基于进化ANFIS的制导炸弹智能控制系统研究  

Intelligent control system of guided bomb based on ANFIS evolved

作　　者：宋恒[1] 左继章[1] 王振家[1] 

机构地区：[1]空军工程大学,陕西西安710038

出　　处：《系统工程与电子技术》2005年第10期1795-1799,共5页Systems Engineering and Electronics

摘　　要：针对目前制导炸弹命中精度低的问题,首次提出一种基于进化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。规则库是通过系统对训练数据进行自学习,并在自学习的过程中引入遗传算法进化调整系统结构和参数而建立的。通过计算机仿真,该智能控制系统具有精度高、泛化功能强且实现了调整智能化等优点。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, a kind of intelligent control system of guided bomb based on adaptive neuro-fuzzy inference system（ANFIS） is presented. Instead of being concluded by a mathernatics model, the information of control system is obtained by FIS, which is built up by “space delamination”. The rule library is set up by genetic algorithm which adjusts the structure and parameters of the system in course of studying. Through simulation testing, the system shows high precision, good generalization ability and intelligent 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 遗传算法 

分 类 号：V24[航空宇航科学与技术—飞行器设计]