ABOUT INDEXING EDITORIAL BOARD ARCHIVES AUTHOR GUIDELINES SUBMIT PAPER NEWS, EVENTS AUTHOR'S PAGE CONTACT
Materiale Plastice
Cite as: Mater. Plast.
https://doi.org/10.37358/Mat.Plast.1964

OSIM Nr. R102356
ISSN Print 0025-5289
ISSN Online 2668-8220
Materiale Plastice - Latest Issue

Latest Issue >>>
ARCHIVES
   Volume 61, 2024
   Volume 60, 2023
   Volume 59, 2022
   Volume 58, 2021
   Volume 57, 2020
   Volume 56, 2019
   Volume 55, 2018
   Volume 54, 2017
   Volume 53, 2016
   Volume 52, 2015
   Volume 51, 2014
   Volume 50, 2013
   Volume 49, 2012
   Volume 48, 2011
   Volume 47, 2010
   Volume 46, 2009
   Volume 45, 2008
   Volume 44, 2007
   Volume 43, 2006
   Volume 42, 2005
   Volume 41, 2004
   Volume 40, 2003
 
<<<< back

Materiale Plastice (Mater. Plast.), Year 2024, Volume 61, Issue 1, 43-65

https://doi.org/10.37358/MP.24.1.5702

Subhash Selvaraj, Rajesh P.k.

Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms


Abstract:
Part dimensional inaccuracies serve as a barrier from adopting Additive Manufacturing (AM) processes in mass production. Fused Deposition Modeling (FDM) is a thermoplastic based low cost AM process which can create conceptual models, prototypes and end user industrial parts. The current study involves predicting the optimal parameter settings and significant parameter for reduced geometric deviations in printed part using Nylon filament reinforced with 20% carbon fiber. Five input factors such as build orientation, layer thickness, infill density, raster angle and infill pattern have been considered for preparing the experimental layout through taguchi’s mixed fractional factorial design. The changes in length, width and thickness of the printed part from CAD value have been evaluated individually through ANOVA and Signal to Noise Ratio method (Smaller the better). Layer thickness is significant only for variations in length, but build orientation affects both width and thickness dimensions. The geometric deviations are further analyzed using combined multi criteria decision making (MCDM) approaches such as Entropy-CoCoSo and PCA-TOPSIS. The optimal parameter settings obtained for reduced geometric deviations is found to be Flat orientation, 0.1mm layer thickness, 50% infill density, 0° raster angle and cubic infill pattern. Layer thickness is found to be highly significant parameter influencing the geometric deviations subsequently followed by build orientation from both the MCDM methods. The multi response performance index values obtained from Entropy-CoCoSo has been trained using classification algorithms such as decision tree, random forest and Naive Bayes. Naive Bayes algorithm outperformed other methods with highest classification accuracy of 99.4% in a training-testing split ratio of 75:25.


Keywords:
nylon Composites; Principal Component Analysis; TOPSIS; CoCoSo; entropy; decision tree algorithms

Issue: 2024 Volume 61, Issue 1
Pages: 43-65
Publication date: 2024/4/1
https://doi.org/10.37358/MP.24.1.5702
download pdf   Download Pdf Article
Creative Commons License
This article is published under the Creative Commons Attribution 4.0 International License
Citation Styles
Cite this article as:
SELVARAJ, S., P.K., R., Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms, Mater. Plast., 61(1), 2024, 43-65. https://doi.org/10.37358/MP.24.1.5702

Vancouver
Selvaraj S, P.k. R. Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms. Mater. Plast.[internet]. 2024 Jan;61(1):43-65. Available from: https://doi.org/10.37358/MP.24.1.5702


APA 6th edition
Selvaraj, S., P.k., R. (2024). Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms. Materiale Plastice, 61(1), 43-65. https://doi.org/10.37358/MP.24.1.5702


Harvard
Selvaraj, S., P.k., R. (2024). 'Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms', Materiale Plastice, 61(1), pp. 43-65. https://doi.org/10.37358/MP.24.1.5702


IEEE
S. Selvaraj, R. P.k., "Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms". Materiale Plastice, vol. 61, no. 1, pp. 43-65, 2024. [online]. https://doi.org/10.37358/MP.24.1.5702


Text
Subhash Selvaraj, Rajesh P.k.,
Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms,
Materiale Plastice,
Volume 61, Issue 1,
2024,
Pages 43-65,
ISSN 2668-8220,
https://doi.org/10.37358/MP.24.1.5702.
(https://revmaterialeplastice.ro/Articles.asp?ID=5702)
Keywords: nylon Composites; Principal Component Analysis; TOPSIS; CoCoSo; entropy; decision tree algorithms


RIS
TY - JOUR
T1 - Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms
A1 - Selvaraj, Subhash
A2 - P.k., Rajesh
JF - Materiale Plastice
JO - Mater. Plast.
PB - Materiale Plastice SRL
SN - 2668-8220
Y1 - 2024
VL - 61
IS - 1
SP - 43
EP - 65
UR - https://doi.org/10.37358/MP.24.1.5702
KW - nylon Composites
KW - Principal Component Analysis
KW - TOPSIS
KW - CoCoSo
KW - entropy
KW - decision tree algorithms
ER -


BibTex
@article{MatPlast2024P43,
author = {Selvaraj Subhash and P.k. Rajesh},
title = {Prediction of Optimal Parameter Settings and Significant Parameter for Reduced Geometric Deviations Through Multi Criteria Decision Making and Machine Learning Algorithms},
journal = {Materiale Plastice},
volume = {61},
number = {1},
pages = {43-65},
year = {2024},
issn = {2668-8220},
doi = {https://doi.org/10.37358/MP.24.1.5702},
url = {https://revmaterialeplastice.ro/Articles.asp?ID=5702}
}


Download article Citations:
 PlainText citation Plain Text
 Text citation Text
 GoogleScholar citation Google Scholar


Downloads number: 11
<<<< back
 
  Search Authors
Crossref Member Badge
 DOI  logo
 Gold Open Access | Source=http://www.plos.org/  | Author=art designer at PLoS
Creative Commons License