Fault Diagnosis for a Three Mass Torsion Oscillator Using a Bank of Fault Models

A fault diagnosis method for a three mass torsion oscillator is considered which is subject to different additive faults. By using a bank of fault models three faults of different type are detected, isolated and identified in size and time of occurrence. The bank of fault models is formed by a model of each considered fault. Comparison of simulated fault model outputs and measured signals leads to fault isolation. Fault size and time of occurrence are identified by a parity equation approach and used as fault model parameters. The method is capable to perform the tasks with use of one actuator and one sensor signal. It is shown that common approaches for fault isolation can not be used due to the small number of measured signals.