PROJECT TITLE :

Adaptive Gauss–Hermite filter for non-linear systems with unknown measurement noise covariance

ABSTRACT:

A non-linear adaptive state estimator based mostly on the Gauss–Hermite (GH) quadrature rule has been proposed to suit non-linear signal models where the measurement noise covariance remains unknown. The proposed algorithm that may be used for both parameter and state estimation incorporates on-line adaptation of the measurement noise covariance (R) following maximum-chance estimation-primarily based technique. The GH quadrature approach has been thought of so that the proposed filter may inherit the enhanced estimation accuracy as exhibited by its non-adaptive counterpart. The proposed adaptation algorithm, in contrast to another reported ways, automatically ensures positive definiteness of the tailored measurement noise covariance. The efficacy of the adaptive algorithm over the non-adaptive GH filter has been demonstrated using Monte Carlo simulation and 2 case studies. Performance comparison has conjointly been dispensed with respect to adaptive unscented Kalman filter with the assistance of same case studies.