Fault diagnosis of power transformer based on association rules gained by rough set
Ming Qiu Zhou, Wang Tai-yong · 2010
Dissolved gas analysis (DGA) is one of the most useful techniques, which are used to detect the incipient faults of power transformer. In the past decade, various fault diagnosis techniques have been proposed that include the conventional ratio method to detect the incipient faults of power transformer. In the paper, rough set is presented to generate association rules which are used to fault diagnosis of power transformer. Rough set can mine the deep relation, association rule of power transformer is gained by rough set. By reduction of rough set, redundant feature attribute which affects the classification performance will be deleted. Then, association rule of power transformer is gained. The experimental results indicate that the method has very good results.