Based on the difference of information source during different identification phases, dynamic Bayesian network is
used to model the whole process of integrated identification friend-or-foe. Due to the increasing number of model parameters,
the acquiring of multitudinous swatch and the learning and training process become difficult. Therefore, the random fuzzy
theory is adopted for parameter learning, which not only makes sufficient use of transcendent information, but also avoids
the subjective factor as utmost as possible. The simulation results show the effectiveness of the proposed method.