粒子群优化的动态自适应指数平滑模型,以开关柜的历史监测数据作为时间序列,建立了开关柜状态变化预测模型。仿真结果表明该模型较好地把握了开关柜状态变化的趋势,有助于电力巡检人员对设备的巡检。最后,根据电力行业对开关柜实时运行状态的需求,设计了一套基于模糊理论和时间序列分析的开关柜在线健康状态评估与预测辅助系统。该系统利用传感器网络实现了数据采集、存储、管理、评估与预测一体化,对电网安全可靠运行起到了辅助决策的作用。
[Abstract]:As one of the most important and complex equipments in power system, switchgear plays an important role in ensuring the safety and reliability of power system. However, it is always due to condensation, partial discharge, insulation aging. The occurrence of a series of abnormal conditions, such as arc light and contact heating, seriously affects the service life of the equipment, and even causes serious accidents, resulting in the loss of life and property. The actual situation of maintenance, many hidden dangers in the switchgear can not be real-time monitoring, after the accident can not be obtained evidence and re-extrapolation of the accident process; In addition, in the course of daily operation, the health status of switchgear has not been scientifically evaluated, and the change trend of its state has not been properly predicted. Based on fuzzy theory and time series analysis, a set of on-line health evaluation and prediction assistant system for switchgear is studied and designed in this paper, and real-time on-line monitoring of important operating state parameters of switchgear is carried out. According to the latest state data of real-time monitoring, the health status of switchgear is comprehensively evaluated, and the trend of state change of switchgear is forecasted by using the historical data collected by system monitoring. It realizes the state evaluation and accident warning of switchgear, facilitates the inspectors to understand the health status and development trend of switchgear in real time, and provides important reference information for equipment maintenance. Based on the fuzzy comprehensive evaluation method of dynamic modification weight of early warning, a comprehensive assessment model of switchgear health state is established. The experimental results show that the evaluation model established in this paper accords with the actual standards and needs of the power industry. Then. A dynamic adaptive exponential smoothing model based on particle swarm optimization (PSO) is proposed. The historical monitoring data of switchgear are used as time series. The simulation results show that the model has a good grasp of the state change trend of the switchgear, which is helpful for the inspection of the equipment by the power inspector. Finally, the simulation results show that the model has a good understanding of the trend of the state change of the switchgear. According to the needs of the power industry to the real-time operation of switchgear. Based on fuzzy theory and time series analysis, an on-line health evaluation and prediction assistant system for switchgear is designed, which realizes data acquisition, storage and management by using sensor network. The integration of evaluation and prediction plays an auxiliary role in power grid safe and reliable operation.
【学位授予单位】：安徽师范大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：O159;O211.61;TM591

【参考文献】