聚类分析在电力变压器不良数据识别中的应用

为了发现变压器内部潜伏性故障及其发展程度,针对电力变压器的油中气体成份数据进行聚类分析。利用K-means算法对电力变压器的原始数据进行处理,利用ISODATA算法对经过K-means算法处理的数据在初始聚类中心进行聚类,最终得到变压器五种气体参数的ISODATA算法聚类结果。

Gather a Type Analysis in the Bad Data of the Electric Power Transformer Identify of Application

For the sake of delitescence in the inner part of the detection transformer break down and it development degree,aim at the air composition in the oil of electric power transformer analysis data to carry on to gather a type analysis.The merit and shortcoming which pass to gather a type of calculate way to the K-means and the ISODATA carry on comparison,end choose to be with the ISODATA calculate way carry on gathering a type analysis.The originality data which make use of K-means calculate way to the electric power transformer carry on processing,will it result Be an ISODATA calculate way beginning start to gather a type of center to carry on gathering a type,end get five kinds of ISODATA calculate way of air parameter of transformer to gather a type result.