Transformers Condition Evaluation Based on Bayesian Classifier

2018 3rd International Conference on Insulating Materials, Material Application and Electrical Engineering

材料科学;无线电电子学;电工学

Zhang, Xin^1 ; Li, Jianglin^2 ; Liu, Guangzhen^3 ; Liu, Liqing^1 ; Ma, Hao^1 ; Yang, Tiankai^4

Electric Power Research Institute, State Grid Tianjin Electric Power Corporation, Tianjin

300384, China^1

XJ Group Corporation, Xuchang

461000, China^2

State Grid Tianjin Electric Power Corporation, Tianjin

300010, China^3

School of Electrical and Information Engineering, Tianjin University, Tianjin

300072, China^4

关键词: Bayesian classifier;    Condition evaluation;    Condition overhaul;    Electrical tests;    Evaluation indicators;    Online monitoring;    Transformer condition assessment;    Transformer monitoring;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/452/4/042031/pdf
DOI  :  10.1088/1757-899X/452/4/042031

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

Higher requirements was put forward to accurate and efficient transformer condition assessment by the large-scale promotion of condition overhaul. Core indicators reflecting the running state of transformer were selected to establish transformer evaluation indicators system with analysis on transformer on-line monitoring, live detection and electrical test, and then the indicator scoring method and subordinating degree function of indicator score and transformer state were given. On this basis Bayesian theory was introduced briefly and a transformer condition assessment method based on Bayesian classifier was presented considering transformer monitoring and test data, the current data included, on multiple time dimensions. Finally, through analysis on transformers actual monitoring data in some power network, accurate assessment of transformer running state was made and the practicability and accuracy of this method was verified.