基于Elman网络的切削表面粗糙度预测方法  

Research on Prediction of Cutting Surface Roughness Based on Elman Neural Network

作　　者：粟潘[1] 孙华[1] 张永顺[1] 张江平[1] 

机构地区：[1]西华大学机械工程及自动化学院,四川成都610039

出　　处：《机械管理开发》2011年第5期203-204,206,共3页Mechanical Management and Development

摘　　要：根据Elman神经网络模型能够逼近任意非线性函数的特点和具有反映系统动态特性的能力,讨论神经网络非线性、多因素预测原理及其拓扑结构的基础上,提出利用Elman神经网络建立切削表面粗糙度预测模型的方法;在Matlab及其神经网络工具箱的基础上,采用Elman神经网络对铝6061切削表面的粗糙度进行训练、预测、分析。结果表明,建立的Elman神经网络模型收敛速度快、预测精度高。Elman neural network model can accord to the characteristics of approximate any nonlinear function and have reflect the dynamic property of the system.This paper discussed ability in neural network nonlinear,multi-factor prediction of the principle and topological structure.Based on neural network modeling using Elman cutting surface roughness prediction model of the method,and the neural network in Matlab toolbox,using introduction of 6061 aluminum Elman neural network to cut surface roughness has trained,forecasting and analysis.The results show that the established Elman neural network model convergence fastly,the forecast precision is high.

关 键 词：铝6061 ELMAN神经网络 神经元个数 粗糙度预测 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]