基于ANFIS的制导炸弹智能控制系统  

Intelligence Control System of Guided Bomb Based on ANFIS

作　　者：宋恒[1] 肖坤[1] 王振家[1] 汪浩生[1] 

机构地区：[1]空军工程大学工程学院,陕西西安710038

出　　处：《火力与指挥控制》2003年第z1期109-112,共4页Fire Control & Command Control

摘　　要：针对目前制导炸弹命中精度低的问题,首次提出一种基于自适应神经模糊推理系统(ANFIS)的制导炸弹智能控制系统。该系统不基于数学模型,用独特的空间分层方法建立若干模糊推理系统,依靠专家经验来获取控制信息。规则库是通过分析训练数据,用Levenberg-Marquardt优化方法改进的BP神经网络对训练数据自学习而建立的。通过计算机仿真,该智能控制系统具有精度高、泛化功能强且调整灵活等优点。可以预见,这种智能控制系统在军事上有很好的应用前景。Aiming at the problem of guided bombs in low precision,this paper presents a kind of intelligence control system of guided bomb based on Adaptive Neuro-Fuzzy Inference System(ANEIS). Instead of being concluded by a mathematics model,the information of control system is obtained by FIS,which is built up by'space delamination'. The rule library is set up by BP neural network improved by Levenberg-marquardt optimize studying data analyzed. Through simulation testing,the system shows high precision, good generalization ability and adaptability,which might provided it with good application in military field.

关 键 词：制导炸弹 智能控制系统 模糊推理系统 BP神经网络 空间分层 

分 类 号：E92[军事—军事装备学] E072[兵器科学与技术—武器系统与运用工程]