摘要
针对传统的水下机器人模糊神经网络控制器存在计算量大、抗环境扰动滞后等缺点,设计递归模糊神经网络控制器,通过在线的动态反馈增强水下机器人对环境变化的反应能力。并在网络的第三层即Petri层设计阈值,根据控制器误差的在线控制网络的学习和训练量,从而减少了模糊神经网络的计算量,提高反应速度。基于反向梯度传播原理,由能量函数设计了该网络的学习算法,并根据离散型李亚普诺夫函数确定了学习率参数,从而保证整个网络的收敛性。实验结果表明,该控制器能够提高递归神经网络的计算效率,减少控制误差,对外界干扰具有较强的鲁棒性,在水下机器人的控制方面取得了更好的效果。
Traditional fuzzy network controller was disadvantadged in heavy caculation and hysteresis re- sponse to strong disturbance. Therefore a fuzzy recurrent neural network controller was designed, in order to improve the robustness corresponding to environment change through online dynamic feedback. Thresh-old was issued in the third layer so as to regulate training and learning according to controller errors. Thus eaculation of the whole network was reduced. Moreover, the online training algorithm was developed based on gradient descent method. The learning rate parameters were determined according to discrete-type Lyapunov function, which guaranteed the whole network convergence. Experiments have demonstra-ted that the controller can improve the computation efficiency, reduce control errors, possess strong ro-bustness and be very effective in the underwater robotic control.
出处
《电机与控制学报》
EI
CSCD
北大核心
2012年第5期91-96,共6页
Electric Machines and Control
基金
国家863计划资助项目(2008AA092301-2)
海洋工程国家重点实验室(上海交通大学)开放课题资助(1102)
