Results are presented from a study of leakage losses from a position control systemand the resulting knowledge that may be incorporated into an on-line expert system for fault diagnosis. The use of aminimum number of sensors results in leakage and position error data that have limitations for multiple-faultsituations. It is then shown how the application of an artificial neural network can give additional confidence to a fault assertion, and results are shown for a number of leakage conditions.
