摘要
提出一种神经网络在线工业跟踪控制方法，此方法能解决ＢＰ学习算法中误差函数对权值的偏导数计算问题和执行器输出的脉动变化和饱和问题。把本控制器用于船舶自动舵控制，仿真结果表明了它的可行性和自适应性。
A neural network approach for on-line industrial tracking control is presented. The proposed direct neural controller can solve two difficult problems, that is, the evaluation of the partial derivative of error function with respect to weight in BP algorithm, and the fluctuation and saturation of the actuator output. Simulations of a ship course-keeping control have been investigated, and the results demonstrate the feasibility and adaptive property of the proposed scheme.
出处
《控制与决策》
EI
CSCD
北大核心
1999年第2期125-129,134,共6页
Control and Decision
基金
中国船舶工业国防科技应用
基础研究基金
关键词
神经网络控制器
控制器
自动舵
船舶
on-line training, adaptive property, neural controller, ship course-keeping, autopilot
