Cooperative Team Air Combat Decision based on Integration of Rough Sets and Neural Networks

Considering the ability of rough sets theory on reduction of decision system and that of neural networks for clustering and nonlinear mapping,a new hybrid tactics decision system of rough sets and neural networks for cooperative team air combat is presented.Firstly,the continuous attributes in air combat decision system were discretized with self-organizing map neural networks.Then,the input to the model is mapped into the output subspaces by using rules acquired from rough sets.Lastly,the output of the system is approximated by BP neural networks in the subspaces.Simulation results for 2 via 4 cooperative team air combat show the method can reduce the cost of decision system and increase the efficiency of decision.With enough sample data,the solution can be applied to other decision systems in air combat