基于非单点模糊网络的制导炸弹智能控制研究  

An Intelligent Control System of Guided Bomb Based on Non-singleton Fuzzy Regular Neural Networks

作　　者：徐国强[1] 宋恒[2] 祝志兵 

机构地区：[1]空军第一航空学院,河南信阳464000 [2]空军工程大学工程学院,西安710038

出　　处：《弹箭与制导学报》2006年第1期54-57,61,共5页Journal of Projectiles,Rockets,Missiles and Guidance

摘　　要：提出并设计一种具有抗干扰能力的制导炸弹智能控制系统。该系统采用非单点模糊正则网络为核心,在自学习建立规则库的过程中,能够自动滤除训练数据中的噪声,获取准确的控制信息。通过计算机仿真,并与基于ANF IS的制导炸弹智能控制系统进行比较,证明该系统抗干扰能力强、控制精度高。This paper presents a kind of intelligent control system of guided bomb with antl-jamming capability. The system was composed of non-singleton fuzzy regular networks. In course of building up the rule base by self-study, the system can automatically filter out the noise of training data, acquire exact control information. In slmulation, the system was compared with the intelligent control system of guided bomb based on adaptive neuro-fuzzy inference system （ANFIS）. The result shows the system has good anti-jamming capability and high control precision.

关 键 词：制导炸弹 智能控制系统 非单点模糊系统 神经网络 

分 类 号：TJ765[兵器科学与技术—武器系统与运用工程]