自适应学习误差模型船舶柴油机调速器的研究  

Research on Ship Diesel Engine Speed Regulator Using on-Line Learning and Self-Tuning Error Model

作　　者：张桂臣[1] 任光[1] 

机构地区：[1]大连海事大学轮机工程学院,辽宁大连116026

出　　处：《内燃机学报》2009年第3期259-264,共6页Transactions of Csice

基　　金：交通部交通应用基础研究项目(200332922505);高等学校博士学科点专项科研基金(20030151005)

摘　　要：船速控制的重要功能是维持船舶航速稳定和主机的热平衡,从而提高船舶操纵性能,以船-机-桨系统为控制对象的船舶调速器能够较好地实现这些功能。在分析船舶航速误差模型变化特性的基础上,应用激励函数的自适应神经网络和最陡下降法的非线性优化技术,提出了自适应学习误差模型控制方法,应用于船舶柴油机调速器控制系统。为验证新方法的有效性,在实验室条件下,建立了船舶柴油机调速器半实物仿真系统。仿真结果表明,新的船舶柴油机调速器在系统模型不确定和参数摄动情况下,能在线学习被控系统的动态特性,具有抑制扰动和参数摄动的能力,系统调节过程的稳定性和快速性都有提高。Ship speed control is a key issue in improving performance of ship maneuvers, keeping ship speed stabilization and heat balance effect of main engine. Ship speed regulator of ship-engine-propeller to be as the control object can realize this objective. On the basis of variation characteristics of ship speed error model, a ship speed regulator using the on-line adaptive error model is proposed in this paper. The control scheme is based on back propagation multi-layer perceptrons （MLP） adaptive neural network in which a modified hyperbolic tangent function is used as the activation function of an auto-tuning neuron and is updated by the steepest descent method. The hardware-in-the-loop simulation of ship speed regulator system is implemented. Test result shows that ship speed regulator enhances the ability to restrain disturbance and system with parameter perturbance and improves the stability and speed performance in case of system uncertainty.

关 键 词：船舶 柴油机 调速器 误差模型 

分 类 号：TK421[动力工程及工程热物理—动力机械及工程]