基于CHSMM的变压器状态评估方法研究  

Research on Transformer State Evaluation Method Based on CHSMM

作　　者：邓燕 王旭红[1] DENG Yan;WANG Xu-hong(School of Electrical&Information Engineering,Changsha University of Science and Technology,Changsha 410114,China)

机构地区：[1]长沙理工大学电气与信息工程学院,长沙410114

出　　处：《电力学报》2021年第1期7-16,共10页Journal of Electric Power

摘　　要：为了保证电力系统可以安全、可靠运行,实时对油浸式变压器的健康状态进行评估是非常必要的。针对现有技术存在的问题,提出一种基于改进隐马尔科夫模型(Hidden Markov Model,HMM)的油浸式变压器运行状态评估方法。针对传统马尔科夫模型的缺点,进行模型改进,提出了将连续隐半马尔科夫模型(Continuous Hidden Semi-Markov Model,CHSMM)应用到基于DGA技术的变压器状态诊断。经仿真实验证明,该方法实现简单、应用方式灵活、能够精准评估油浸式变压器的运行状态。基于CHSMM的变压器状态评估方法实现了对变压器状态的有效评估,可为实际工程中油浸式变压器的状态评估提供指导。In order to ensure the safe and reliable operation of power system,it is necessary to evaluate the health status of oil-immersed transformer in real time.In view of the existing technical problems,a method for evaluating the operating status of oil-immersed transformers based on improved hidden Markov model(HMM)is proposed.Aiming at the shortcomings of the traditional Markov model,the continuous hidden semi-Markov model(CHSMM)is used to diagnose transformer faults based on DGA technology.The simulation results show that the method is simple,flexible and can accurately evaluate the operation state of oil-immersed transformer.The transformer condition evaluation method based on CHSMM can effectively evaluate the transformer condition,which can provide guidance for the condition evaluation of oil-immersed transformer in practical projects.

关 键 词：变压器 状态评估 CHSMM DGA数据 

分 类 号：TM41[电气工程—电器]