广东电力Issue(12)：104-108,5.DOI:10.3969/j.issn.1007-290X.2015.12.020
基于耦合隐马尔可夫模型的变压器故障诊断研究
Research on Transformer Fault Diagnosis Based on Coupled Hidden Markov Model
摘要
Abstract
In allusion to problems of criteria for dissolved gas analysis (DGA)technology being too absolute and coding being incomplete as well as single-state sequence structure of hidden Markov model (HMM)constraining capacity of multi-channel information fusion,a kind of method for fault diagnosis based on coupled HMM is proposed. Transformer oil spectrum data is used for model training and state evaluation testing that verifies feasibility and effectiveness of this method. Example re-sults indicate that accuracy rate of this diagnosis method is superior to that of the method based on HMM which means effec-tiveness to reduce risks of erroneous judegement.关键词
电力变压器/故障诊断/隐马尔可夫模型/耦合隐马尔可夫模型/油中溶解气体分析Key words
electric power transformer/fault diagnosis/hidden Markov model/coupled hidden Markov model/dissolved gas analysis分类
信息技术与安全科学引用本文复制引用
过浩,王智博,赵丽莉,朱超..基于耦合隐马尔可夫模型的变压器故障诊断研究[J].广东电力,2015,(12):104-108,5.基金项目
国家高技术研究发展计划(863计划)项目资助(2013AA050601) （863计划）
