Optimization of Heat Affected Zone for Air Plasma Cutting Process: A Support Vector Machine Approach

Research areas:

• Volume 2,Issue 1, July. 2013

Year:

2013

Type of Publication:

Article

Keywords:

Air Plasma Cutting, Support Vector Machine, Heat Affected Zone, Output Current

Authors:

K. Kadirgama; M. M. Rahman; Z. Ghazali

Journal:

IJAIM

Volume:

2

Number:

1

Pages:

13-18

Month:

July

Abstract:

This paper explores the development of intelligent system to predict heat affected zone (HAZ) for air plasma cutting process. Three variables including the output current, stand-off gap and pressure are selected in this study. Design of experiments (DOE) techniques is implemented to reduce the number of experiments. Support vector machine neural network models were developed. It is observed that the developed model is within the limits of the agreeable error when experimental and network model results are compared. It is further observed that the error when the network is optimized by experimental results have come down to less than 2% from not more than 9%. Sensitivity analysis is also done to find the relative influence of factors on the performance measures. It is observed that output current is the most significant variable compare with stand-off gap and pressure.

Full text: IJAIM_127_Final.pdf