Power System Fault Diagnosis Method Based On Improved Bayesian Network

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 methods such as expert system, artificial neural network, optimization method, Petri network, rough set theory and fuzzy set theory have been applied to power system fault diagnosis, and many publications have been presented. However, there are still some drawbacks for those methods.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. Furthermore, according to the trait of Bayesian network approach, a MAS fault diagnosis system structure is designed. The contents in this paper include the following aspects:1. 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.2. 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.3. The Bayesian network approach is presented to deal with power system fault diagnosis, and case study proved the effectiveness of this approach.4. The algorithm of probability learning in fault diagnosis Bayesian network is proposed.5. According to the trait of Bayesian network approach, a MAS fault diagnosis system structure is presented.