Network fault diagnosis method for hierarchical fuzzy petri net based on integrated variable weight

Abstract

The invention discloses a network fault diagnosis method for a hierarchical fuzzy petri net based on integrated variable weight. The network fault diagnosis method comprises the following steps that 1, suspicious fault components are searched in a fault area by using a wiring analysis method; 2, double-layer fuzzy petri net diagnostic models are established for the suspicious fault components separately; 3, the suspicious fault components are subjected to the timing information check, and the confidence coefficient of the corresponding library which does not meet the delay constraint in the models is corrected; and 4, the component failure rate is calculated by using the fixed weight and the integrated variable weight separately, and the criteria of four conditions that the components arenormal, the components fail, the components fail but the warning information partially misses and the components are normal but misinformation exists. In view of the fact that when a traditional fixedweighting method performs fault reasoning under the condition that the winding information partially misses, the faulty line is possibly misjudged as the fault of the non-faulty line, the determiningmethod of the information missing and the information misinformation is provided, and the accuracy of the fault diagnosis is improved.

Description

technical field [0001] The method relates to the field of power fault diagnosis, in particular to a method for fault diagnosis of a hierarchical fuzzy petri network power grid based on comprehensive variable weight. Background technique [0002] It is of great significance to study the grid fault diagnosis method to ensure the safe operation of the grid. At present, the research methods of power system fault diagnosis include expert system, artificial neural network, petri network, rough set theory, fuzzy set theory, optimization technology and multi-agent system, etc. The fuzzy petri nets proposed by experts can not only describe dynamic parallel or sequential failure behaviors through simple graph structures, but also can make uncertain state reasoning through matrix operations. However, the existing fault diagnosis technology based on fuzzy petri nets adopts the fixed weighting method, that is, experts assign fixed weights to the corresponding components according to the...

AI Technical Summary

Problems solved by technology

However, the existing fault diagnosis technology based on fuzzy petri nets adopts the fixed weighting method, that is, experts assign fixed weights to the corresponding components according to the priority order of protection and circuit breaker action, and this weighting method only reflects the evaluation subjectively. The relative importance of the elements does not consider the dynamic impact of the state level of the evaluation element itself on decision-making, so the evaluation results may deviate from the actual situation, which is not conducive to the comprehensive diagnosis of power grid faults

Images