Assessment of the performance of neural networks models for the prediction of surface roughness after grinding of steels

Nikolaos E. Karkalos, J. Kundrák, Angelos P. Markopoulos

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Attaining acceptable levels of surface roughness is one of the primary goals of grinding. In order to achieve this goal, several approaches can be employed by varying the system parameters and attempting to find the conditions which ameliorate the outcome of the process. One way that can be rather assistive to the analysis of manufacturing processes is the use of soft computing methods such as artificial neural networks. In the current work, artificial neural network models of various categories, namely multi-layer perceptron and radial basis function neural networks, with various model parameters are developed and compared in order to determine the best performing model for the prediction of surface roughness during peripheral grinding of steel components. The results indicate that radial basis function networks outperform classical multi-layer perceptrons and constitute a promising alternative for the modeling of manufacturing processes.

Original languageEnglish
Pages (from-to)55-75
Number of pages21
JournalInternational Journal of Artificial Intelligence
Volume15
Issue number1
Publication statusPublished - Mar 1 2017

Fingerprint

Surface roughness
Multilayer neural networks
Neural networks
Steel
Soft computing
Radial basis function networks

Keywords

  • Artificial neural networks
  • Grinding
  • Multi-layer perceptron
  • Radial basis functions
  • Soft computing
  • Surface roughness

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Assessment of the performance of neural networks models for the prediction of surface roughness after grinding of steels. / Karkalos, Nikolaos E.; Kundrák, J.; Markopoulos, Angelos P.

In: International Journal of Artificial Intelligence, Vol. 15, No. 1, 01.03.2017, p. 55-75.

Research output: Contribution to journalArticle

@article{8c9a6810a7bf49d0b7cd3f2455b69d1c,
title = "Assessment of the performance of neural networks models for the prediction of surface roughness after grinding of steels",
abstract = "Attaining acceptable levels of surface roughness is one of the primary goals of grinding. In order to achieve this goal, several approaches can be employed by varying the system parameters and attempting to find the conditions which ameliorate the outcome of the process. One way that can be rather assistive to the analysis of manufacturing processes is the use of soft computing methods such as artificial neural networks. In the current work, artificial neural network models of various categories, namely multi-layer perceptron and radial basis function neural networks, with various model parameters are developed and compared in order to determine the best performing model for the prediction of surface roughness during peripheral grinding of steel components. The results indicate that radial basis function networks outperform classical multi-layer perceptrons and constitute a promising alternative for the modeling of manufacturing processes.",
keywords = "Artificial neural networks, Grinding, Multi-layer perceptron, Radial basis functions, Soft computing, Surface roughness",
author = "Karkalos, {Nikolaos E.} and J. Kundr{\'a}k and Markopoulos, {Angelos P.}",
year = "2017",
month = "3",
day = "1",
language = "English",
volume = "15",
pages = "55--75",
journal = "International Journal of Artificial Intelligence",
issn = "0974-0635",
publisher = "Indian Society for Development and Environment Research",
number = "1",

}

TY - JOUR

T1 - Assessment of the performance of neural networks models for the prediction of surface roughness after grinding of steels

AU - Karkalos, Nikolaos E.

AU - Kundrák, J.

AU - Markopoulos, Angelos P.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Attaining acceptable levels of surface roughness is one of the primary goals of grinding. In order to achieve this goal, several approaches can be employed by varying the system parameters and attempting to find the conditions which ameliorate the outcome of the process. One way that can be rather assistive to the analysis of manufacturing processes is the use of soft computing methods such as artificial neural networks. In the current work, artificial neural network models of various categories, namely multi-layer perceptron and radial basis function neural networks, with various model parameters are developed and compared in order to determine the best performing model for the prediction of surface roughness during peripheral grinding of steel components. The results indicate that radial basis function networks outperform classical multi-layer perceptrons and constitute a promising alternative for the modeling of manufacturing processes.

AB - Attaining acceptable levels of surface roughness is one of the primary goals of grinding. In order to achieve this goal, several approaches can be employed by varying the system parameters and attempting to find the conditions which ameliorate the outcome of the process. One way that can be rather assistive to the analysis of manufacturing processes is the use of soft computing methods such as artificial neural networks. In the current work, artificial neural network models of various categories, namely multi-layer perceptron and radial basis function neural networks, with various model parameters are developed and compared in order to determine the best performing model for the prediction of surface roughness during peripheral grinding of steel components. The results indicate that radial basis function networks outperform classical multi-layer perceptrons and constitute a promising alternative for the modeling of manufacturing processes.

KW - Artificial neural networks

KW - Grinding

KW - Multi-layer perceptron

KW - Radial basis functions

KW - Soft computing

KW - Surface roughness

UR - http://www.scopus.com/inward/record.url?scp=85015334046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015334046&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85015334046

VL - 15

SP - 55

EP - 75

JO - International Journal of Artificial Intelligence

JF - International Journal of Artificial Intelligence

SN - 0974-0635

IS - 1

ER -