基于遗传算法的BP神经网络优化策略研究  

Application of Artificial Neural Network Based on Genetic Algorithm to Cooperative Transport of Multi-robots System

作　　者：靳建彬[1] 王元钦[2] 陈源[1] 

机构地区：[1]装备指挥技术学院研究生管理大队,北京101416 [2]装备指挥技术学院科研部,北京101416

出　　处：《计算机与现代化》2010年第9期88-91,共4页Computer and Modernization

摘　　要：人工神经网络(ANN)可用作机器人控制器,完成多机器人协作搬运作业。针对这种方法收敛速度较慢,误差较大的不足,本文提出基于遗传算法优化的方法。该方法利用遗传算法优化人工神经网络,通过改变ANN结构和遗传算法操作参数,找到最优网络,提高网络收敛速度。仿真结果证明,该方法的可行性与有效性。Artificial neural network can be used as the robot controller,in order to complete the multi-robots cooperation transporting task.In response to the shortages of slow convergence speed and large errors in this method,this paper presents a method optimized by the genetic algorithm.This method makes use of genetic algorithm to optimize the artificial neural networks,and changes the ANN structure and the operational parameters of genetic algorithms to find the optimal network and improve the network convergence speed.Simulation results show the feasibility and effectiveness of the method.

关 键 词：人工神经网络(ANN) 遗传算法 收敛速度 多机器人 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]