Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Die & Mould Industry》 2010-01
Add to Favorite Get Latest Update

Prediction of the protection layer thickness of electrode in EDM

HU Ren-ping1,LIU Gang1,YANG Yang2(1.Hunan Railway College of Science & Technology,Zhuzhou,Hunan 412000,China; 2.School of Mechanical and Electrical Engineering,East China Jiaotong University,Nanchang,Jiangxi 330013,China)  
A model for predicting the protection layer of electrode based on neural networks was proposed in accordance with the nonlinear time variant characteristic in EDM process.The protection layer thickness of electrode was determined by the network and the covering contributes to lower electrode loss during the machining process.In establishing the model,an automatic optimization of feedforward neural network based on improved genetic algorithm was suggested,which can avoid the deficiency of multilayer feedforward neural network algorithms.The search of network structure and space of weight was then finished;the convergence speed was accelerated and the ability to search for the global optimum solution was enhanced.
【CateGory Index】: TG661
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved