Fault diagnosis via fuzzy time analysis

In this paper, we propose a kind of extended fuzzy Petri net (EFPN) which is used in building the fault diagnosis model. First, we define a weighted mathematical expectation μ to calculate the distribution center of point-in-time with weight, and give the definition of weighted variance v to evaluate the indexes of discrete degree of the point-in-time with weight. Second, the maximum membership function φ and the fuzzy timestamp function τ are proposed, and these functions are used for calculating the temporal uncertainty and the different temporal distribution of TSSs. Finally, by using μ, v, φ and τ, the fault diagnosis model of substation equipments is constructed to analyze the confidence degree of all possible faults. Moreover, the repetitiveness of signals is analyzed to assess the influence degree caused by uncertainty factors which affect the results of reasoning. Simulation experiment shows that the EFPN is an effective substation fault diagnosis model, and it can be used to deal with the temporal uncertainty problem which is presented among the TSSs. More important is that the EFPN offers a new approach to make qualitative and quantitative analysis on the temporal relationship of the TSSs.