The Study of EDM TC11 Surface Discharge Mark Diameter Based on the Artificial Neural Network Modeling

2014 ◽  
Vol 490-491 ◽  
pp. 586-589
Author(s):  
Ji Gao ◽  
Di Wang ◽  
Yao Sun ◽  
Shuai Wang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Process Parameters ◽  
Electrical Discharge Machining ◽  
Surface Discharge ◽  
Neural Network Modeling ◽  
Pulse Interval ◽  
Peak Voltage ◽  
Process Indicators ◽  
Artificial Neural

The process parameters of electrical discharge machining, such as : workpiece polarity, pulse width, pulse interval, peak current, peak voltage, all have influence on TC11’s surface roughness.But general methods are difficult to determine the relationship between the process parameters and the process indicators. This article established a artificial neural network model of EDM TC11 surface discharge mark diameter which can forecast. Neural network algorithm used BP algorithm, the network structure was the 2-4-1.

The Study of EDG GH3536 Surface Roughness Base on the Artificial Neural Network Modeling

2013 ◽  
Vol 690-693 ◽  
pp. 3175-3179
Author(s):  
Ji Gao ◽  
Di Wang ◽  
Yao Sun
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
Artificial Neural Network ◽  
Process Parameters ◽  
Neural Network Modeling ◽  
Pulse Interval ◽  
Peak Voltage ◽  
Process Indicators ◽  
Neural Network Algorithm ◽  
Artificial Neural

The process parameters of electrical discharge grinding,such as workpiece polarity, pulse width, pulse interval, peak current, peak voltage, all have influence on GH3536’s surface roughness.General method is difficult to determine the relationship between the process parameters and the process indicators. This article established a artificial neural network model of EDG GH3536 surface roughness which can forecast. Neural network algorithm use BP algorithm, the network structure is the 2-4-1.

Sign in / Sign up

Export Citation Format

Share Document