Research On Fault Diagnosis Of Power Supply And Distribution System In Intelligent Building Based On Wavelet And Bayesian Networks

With the development of the times,intelligent building has become a trend,making daily life become efficient and convenient,the power supply and distribution system of intelligent building is increasingly large,it is inevitable to have failures,so the security of intelligent building is necessary.Once there is a fault in the power supply and distribution system in intelligent building,regulate the workload of staff,is bound to increase power to affect people's normal life,Serious events can make the whole building damage and unnecessary economic losses,and had a huge impact on power quality,and even cause personal casualty accidents,so the fault diagnosis of power supply and distribution system in intelligent building technology is particularly important,the study of fault diagnosis is of great significance.The fault diagnosis method proposed in this paper is mainly aimed at the fault problems prone to occur in intelligent buildings.The fault types in the power supply and distribution system of intelligent buildings are more than those in traditional buildings,and the consequences will be more serious.Intelligent buildings have more sensors and intelligent devices than traditional buildings.Due to the complexity of its system,in addition to the four most basic faults in traditional buildings,such as three-phase short circuit,two-phase ground short circuit,two-phase short circuit and single-phase short circuit,serious phenomena such as multiple faults will also occur.For these diversified situations,more unknown or more complex faults are hidden in them,and more accurate diagnostic methods are needed to make judgments.Based on the characteristics of the power supply and distribution system of the intelligent building,the topological structure and fault characteristics of the power network are analyzed theoretically,and the fault types are determined.This paper proposes a fault diagnosis method for power supply and distribution network of intelligent building based on wavelet transform and bayesian network.In order to verify that the fault diagnosis method proposed in this paper is more advantageous than the same type of fault diagnosis method for power supply and distribution system of intelligent building,the simulation study is carried out with an example at last.The fault components can be correctly identified for simple faults and complex multiple faults,and can be effectively identified for protection and circuit breaker in the presence of rejection,misoperation,misstatement,misreporting,timely marking errors,etc.At the same time,the time point constraint interval of component fault can be deduced,which has high fault tolerance.MATLAB programming is used for matrix calculation reasoning,the diagnosis time is no more than 1s,and has nothing to do with the complexity of the fault.It can be seen that the proposed model can meet the real-time requirements of online fault diagnosis applications.In order to make the final result more objective and accurate,the method proposed in this paper is compared with other fault diagnosis methods,and the simulation experiment is carried out under the same conditions with four methods: neural network method,rough set method,model prediction method and bayesian network method.Therefore,this method can effectively improve the accuracy of fault diagnosis.