Failure prognostic by using Dynamic Bayesian Networks

this paper presents a procedure for failure prognostic by using Dynamic Bayesian Networks (DBNs). The graphical representation of this tool is particularly well suitable for modeling complex systems, with non homogeneous sources of data and knowledge. Moreover, DBNs allow to deal with uncertainty which is an inherent property to any failure prognostic work, especially regarding the estimation of the Remaining Useful Life (RUL) before a failure. The DBN model can be also used to observe the propagation of the effect of any state of the model on the other remaining states. The proposed procedure is applied on a small industrial system to show its feasibility.