A novel model for linear dynamic system with random delays

This paper explores a novel model to describe linear dynamic system with random delays. Compared with the existing research, the probabilities of random delays in the novel model are calculated by conditional probabilities. Therefore, the process noises and measurements noises in the new model for random delay problems are infinitely correlated. By treating the model as random parameter matrices Kalman filtering with one-step correlated noises approximately, the new state estimators are presented. Numerical examples show that the new estimators work better than the existing algorithm in many cases.