Transformer oil temperature abnormity monitoring method based on density aggregation algorithm

• Main Authors: TANG JUN, MA XIAOMIN, TAN MINGYUE, MAO YIPENG
• Format: Patent
• Language: Chinese; English
• Published: 04.04.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a transformer oil temperature anomaly monitoring method based on a density aggregation algorithm, which comprises the following steps of: firstly, acquiring transformer oil temperature data, cleaning data according to working characteristics of a transformer cooling device, selecting characteristic parameters, then extracting characteristics from the parameters, extracting parameter characteristics, and obtaining an input characteristic matrix; and performing clustering processing on the normalized feature matrix by calling density aggregation based on a dynamic time warping distance, and performing anomaly detection on the oil temperature data of the transformer by using a density aggregation algorithm. 本发明提供一种基于密度聚集算法的变压器油温异常监测方法，先采集变压器油温的数据，根据变压器冷却装置的工作特性清洗数据选择出特征参数，继而从参数中进行特征提取，提取参数特征，得到输入特征矩阵。调用基于动态时间归整距离的密度聚集对归一化后的特征矩阵进行聚类处理，利用密度聚集算法进行变压器油温数据的异常检测。