Multi-agent and Bayesian network applied in transformer faults diagnosis

Once failures for large transformer power occur, which will result in catastrophic economic losses and social impact. Therefore, it is necessary to design and apply a state monitoring and fault diagnosis system for large-scale transformer in order to improve the reliability and accuracy for power transformer during its running, which will benefit increasing the power enterprise economic performance, promoting economic and social development The analysis to dissolved gases in a transformer is useful to the diagnosis of the transformer faults. Due to the shortcomings of the randomness and uncertainty of power transformer fault diagnosis data, the benefits of the Bayesian network classifiers and the features of multi-agent, this paper introduces a multi-agent system diagnosis model, and the result of practical sample verifies the effectiveness of the proposed model.