Approximate effect of parameter pseudonoise intensity on rate of convergence for EKF parameter estimators

Describes the effect that the assumption of a fictitious noise (called pseudonoise) driving the unknown parameter values has on the parameter estimate convergence rate in filter-based parameter estimators. The initial approach is to examine a first-order system described by one state variable with one parameter to be estimated. The intent is to derive analytical results for this simple system that might offer insight into the effect of the pseudonoise assumption for more complex systems. Such results would make it possible to predict the estimator error convergence behavior as a function of the assumed pseudonoise intensity, and this leads to the natural application of the results to the design of extended Kalman filter (EKF)-based parameter estimators. The results obtained show that the analytical description of the convergence behavior is very difficult