将空空导弹攻击区的拟合表示成一非线性逼近问题 ,从而利用模糊逻辑系统的万能逼近性质 ,并结合误差反向传播学习算法 (BP算法 )实现了对导弹攻击区的自动学习。在此基础上 ,提出了利用扩展的 T- S推理进行攻击区分组逼近与综合的方法。仿真结果表明该方法具有精度高、参数少、通用性强等优点。 The fitting of air-to-air missile attack zone is expressed as a non-linear approximation problem, so the universal approximation property of fuzzy logic system is utilized. Combined with error back propagation learning algorithm (BP algorithm), the missile attack area is automatically learned. On this basis, a method of attack grouping approximation and synthesis using extended T-S reasoning is proposed. Simulation results show that this method has the advantages of high precision, less parameters and high universality.