基于变压器老化的状态风险评估研究  

Research on the Risk Assessment Based on Transformer Aging

作　　者：叶海峰 罗颖婷 许海林 李炀 李国政 YE Haifeng;LUO Yingting;XU Hailin;LI Yang;LI Guozheng(Electric Power Research Institute,Guangdong Power Grid Co. Ltd,Guangzhou 510000;Brilliant-Data,Guangzhou. Ltd,Guangzhou 510000)

机构地区：[1]广东电网有限责任公司电力科学研究院,广州510000 [2]广州佰聆数据股份有限公司,广州510000

出　　处：《微型电脑应用》2019年第1期10-14,共5页Microcomputer Applications

基　　金：中国南方电网有限责任公司科技项目(GDKJXM20162560)

摘　　要：在变压器状态风险评估的实际应用与管理中,权重系数的确定是当前状态风险评估的主要难题。基于变压器老化机理分析完成变压器状态评估指标体系的构建,分别从变压器自然老化与变压器加速老化两个过程,对权重系数进行考察;针对自然老化过程,提出了基于层次分析法与关联规则挖掘的权重系数确定方法;针对加速老化过程,提出了基于贝叶斯网络的权重系数确定方法;并基于上述权重系数,完成了变压器状态风险评估模型的构建工作。实践表明,该评估模型能解决传统状态评估方法的缺陷和不足,对变压器状态风险评估有较好的指导作用。In the actual application and management of transformer risk assessment, the determination of the weight coefficient is the main problem in the current risk assessment. This paper builds the transformer condition evaluation index system based on transformer aging mechanism, and examines the weight coefficient from the natural aging process of the transformer and the accelerated aging process of the transformer. For the natural aging process of the transformer, based on the analytic hierarchy process and association rules, a weight coefficient determination method is proposed. For transformer accelerated aging process, a weight coefficient determination method is proposed based on Bayesian network. Practice shows that the assessment model can solve the defects and deficiencies of the traditional assessment methods, and plays a good guiding role in the risk assessment of transformer state.

关 键 词：风险评估 变压器 老化 贝叶斯网络 关联规则 

分 类 号：TM385[电气工程—电机]