Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids
Precise milling of thin-walled components is a difficult task process owing to the geometric complexity and low stiffness connected with them. This paper is concerned with a systematic comparative study between predicted and measured surface roughness. RSM and ANN applied in prediction and optimizat...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Article |
Published: |
Asian Research Publishing Network
2019
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/92670/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.92670 |
---|---|
record_format |
eprints |
spelling |
my.utm.926702021-10-28T10:09:51Z http://eprints.utm.my/id/eprint/92670/ Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids Yanis, M. Mohruni, A. S. Sharif, S. Yani, I. TJ Mechanical engineering and machinery Precise milling of thin-walled components is a difficult task process owing to the geometric complexity and low stiffness connected with them. This paper is concerned with a systematic comparative study between predicted and measured surface roughness. RSM and ANN applied in prediction and optimization of milling thin-walled steel components. Cutting speed, feed rate, radial and axial depth of cut are the main affecting process parameters on surface roughness. In order to protect our precious environment, this work utilized vegetable oil as biodegradable cutting fluids that resolve the lowest amount of ecological contamination provide well economic conditions. The milling have done under flood cooling and using uncoated carbide as cutting tool. The results indicate that the RSM and ANN models are very close to the experimental results, ANN predictions show better convergence than the RSM model. The best of surface roughness value (0.314 μm) can be achieved with a desirability of 98.6%, cutting speed, feed rate, radial and axial depth of cut were 125 m/min, 0.04 mm/tooth, 0.25 mm and 10 mm, respectively. The best configuration of the ANN structure was 4-16-1. The feed rate cause most significant effect on surface roughness, followed by axial and radial depth of cut. Asian Research Publishing Network 2019 Article PeerReviewed Yanis, M. and Mohruni, A. S. and Sharif, S. and Yani, I. (2019) Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids. ARPN Journal of Engineering and Applied Sciences, 14 (18). pp. 3124-3134. ISSN 1819-6608 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
topic |
TJ Mechanical engineering and machinery |
spellingShingle |
TJ Mechanical engineering and machinery Yanis, M. Mohruni, A. S. Sharif, S. Yani, I. Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids |
description |
Precise milling of thin-walled components is a difficult task process owing to the geometric complexity and low stiffness connected with them. This paper is concerned with a systematic comparative study between predicted and measured surface roughness. RSM and ANN applied in prediction and optimization of milling thin-walled steel components. Cutting speed, feed rate, radial and axial depth of cut are the main affecting process parameters on surface roughness. In order to protect our precious environment, this work utilized vegetable oil as biodegradable cutting fluids that resolve the lowest amount of ecological contamination provide well economic conditions. The milling have done under flood cooling and using uncoated carbide as cutting tool. The results indicate that the RSM and ANN models are very close to the experimental results, ANN predictions show better convergence than the RSM model. The best of surface roughness value (0.314 μm) can be achieved with a desirability of 98.6%, cutting speed, feed rate, radial and axial depth of cut were 125 m/min, 0.04 mm/tooth, 0.25 mm and 10 mm, respectively. The best configuration of the ANN structure was 4-16-1. The feed rate cause most significant effect on surface roughness, followed by axial and radial depth of cut. |
format |
Article |
author |
Yanis, M. Mohruni, A. S. Sharif, S. Yani, I. |
author_facet |
Yanis, M. Mohruni, A. S. Sharif, S. Yani, I. |
author_sort |
Yanis, M. |
title |
Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids |
title_short |
Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids |
title_full |
Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids |
title_fullStr |
Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids |
title_full_unstemmed |
Optimization of surface roughness using RSM and ann modelling on thin-walled machiningunder biodegradable cutting fluids |
title_sort |
optimization of surface roughness using rsm and ann modelling on thin-walled machiningunder biodegradable cutting fluids |
publisher |
Asian Research Publishing Network |
publishDate |
2019 |
url |
http://eprints.utm.my/id/eprint/92670/ |
_version_ |
1715189672403009536 |
score |
13.18916 |