Periodic analysis on gas path fault diagnosis of gas turbines

The gas path fault diagnosis is considered widely to ensure the economy, safety and practicability of gas turbines. Traditional gas path diagnosis methods are vulnerable to various uncertainties, resulting in a deviation between the diagnostic results and the real states, which brings huge potential safety hazard to industrial production. Periodic analysis can suppress the uncertainty interference and extract accurately the features of performance parameters to improve the accuracy of health evaluation. Motivated by these, a novel periodic analysis method is proposed for detecting gas path faults, namely the changing periodicity of performance parameters representing the health state of gas turbine is detected to determine whether gas path fault occurs. It is theoretically analyzed that the relationship between the periodicity of observed performance parameters and that of boundary conditions, system uncertainties, and thermodynamic parameters. The simulation experiments are performed to analyze the effects of gas path faults on periodicity of boundary conditions, system uncertainties and thermodynamic parameters. The results show that most gas path faults break the periodicity of performance parameters, proving that the operating states can be monitored through the periodic analysis of performance parameters. An online diagnosis procedure is further proposed by combining signal decomposition and rolling periodic extraction method to judge whether the gas turbine is in health or not. The validity is verified by comparing the periodicity of performance parameters under healthy and fault states. Periodic analysis suppresses the effects of system and parameter uncertainties and detects sensitively gas path faults, which provides a new idea for the fault diagnosis of gas turbines.