Prediction of surface roughness in low speed turning of AISI316 austenitic stainless steel

Gabriel Medrado Assis Acayaba, Patricia Muñoz de Escalona

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Surface roughness is an important quality in manufacturing, as it affects the product’s tribological, frictional and assembly characteristics. Turning stainless steel at low cutting speeds may result in a rougher surface due to built up edge formation, where as speed increases the surface roughness improves, due to the low contact time between the chip and the tool to allow bonding to occur.However, this increase in cutting speed produces higher tool wear rates, which increases the machining costs.
Previous studies have indicated that savings in cost and manufacturing time are obtained when predicting the surface roughness, prior to the machining process. In this paper, experimental data are used to develop prediction models using Multiple Linear Regression and Artificial Neural Network methodologies. Results show that the neural network outperforms the linear model by a fair margin (1400%). Moreover, the developed Artificial Neural Network model has been integrated with an optimisation algorithm, known as Simulated Annealing (SA),this is done in order to obtain a set of cutting parameters that result in low surface roughness. A low value of surface roughness and the set of parameters resulting on it, are successfully yielded by the SA algorithm.
LanguageEnglish
Pages62-67
Number of pages6
JournalCIRP Journal of Manufacturing Science and Technology
Volume11
Early online date9 Sep 2015
DOIs
Publication statusPublished - Nov 2015

Fingerprint

Austenitic stainless steel
Surface roughness
Simulated annealing
Neural networks
Machining
Stainless Steel
Linear regression
Costs
Stainless steel
Wear of materials

Keywords

  • stainless steel
  • turning
  • surface roughness
  • multiple linear regression
  • artificial neural networks
  • simulated annealing

Cite this

Acayaba, Gabriel Medrado Assis ; Muñoz de Escalona, Patricia. / Prediction of surface roughness in low speed turning of AISI316 austenitic stainless steel. In: CIRP Journal of Manufacturing Science and Technology. 2015 ; Vol. 11. pp. 62-67.
@article{04eb820be54242f7b84b4445167d15eb,
title = "Prediction of surface roughness in low speed turning of AISI316 austenitic stainless steel",
abstract = "Surface roughness is an important quality in manufacturing, as it affects the product’s tribological, frictional and assembly characteristics. Turning stainless steel at low cutting speeds may result in a rougher surface due to built up edge formation, where as speed increases the surface roughness improves, due to the low contact time between the chip and the tool to allow bonding to occur.However, this increase in cutting speed produces higher tool wear rates, which increases the machining costs.Previous studies have indicated that savings in cost and manufacturing time are obtained when predicting the surface roughness, prior to the machining process. In this paper, experimental data are used to develop prediction models using Multiple Linear Regression and Artificial Neural Network methodologies. Results show that the neural network outperforms the linear model by a fair margin (1400{\%}). Moreover, the developed Artificial Neural Network model has been integrated with an optimisation algorithm, known as Simulated Annealing (SA),this is done in order to obtain a set of cutting parameters that result in low surface roughness. A low value of surface roughness and the set of parameters resulting on it, are successfully yielded by the SA algorithm.",
keywords = "stainless steel, turning, surface roughness, multiple linear regression, artificial neural networks, simulated annealing",
author = "Acayaba, {Gabriel Medrado Assis} and {Mu{\~n}oz de Escalona}, Patricia",
year = "2015",
month = "11",
doi = "10.1016/j.cirpj.2015.08.004",
language = "English",
volume = "11",
pages = "62--67",
journal = "CIRP Journal of Manufacturing Science and Technology",
issn = "1755-5817",

}

Prediction of surface roughness in low speed turning of AISI316 austenitic stainless steel. / Acayaba, Gabriel Medrado Assis; Muñoz de Escalona, Patricia.

In: CIRP Journal of Manufacturing Science and Technology, Vol. 11, 11.2015, p. 62-67.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of surface roughness in low speed turning of AISI316 austenitic stainless steel

AU - Acayaba, Gabriel Medrado Assis

AU - Muñoz de Escalona, Patricia

PY - 2015/11

Y1 - 2015/11

N2 - Surface roughness is an important quality in manufacturing, as it affects the product’s tribological, frictional and assembly characteristics. Turning stainless steel at low cutting speeds may result in a rougher surface due to built up edge formation, where as speed increases the surface roughness improves, due to the low contact time between the chip and the tool to allow bonding to occur.However, this increase in cutting speed produces higher tool wear rates, which increases the machining costs.Previous studies have indicated that savings in cost and manufacturing time are obtained when predicting the surface roughness, prior to the machining process. In this paper, experimental data are used to develop prediction models using Multiple Linear Regression and Artificial Neural Network methodologies. Results show that the neural network outperforms the linear model by a fair margin (1400%). Moreover, the developed Artificial Neural Network model has been integrated with an optimisation algorithm, known as Simulated Annealing (SA),this is done in order to obtain a set of cutting parameters that result in low surface roughness. A low value of surface roughness and the set of parameters resulting on it, are successfully yielded by the SA algorithm.

AB - Surface roughness is an important quality in manufacturing, as it affects the product’s tribological, frictional and assembly characteristics. Turning stainless steel at low cutting speeds may result in a rougher surface due to built up edge formation, where as speed increases the surface roughness improves, due to the low contact time between the chip and the tool to allow bonding to occur.However, this increase in cutting speed produces higher tool wear rates, which increases the machining costs.Previous studies have indicated that savings in cost and manufacturing time are obtained when predicting the surface roughness, prior to the machining process. In this paper, experimental data are used to develop prediction models using Multiple Linear Regression and Artificial Neural Network methodologies. Results show that the neural network outperforms the linear model by a fair margin (1400%). Moreover, the developed Artificial Neural Network model has been integrated with an optimisation algorithm, known as Simulated Annealing (SA),this is done in order to obtain a set of cutting parameters that result in low surface roughness. A low value of surface roughness and the set of parameters resulting on it, are successfully yielded by the SA algorithm.

KW - stainless steel

KW - turning

KW - surface roughness

KW - multiple linear regression

KW - artificial neural networks

KW - simulated annealing

UR - http://www.journals.elsevier.com/cirp-journal-of-manufacturing-science-and-technology/

U2 - 10.1016/j.cirpj.2015.08.004

DO - 10.1016/j.cirpj.2015.08.004

M3 - Article

VL - 11

SP - 62

EP - 67

JO - CIRP Journal of Manufacturing Science and Technology

T2 - CIRP Journal of Manufacturing Science and Technology

JF - CIRP Journal of Manufacturing Science and Technology

SN - 1755-5817

ER -