Research On Transmission Grid Fault Diagnosis Method Based On Time Series Intuitionistic Fuzzy Inhibitor Arc Petri Net

With the rapid development of China’s national economy,people’s demand for safe,high-quality,and reliable electric power in production and life has been increasing.At present,China’s power grid is mainly composed of 500KV power grid,and the provincial grids are interconnected to form a large-scale and complex power network.In addition,the complexity of the system characterizes the complexity of information to a large extent.Therefore,when the power grid fails,the complexity of the alarm information poses a more severe challenge to the diagnostic performance of the fault diagnosis system.Based on the analysis of the existing intelligent fault diagnosis methods for power grids,a novel method for fault diagnosis of transmission grids with intuitionistic fuzzy inhibitor arc Petri nets that takes into account the time series matching factors is proposed.First,the similarity matching method of time series to process the alarm information with time scales is applied.This method takes both the editing distance and the time distance into account.Compared with the timing relationship inherent in the Petri net,this method can not only simultaneously calculate the time difference and sequence difference at the time of fault occurrence,but also fully consider the impact of timing on fault diagnosis.At the same time,we use the characteristics of intuitionistic fuzzy sets to fully consider the impact of uncertain and incomplete information on diagnosis results from the degree of information membership and non-membership.Secondly,the traditional Petri net fault diagnosis model has various problems:the action logic of relay protection cannot be fully reflected in the model structure;the accuracy,fault tolerance and speed of the model cannot meet the requirements of real-time online fault diagnosis;the human subjective factors can lead to errors in the diagnosis of grid faults.Based on these problems,an intuitionistic fuzzy Petri net fault diagnosis method with inhibitor arc is proposed.Inhibitor arc tuples are introduced into intuitionistic fuzzy Petri net,which enables the protection action logic to be reflected in the model structure and the BP algorithm is used to train weight parameters in the model to solve the fault diagnosis errors caused by human subjective factors.To summary,a general model of TIFIAPN integrated power network fault diagnosis is constructed,and the corresponding inference algorithm is formed.The effectiveness of this method is verified by the simulation of a local power system case,and a comprehensive test platform is built based on Lab VIEW language,which verifies the effectiveness of the power grid fault diagnosis method proposed in this thesis.