Bayesian network methods for fault diagnosis of power systems

To solve the incompleteness and uncertainty of information existing in power system fault diagnosis, a new fault diagnosis method based on Bayesian network is proposed in this paper. The models are special Bayesian networks consisting of Noisy-Or and Noisy-And nodes, which are converted from the logic relationship among section fault, protective relay operation and circuit breaker trip. The Bayesian network models using imperfect information are established for fault diagnosis according to the operating rules of protective devices. Diagnostic results of instance proved the effectiveness and superiority of the proposed method.