Generalized Likelihood Ratio Approach to the Detection and Estimation of Jumps in Linear Systems

Abshclct-We consider a class of stochastic hear systems that are subject to jumps of unknown magnitudes in the state variables ornoling at nnknown times. This model can be nsed when considering such problem as estimation for systems subject to possible component fai lures and the tracking of vehicles capable of abrupt maneuvers Using Kalmao-Bucy filtering and generalized likelihood ratio techniques, we devise an adaptive filtering system for the detection and estimation of the jumps. An example that illustrates the dymmical properlies of our fiitering scheme is discusssed in detail.