A power network fault diagnosis method based on rough set theory and fault information networks
Lin-Xian Wang · Relay · 2008
When complex fault occurs or uncertain factors appear,such as mal-operation,miss operation and missing messages because of channel disturbance,the existing power system diagnosis methods based on switch and protection messages do not reach correct conclusions.To settle this problem,this paper proposes a new method to diagnose faults in power network in which the fault information can be made good use of.At first,the protections and circuit breakers are taken as conditional attributes and faulty region as decision-making attribute to investigate various faults and establish decision table.By use of attribute reducing method based on cognizable matrix and information entropy,the optimal attribute reduction combination is extracted.Then using the result of the fault information analysis,the values in the optimal attribute reduction combination are amended.Finally,the diagnosis result could be given by the decision table.The practical fault diagnosis software is programmed based on VC++ 6.0.Results of calculation examples show that the method is correct and effective,can improve the fault tolerance capability,and can remedy limitations of using the protection and switch messages for fault diagnosis effectively,so the method is available.