On the estimation of distributed systems with uncertain parameters

This paper formulates the basic state estimation procedures for a class of distributed systems with uncertain parameters. The parameters are not assumed to be random but believed to be arbitrary time functions known to be in a closed and bounded region. The developed estimation scheme provides an assured accuracy and a "guaranteed" error estimator which gives an upper bound of the estimation error for any allowed variation of uncertain parameters. The estimation algorithm will be much simpler and easier to implement than any adaptive estimation scheme, since the parameter estimation procedure is not required and is therefore bypassed.