According to the uncertainty and fuzzy problems in gas turbine gas path fault diagnosis, a gas turbine gas path fault diagnosis technology based on the fuzzy Petri net was presented. First, the neural network technology was introduced to solve the uncertainty of the operation normal value, and the fuzzy math was applied to solve the question of operation parameter deviation determining. Then, according to the fault diagnosis Petri net's characteristic, the matrix format and the rule of transition enabling and firing of the fuzzy Petri net were modified and defined. And a fault diagnosis reasoning algorithm based on the fuzzy Petri net was put forward, which can achieve a quick diagnosis with simple matrix operation. Last, the practicability and validity of the technology was proved by an example of gas path fault diagnosis of a JT9D engine.
展开▼
