A new observer-based approach to disturbance rejection and control in
linear continuous systems is introduced. A recently developed techniqu
e of continuous deadbeat observation is exploited to estimate the proc
ess states and disturbance signal described by a known dynamic model.
A realization condition in the form of linear algebraic equations is d
erived. When there is no reliable disturbance model available, it is s
uggested to use a neural network-based structure. An application examp
le illustrates the feasibility of the approach taken.