Applications And Research Of The Bayesian Network In Power System Fault Diagnosis

With the increasing scale and more complex structure of power system, further requests have been advanced in power system fault diagnosis. The developments in Artificial Intelligent technology provide plentiful theories and methods for this research field. A lot of method such as expert system, artificial neural network, optimization method, rough set theory and fuzzy set theory has been applied to power system fault diagnosis, and many publications have been presented. However, there are still some drawbacks for those methods.The Bayesian Network is a directed acyclic graph presenting directly the reliance relations among many variables. It depicts the cause and effect relations by a directed acyclic graph and the chummy relations by a conditional probability distribution table among all nodes. Moreover, we can incorporate the prior knowledge into current data effectively and get a more reasonable result. Especially when the current data are scarce or hard to obtain, the advantage of the Bayesian Network is evident.Aiming at the incompleteness and uncertainty of information existing in power system fault diagnosis and taking temporal order attribute of information into account, a new fault diagnosis approach based on Bayesian network is proposed in this paper. The contents in this paper include the following aspects: Described the Bayesian network of parameter learning and structure learning; A power system fault diagnosis model based on Bayesian network has been proposed. Moreover, the temporal order attribute of information is considered in the Bayesian network model; Researched the issue of data pretreatment, the algorithm of identify the coherence of temporal order information and the method of state estimation for incomplete information are proposed; The Bayesian network approach is presented to deal with power system fault diagnosis, and so on.