An Integrated Approach to Prognosis of Hybrid Systems With Unknown Mode Changes

A new framework to design model-based prognosis for hybrid systems with unknown mode changes is proposed in this paper. The key step is the construction of an interacting diagnostic hybrid bond graph-particle filter (IDHBG-PF) module in the framework. In the module, the diagnostic hybrid bond graph (DHBG) part is employed for mode tracking after fault occurrence and fault isolation, and the particle filter (PF) part is used for joint state and parameter estimation as well as remaining useful life prediction. The DHBG part provides the set of suspected faults (SSF) to augment the dynamic model for the PF part, whereas the PF part outputs true faults for SSF refinement to facilitate prognosis and further fault isolation. During the prognosis, the probability density function (pdf) of the predicted remaining useful life under different operating modes can be calculated using the estimated mode-dependent degradation rate (MD-DR) and the user-selected failure threshold. The key concepts of the developed prognosis framework are validated by experimental results.