Transformer fault diagnosis based on IAFSA and rough set
Chen Xiaoqing, Liu Jue-min, Huang Ying-wei, Fu Bo · 2012
With For a large number of incomplete fault data, the traditional artificial intelligence methods based cannot effectively and timely analysis or can not be accurately diagnosed or misdiagnosed because of the ill-conditioned problem caused by inefficient discretization approaches. A method based on rough set theory integrated with improved artificial fish-swarm algorithm (IAFSA) was presented in this paper for fault diagnosis of transformer. Firstly, the values of dissolved gas-in-oil analysis (DGA) were taken as conditional attributes and the type faults were taken as decision attributes. Various relations between fault and symptom were connected and decision table was established. the improved artificial fish-swarm algorithm is used to discrete continuous attribute; then, using the rough set theory to reduce the decision table. The simplified decision rules were got, which greatly simplifies the difficulty of diagnosis The experimental results indicate that the method has increased the diagnosis accuracy compared with traditional algorithm.