Transformers Condition Evaluation Based on Bayesian Classifier. Issue 4 (December 2018)

• Record Type: Journal Article
• Authors: Zhang, Xin; Li, Jianglin; Liu, Guangzhen; Liu, Liqing; Ma, Hao; Yang, Tiankai
• Is Part Of: IOP conference series. Volume 452:Issue 4(2018)
• Publication Date: 2018-12
• Subjects: Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/452/4/042031
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: 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.