Robust integrated parallel covariance intersection fusion predictor for AR signal systems with mixed uncertainties

Robust integrated parallel covariance intersection fusion predictor for AR systems with mixed uncertainties is presented, where the mixed uncertainties include uncertain noise variances and missing measurements. The design approach of integrated parallel covariance intersection fusion predictor has three steps, which includes model conversion, the design of local and parallel covariance intersection fusion predictor and the confirmation of their robustness. By the state space and the fictious approach, the original system is converted into a multi-model system. According to the mini-max robust estimation principle and the parallel covariance intersection fusion algorithm, the local and fusion predictors are presented. The robustness and the robust accuracies of them are proved by matric conversion method. A simulation example verifies the correctness and effectiveness of the proposed results.