基于改进k-medoids聚类和碳约束的变压器状态异常大数据诊断方法研究

宋金伟; 李俊妮; 宣东海; 吴海涵

宋金伟,李俊妮,宣东海,吴海涵.基于改进k-medoids聚类和碳约束的变压器状态异常大数据诊断方法研究[J].电测与仪表,2026,63(5):20-29.
SONG Jinwei,LI Junni,XUAN Donghai,WU Haihan.Research on big data diagnosis method of transformer abnormal state based on improved k-medoids clustering and carbon constraint[J].Electrical Measurement & Instrumentation,2026,63(5):20-29.

基于改进k-medoids聚类和碳约束的变压器状态异常大数据诊断方法研究

Research on big data diagnosis method of transformer abnormal state based on improved k-medoids clustering and carbon constraint

DOI：

中文关键词: k-medoids聚类变压器状态诊断声纹特征局部密度评估自适应替代混沌搜索

英文关键词:k-medoids clustering transformer condition diagnosis voiceprint features local density assessment adaptive substitution chaos search

基金项目:国家电网公司大数据中心科技项目《基于声纹识别的变压器典型状态在线监测与智能诊断》(SGSJ0000SJJS2100079)

作者中文名	作者英文名	单位
宋金伟	SONG Jinwei	国家电网公司大数据中心
李俊妮	LI Junni	国家电网公司大数据中心
宣东海	XUAN Donghai	国家电网公司大数据中心
吴海涵	WU Haihan	国家电网公司大数据中心

摘要点击次数: 70

中文摘要:

为了进一步提升碳约束型变压器运行状态的诊断准确率和诊断效率,基于改进k-medoids聚类理论提出了变压器状态异常诊断方法,将变压器运行状态划分为正常、预警、异常、故障四种状态作为k-medoids聚类目标。模型首先获得变压器运行状态大数据,其中声纹特征指标采用梅尔倒谱特征作为衡量变压器异常振动声响的标准。接着对变压器运行大数据基于其物理特性进行归一化和标准化,便于聚类模型输入。然后针对传统k-medoids聚类过程引入三项措施进行改进,分别为基于局部密度评估的初始聚类中心生成、自适应替代方向调整以及聚类更新的混沌搜索,通过改进措施优化初始聚类中心生成并提升寻优效率,避免寻优过早陷入局部最优聚类点。最后将某地区碳约束型电网变压器历史运行大数据划分为训练组和测试组,基于训练组来进行k-medoids聚类网络的优化,并将训练完成的k-medoids聚类用于测试组的变压器运行状态聚类和诊断,验证了所提出模型的正确性和有效性。

英文摘要:

In order to further improve the diagnostic accuracy and diagnostic efficiency of carbon constrained type transformer operating state, a transformer state anomaly diagnosis method is proposed based on the improved k-medoids clustering theory. The transformer operating state is divided into four states : normal, early warning, abnormal and fault as the k-medoids clustering target. The model first obtains the running state data of the transformer, and the voiceprint feature index uses the Mel cepstrum feature as the standard to measure the abnormal vibration and sound of the transformer. Then, the transformer operation data is normalized and standardized based on its physical characteristics, which is convenient for clustering model input. Then, three measures are introduced to improve the traditional k-medoids clustering process, which are the initial clustering center generation based on local density evaluation, the adaptive substitution direction adjustment and the chaotic search of clustering update. The initial clustering center generation is optimized by the improvement measures and the optimization efficiency is improved to avoid prematurely falling into the local optimal clustering point. Finally, the historical operation data of a regional power grid transformer are divided into a training group and a test group. The k-medoids clustering network is optimized based on the training group, and the trained k-medoids clustering is used for the transformer operation state clustering and diagnosis of the test group. The correctness of the proposed model is verified.

查看全文查看/发表评论下载PDF阅读器

关闭