A study on fault diagnostic method for the lube oil system of gas turbine based on rough sets theory

Lube oil system is very important to ensure the normal and stable operation of gas turbine. The faults of lube oil system would affect the performance of the whole gas turbine unit, and even lead to shut down. Through analyzing the operating characteristics and typical faults of lube oil system, this paper found that lube oil system possesses a nature of the diverse fault information, and the vague and uncertain relationship between fault causes and fault symptoms. According to lubrication oil system characteristics, this paper proposed a fault diagnostic method for lube system based on rough sets theory. Rough sets theory can get the important parameters which characterizes the equipment operating status from complex multivariate information. This theory can extract fault diagnostic rules by making use of reduction algorithm. The results show that the method can improve the accuracy of diagnosis.