SUGENO型网络在空战CGF战术决策中的应用  

Sugeno ANFIS Model Used in Tactics Decision of Fighter CGF of Air Combat Simulation

作　　者：李蔚恒[1] 王庆林[1] 李彦志[2] 杨承志[2] 

机构地区：[1]北京理工大学信息科学技术学院自动控制系 [2]空军航空大学,长春130022

出　　处：《系统仿真学报》2007年第6期1274-1276,1280,共4页Journal of System Simulation

摘　　要：提出了运用SUGENO线性模型研究空战仿真中飞机CGF的战术机动决策问题,构建了决策ANFIS网络。把各种作战态势纳入到统一框架下考虑,并运用混合学习算法完成网络的训练。用最速下降算法优化前提参数,用最小二乘法拟合结论参数。该模型训练速度快,鲁棒性好,能较客观地反映实际空战模型,较好地模拟飞行员的决策,并为蓝方CGF的智能化设计奠定了基础。The SUGENO linear fuzzy model was proposed to the field of tactics decision in the fighter CGF of the air combat simulation system The tactics ANFIS network was put forward All of the cases of air combat were unified in a whole flame, the hybrid learning algorithm was adopted to train the network. That is, the SD algorithm is used to optimize the premise parameters and the LSE algorithm is used to train the consequent parameters. The results of simulation show that the network has properties of fast convergence and good robustness. It can objectively reflect the actual air combat model and can effectively simulate the decision of the pilot. The algorithm lays a foundation of the intelligentized design of the rival CGF model.

关 键 词：空战仿真 战术决策 自适应神经模糊推理系统 SUGENO模型 混合学习算法 

分 类 号：TP273.4[自动化与计算机技术—检测技术与自动化装置]