Study On Situation Refactor Of The Battlefield Based On Dynamic Bayesian Network

Situation refactoring is an important part of command automation system in the complex battlefield. The complication, dynamic and uncertainty of information warfare have brought the huge challenge for the situation refactor. In this case, how to carry on a comprehensive assessment to situation refactor is an urgent problem need to solve. In the process of the situation refactor, the situation awareness, understanding and predicting need a great deal of indefinite target characteristic information. How to fuse these indefinite information to realize real-time assessment to situation refactoring is the key technology difficulty.This paper is mainly on the application of Dynamic Bayesian network in the situation refactor..Bayesian network is considered the strongest foundation for the mathematical theory of dealing with uncertainty. Dynamic Bayesian Network(DBN) is the development of Bayesian Network(BN). It has a good time evolution of the denotation capacity for the random variables. Make use of closed-loop dynamic Bayesian network topology for continuous learning. It can reduce the uncertainty of Information integration. The method provides a strong theoretical support for this paper. The prime task and the content in this article can be concluded as follows:(1) Introduce the related knowledge of situation factor. Firstly, detailed explain the definition of situation factor, from the situation awareness, understanding and predicting three aspects to construct the function model, detailed description of each function module. Then established the typical battlefield element model according to the real battlefield environment, which can be applied to the process of situation refactoring.(2) Studies on the related knowledge of Bayesian network, starting from the probabilistic network introduces the advantages of the Bayesian network and the building method, extended the advantages of dynamic Bayesian network and its characteristics in the situation factor.(3) A correlated example of situation refactor based on dynamic Bayesian network was analyzed, which takes missile precise strike targets at sea this dynamic process as a background. The evaluation results are demonstrated the approach mentioned above feasible and reasonable.(4) The contrastive analysis was carried out, which under the condition of uncertainty information in the situation refactor between Dynamic Bayesian Network and static Bayesian network. The superiority of dynamic Bayesian network was proved.