Abstract:At present, the analysis of dissolved gas in oil is one of the most reliable methods for the condition analysis of oil-immersed transformers. Aiming at the hidden danger of transformer overheating, this paper proposes an early warning method for the hidden danger of transformer overheating based on gas composition analysis. Firstly, the K-level difference method and one-class support vector machine are used to establish an early warning model that can identify the early hidden dangers of transformers. Secondly, following a unique alarm triggering mechanism, it is com- prehensively judged whether the current transformer has hidden dangers of overheating. Finally, the verification of real transformer data shows that the proposed method has high identification sensitivity.
谭翼坤, 陈明, 黄腾, 乔苏朋, 李志军. 基于气体成分分析的变压器过热隐患预警方法[J]. 电气技术, 2022, 23(10): 51-58.
TAN Yikun, CHEN Ming, HUANG Teng, QIAO Supeng, LI Zhijun. An early warning method for transformer overheating based on gas composition analysis. Electrical Engineering, 2022, 23(10): 51-58.