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] 

机构地区：[1]空军工程大学工程学院,陕西西安710038

出　　处：《弹箭与制导学报》2003年第S3期285-288,共4页Journal of Projectiles,Rockets,Missiles and Guidance

摘　　要：针对目前制导炸弹命中精度低的问题,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、泛化功能强且凋整灵活等优点。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 (ANFIS).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.

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：TJ414[兵器科学与技术—火炮、自动武器与弹药工程]