自适应神经网络用于船舶动力定位系统

船舶动力定位（DP）采用一种控制系统驱动装在船上的侧推器和尾部推进器或者几个全回转的推进器，使船定位在海平面的要求位置上。船受到风、浪及流等海洋环境力的作用时会漂移离开原位置，传统的控制方法是采用PID（比例、积分、微分）反馈控制。顾和李（1994）提出了一种新的基于人工神经网络的控制方法，它具有许多优越性：①一个可随意调节的目标函数以适合不同的需求──定位精度高或节约定位能量后前馈控制并能自适应于不同的环境力变化包括非线性的波浪漂力；本文在目标函数中引入了与速度相关的项，从而提高控制质量。这一方法也可用于自动驾驶船舶沿设定的轨迹航行。计算机模拟结果表明本方法能达到很好的控制效果。

DYNAMIC POSITIONING OF SHIPS USING A PLANNED NEURAL NETWORK CONTROLLER

Dynamic positioning of vessels is a technique which uses ship-mounted propellers and lateral thrusters commanded by a control system to maintain it as closely as required at some desired position in the horizontal plane. The environmental disturbing forces are those due to wind, waves and current. Heretofore control systems basing on PID principle have been used. This paper continues the previous discussion (Gu and Li, 1994) on a new kind of neural network control system which has many advantages, namely:a versatile objective function which is adaptive to the need of the operator-more precision or more saving in power, a completely feed forward control which is self adaptive to changes in environmental forces including nonlinear wave drift forces. Emphasis in this paper is made on the quality of control, which is improved by including a velocity term beside the position term in the objective fuction. The performance is effectively enhanced. The station keeping problem is generalized to include moving the ship by neural-net control to a new target position if required. Computer simulations were carried out with satisfying results.