【作者】 唐旭东； 庞永杰； 李晔； 秦再白；

【Author】 Tang Xudong,Pang Yongjie,Li Ye,Qing Zaibai Key lab of autonomous underwater vehicle,Harbin Engineering University,Harbin 150001,P.R.China

【机构】 哈尔滨工程大学水下机器人重点实验室；

【摘要】 分析了水下机器人(AUV)的控制特点,针对这一控制非线性系统,提出了一种基于专家经验和蚁群优化算法的模糊神经网络控制系统,该方法利用蚁群算法在解决组合优化问题中的强大优势,自动获取模糊控制规则和隶属度函数,同时加入了专家经验,大大简化了需要获取的参数数目,增强蚁群算法的学习效率,考虑到蚁群寻优算法易于早熟的问题,提出了改进蚁群算法。仿真试验和应用结果验证了该方法可行性和有效性。更多还原

【Abstract】 Owing to the characteristic of autonomous underwater vehicles(AUV) control and to solve the typical nonlinearity control system,we deduced a new fuzzy neual network control based on expert experience and ant colony algorithm.This algorithm superiority in solving combination optimization problems which consists of the rule sets and parameters of the membership functions of the continuous fuzzy controller to be slected.In order to enhance the efficiency of ant colony algorithm and prevent the precocity,the expert experience and improving ant colony algorithm are introduced in.Simulation results and applications showed that method is effective enough to make control simpler and robust and to get good control performance.更多还原