Research On Fault Diagnosis Of Distribution Network Based On Data Ming

Electric power industry is the pillar industry of China's economic development,and its advanced technology affects the development of national economy.In this paper,the application of data mining based on rough set and Bayesian network in fault diagnosis of distribution network is studied.The research achievements in the field of fault diagnosis at home and abroad,analyzes the advantages of data mining technology in this field,this paper proposes a method of mining technology and Bayesian network data based on rough set,and analyzed the application of fault diagnosis in distribution network.Firstly,according to the distribution network model,the original decision table is formed by the principle of relay protection.Secondly,according to the formation rules of discernibility matrix in rough set theory.Then,according to the method of rough set,we extract the kernel attribute.If the result is not unique,the theory of average mutual information based on information entropy is introduced.Finally,the Bayesian network model is established according to the simplest kernel attribute,and then the probability is calculated according to the Bayesian inference model.The example shows that the data mining based on rough set and Bayesian network has a good application prospect in distribution network fault diagnosis.