Application of a dynamic fault diagnostic method using Bayesian belief networks on a fuel rig system

Bayesian Belief Networks are probabilistic models that are particularly suited to applications where new evidence can be introduced on the variables. By means of Bayes' theorem, the probability associated to events can be updated following observations and new information available. This feature has advantages in system fault diagnostic processes where sensors on the system provide evidence for the state of a system. Where sensors indicate that the behavior of the monitored variable deviates from that expected, the information is used to find the possible causes of a fault. A method using Bayesian Networks which can account for dynamic system effects has been developed and applied to the fault diagnostics of a fuel rig system. The fuel rig is a simulated aircraft fuel system experimental facility. The results show that Bayesian Networks provide a concise and effective modelling tool for the fault diagnostics processes.