文献类型：期刊文献

中文题名：伺服系统在摩擦条件下的模拟复合正交神经网络控制

英文题名：AN ANALOG COMPOUND ORTHOGONAL NEURAL NETWORK CONTROL OF THE SERVO SYSTEM IN FRICTION CONDITION

作者：叶军[1]

机构：[1]绍兴文理学院机电系

年份：2005

卷号：25

期号：17

起止页码：127

中文期刊名：中国电机工程学报

外文期刊名：Proceedings of the Csee

收录：CSTPCD、、北大核心2004、Scopus、CSCD2011_2012、北大核心、CSCD

基金：浙江省自然科学基金项目(M603070)

语种：中文

中文关键词：伺服系统;直流电机;非线性摩擦力矩;模拟复合正交神经网络;并行控制;PD控制器;神经网络控制器

外文关键词：Servo system; DC motor; Nonlinear friction torque; Analog compound orthogonal neural network; Parallel control; PD controller; Neural network controller

中文摘要：在数字复合正交神经网络的基础上提出一种模拟复合正交神经网络,并用于非线性伺服系统控制中。在带有非线性摩擦力矩的直流电机飞行模拟转台伺服系统中,控制系统是基于PD控制加神经网络前馈控制的并行控制方法,使用神经网络是用来消除非线性摩擦力矩的影响。通过数字复合正交神经网络的连续化算法处理获得了一种模拟复合正交神经网络,并作为前馈控制器。用并行控制与单一的PD控制对带有非线性摩擦力矩的直流电机伺服控制作了仿真研究。仿真结果表明复合控制比单一的PD控制具有实时性好、响应速度快、跟踪精度高,位置与速度跟踪控制获得了满意的效果。该模拟神经控制器能用于不确定对象的控制,为不确定系统控制提供了一种新的途径。

外文摘要：An analog compound orthogonal neural network was presented on the basis of the digital compound orthogonal neural network and was applied in the control of the servo system with nonlinearity. In the flight simulator servo system of DC motor with nonlinear friction torque, the control system was based on the parallel control method of the PD feedback control and the feedforward control of the neural network. The affect of nonlinear friction torque was rejected by use of the neural network. The analog compound orthogonal neural network was obtained by means of a continuous algorithm treatment for a digital compound orthogonal neural network, and was used as the feedforward controller. The servo control of DC motor with nonlinear friction torque was simulated by means of the parallel control and the single PD control. The simulation results prove that the compound control has better real-time control performance, faster response velocity, and higher tracking precision than the single PD control. The position and speed tracking control obtain satisfactory effects. The analog neural controller can be applicable to the control of uncertain objects and provides a novel approach for the type of an uncertain control system.