摘要
针对电力变压器结构、老化、故障机理复杂,具有不确定性,难以进行准确的状态评估的问题,将变压器健康状态分为良好、一般、注意、较差4种状态,提出了一种基于支持向量机的二叉树多级分类器变压器健康状态评估方法。该模型以变压器油中溶解气体的产气量和产气速率为评价指标,利用支持向量机挖掘评价指标与变压器健康状况之间的关系。
Aiming at the problem that power transformer structure, ageing, fault mechanism are complex and their conditions are difficult to evaluate accurately, a condition assessment method that synthetically considering the transformer dissolved gas analysis （DGA） technique based on support vector machine is proposed in this paper. The transformer condition is divided into four grades： ＂fine＂, ＂general＂, ＂pay attention to＂, ＂relatively poor＂, using support vector machine and binary tree to decide its condition.
出处
《电力科学与工程》
2008年第2期47-50,共4页
Electric Power Science and Engineering
关键词
变压器
支持向量机
油中溶解气体分析
状态评估
power transformer
support vector machine （SVM）
dissolved gas analysis （DGA）
condition evaluation
