Fault diagnosis of power grid with information fusion of multi-level

Based on the multi-source data of protection, breaker and fault recorder is the future trend of fault diagnosis. Firstly, the information fusion in this paper is accomplished on characteristic layer. With the help of wavelet techniques, the firing sequence of Fuzzy Petri net can be treated. The substation fault diagnosis results as well as evaluation of the operations of protections and breakers are obtained through FPN calculation. Then a brief fault report is generated and sent to the primary station, which is used to revise the telesignal data. Finally, the total grid diagnosis result is obtained through optimization method. In the decision layer fusion, the optimization result is fused with the analysis of record through two kinds of wavelet index by improved DS evidence theory. Based on Real Time Digital System (RTDS) the package solution is proved.