Modifying the inconsistency of Bayesian networks and a comparison study for fault location on electricity distribution feeders

The Bayesian network is a probabilistic graphical model in which a problem is structured as a set of parameters and the probabilistic relationships among them. Researchers have effectively applied Bayesian network in many fields to incorporate the expert knowledge and data for updating prior belief in the light of new evidence. However, there is inconsistency between priors and inference rules of a Bayesian network in real settings. This study aims to fill the gap for resolving the inconsistency problem involved in Bayesian networks. In particular, a Bayesian network, on the basis of expert knowledge and historical data, was constructed for fault diagnosis on power distribution feeders. We proposed a new method to modify the inconsistency between priors and inference rules of a Bayesian network and compared it with the existing methods, with real data. This study concludes with discussions on results and future research.