Self-tuning full-order Kalman filter for descriptor system

For the descriptor system with unknown noise variances, the self-tuning full-order Kalman filter with self-tuning descriptor Riccati equation is presented. Firstly, the fused estimates of these unknown noise variances can be obtained by the correlation function method. Then, substituting these fused estimates into the recursive Kalman filter with descriptor Riccati equation yields the self-tuning full-order Kalman filter and its filtering error variance. A simulation example of a descriptor system verifies its effectiveness of the self-tuning Kalman filter.