基于OPTICS的变电设备状态监测异常数据过滤算法

An OPTICS Clustering-Based Abnormal Data Filtering Algorithm for Condition Monitoring of Power Equipment

针对变电一次设备状态监测中普遍存在的异常数据问题,提出了一种基于点排序识别聚类结构(Ordering Points to Identify the Clustering Structure,OPTICS)的状态监测异常数据过滤算法。通过对一次设备状态监测的历史数据进行异常数据特征分析,建立了基于密度聚类的异常数据过滤机制。并以某110 k V变电站一次设备变压器油色谱以及GIS SF6密度微水实验为例,对该算法的异常数据检测效果进行了验证。该算法与传统异常数据过滤算法的对比试验结果表明,该算法能够准确地识别异常数据的特征,有效过滤状态监测中的异常数据,显著降低噪声干扰,从而提高数据的可靠性。

Aiming at the widespread abnormal data in substation primary equipment condition monitoring, this paper proposes an OPTICS（Ordering Points to Identify the Clustering Structure, OPTICS） clustering-based condition monitoring abnormal data fi ltering algorithm. Through the characteristic analysis of historical primary equipment condition monitoring data, the abnormal data fi ltering mechanism was built based on density clustering. The effectiveness of detecting abnormal data was verifi ed through the experiments on a 110 k V substation equipment transformer oil chromatography and the GIS SF6 density micro water. Compared with traditional abnormal data fi ltering algorithms, the OPTICS clustering-based algorithm has shown signifi cant performance in identifying the features of abnormal data as well as fi ltering condition monitoring abnormal data, noises were reduced effectively, and the overall reliability of condition monitoring data was also improved.