改进型RBF神经网络下目标威胁评估

摘要

The threat assessment of informational armored unit is studied. The existing assessment methods are unsatisfying without considering the combat style. In order to solve this, this paper establishes the improved RBF according to the rapidity and the optimal approximation ability of RBF neural network. The example shows that the modified method not only meets the demands of battle ground and tactics, but also has a high practical value.%为解决信息化装甲分队目标威胁评估问题，依据径向基函数（RBF）神经网络的快速性和唯一最佳逼近性设计了改进型RBF神经网络。实例分析表明，该改进方法可满足不同作战样式下目标威胁评估要求，具有较高的实用价值。