Bayesian Network Based Fault Section Estimation in Power Systems

In this paper, a novel method for fault section estimation in power systems based on Bayesian network is presented. The main contributions of this paper include the following two aspects. One is that the fault diagnosis models based on Bayesian network are proposed, which are converted from the logic relationship among section fault, protective relay operation and circuit breaker trip. This method is very simple, but can perfectly treat with the uncertain information existing in power system fault diagnosis. Another is that the method is developed for creating every section´s diagnosis network automatically, thus the fault diagnosis can be fulfilled in a very short time for large-scale power system and can be implemented online. Diagnostic results of instance show that the proposed method is efficient and correct, and is very suitable for complex fault diagnosis problems, especially for the multiple-section fault cases and for the cases where protective relays and circuit breakers malfunction