To improve the reliability of hydraulic systems, a fault diagnosis approach based on radial basis function (RBF) networks was proposed in this paper. According to the target fault features extracted from a fuzzy auto-regressive with extra outputs (FARX) model, RBF networks serve as a fault classifier and the output of the RBF networks is the result of fault diagnosis. Several typical faults of hydraulic systems were used to test the fault diagnosis approach. Experiment results showed that the fault diagnosis approach is feasible and effective...
