Application of Fuzzy Petri net expert system in insulator running state

Abstract

Because insulator has complex operating environment and its infection factors have interaction, the diagnosis of insulatorpsila running state is very difficult. Fuzzy Petri net has better knowledge expression ability for designing dynamic knowledge expert system. Fuzzy Petri nets are used to design intelligent expert diagnosis system for insulatorpsila running state in this paper. Fuzzy Petri net can describe the relative degree of each proposition in the antecedent contributing to the consequent accurately. In order to reason and learn expediently, FPN without loop is transformed into hierarchy model and continuous functions are built to approximate transition firing and fuzzy reasoning. The adaptive learning techniques based on improved learning way are used to learn and train the parameters of fuzzy production rules in FPN. The experimentation result shows the designed FPN has strong learn ability. These techniques used in this paper are quite effective in expert diagnosis system.