Predictive modelling of surface roughness for double vibropolishing in trough system

Vibratory finishing is a ubiquitous surface finishing process administered to components of various functionalities. Alongside the development of more complex finishing techniques such as drag finishing and abrasive flow machining, significant progress on numerical simulation has also been achieved,...

Full description

Bibliographic Details
Main Authors: Alcaraz, Joselito Yam Tomacder, Mankar, A.V., Ahluwalia, Kunal, Mediratta, Rijul, Majumdar, Kausik Kumar, Yeo, Swee Hock
Other Authors: School of Mechanical and Aerospace Engineering
Format: Journal Article
Language:English
Published: 2018
Subjects:
Online Access:https://hdl.handle.net/10356/89945
http://hdl.handle.net/10220/47158
_version_ 1811686601538928640
author Alcaraz, Joselito Yam Tomacder
Mankar, A.V.
Ahluwalia, Kunal
Mediratta, Rijul
Majumdar, Kausik Kumar
Yeo, Swee Hock
author2 School of Mechanical and Aerospace Engineering
author_facet School of Mechanical and Aerospace Engineering
Alcaraz, Joselito Yam Tomacder
Mankar, A.V.
Ahluwalia, Kunal
Mediratta, Rijul
Majumdar, Kausik Kumar
Yeo, Swee Hock
author_sort Alcaraz, Joselito Yam Tomacder
collection NTU
description Vibratory finishing is a ubiquitous surface finishing process administered to components of various functionalities. Alongside the development of more complex finishing techniques such as drag finishing and abrasive flow machining, significant progress on numerical simulation has also been achieved, e.g. computational fluid dynamics, discrete element method. Yet, search into predictive roughness modelling has been insipid. In this study, multi-variable regression and artificial neural network modelling was done using experimental data obtained from subjecting rectangular test coupons to double vibropolishing in a vibratory trough. Two regression models, i.e. exponential and power, and several Multi-Layer Perceptron (MLP) architectures were trained using experimental data, and were subsequently evaluated for generalization ability. Model selection was done by comparing the mean-absolute percentage error and r-squared values from both training and testing datasets.
first_indexed 2024-10-01T05:03:01Z
format Journal Article
id ntu-10356/89945
institution Nanyang Technological University
language English
last_indexed 2024-10-01T05:03:01Z
publishDate 2018
record_format dspace
spelling ntu-10356/899452023-03-04T17:17:10Z Predictive modelling of surface roughness for double vibropolishing in trough system Alcaraz, Joselito Yam Tomacder Mankar, A.V. Ahluwalia, Kunal Mediratta, Rijul Majumdar, Kausik Kumar Yeo, Swee Hock School of Mechanical and Aerospace Engineering Rolls-Royce@NTU Corporate Lab Numerical Modelling Vibratory Finishing DRNTU::Engineering::Mechanical engineering Vibratory finishing is a ubiquitous surface finishing process administered to components of various functionalities. Alongside the development of more complex finishing techniques such as drag finishing and abrasive flow machining, significant progress on numerical simulation has also been achieved, e.g. computational fluid dynamics, discrete element method. Yet, search into predictive roughness modelling has been insipid. In this study, multi-variable regression and artificial neural network modelling was done using experimental data obtained from subjecting rectangular test coupons to double vibropolishing in a vibratory trough. Two regression models, i.e. exponential and power, and several Multi-Layer Perceptron (MLP) architectures were trained using experimental data, and were subsequently evaluated for generalization ability. Model selection was done by comparing the mean-absolute percentage error and r-squared values from both training and testing datasets. NRF (Natl Research Foundation, S’pore) Published version 2018-12-21T03:55:21Z 2019-12-06T17:37:10Z 2018-12-21T03:55:21Z 2019-12-06T17:37:10Z 2018 Journal Article Alcaraz, J. Y. T., Mankar, A. V., Ahluwalia, K., Mediratta, R., Majumdar, K. M., & Yeo, S. H. (2018). Predictive Modelling of Surface Roughness for Double Vibropolishing in Trough System. Procedia CIRP, 77, 489-492. doi:10.1016/j.procir.2018.08.258 2212-8271 https://hdl.handle.net/10356/89945 http://hdl.handle.net/10220/47158 10.1016/j.procir.2018.08.258 en Procedia CIRP © 2018 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/). 4 p. application/pdf
spellingShingle Numerical Modelling
Vibratory Finishing
DRNTU::Engineering::Mechanical engineering
Alcaraz, Joselito Yam Tomacder
Mankar, A.V.
Ahluwalia, Kunal
Mediratta, Rijul
Majumdar, Kausik Kumar
Yeo, Swee Hock
Predictive modelling of surface roughness for double vibropolishing in trough system
title Predictive modelling of surface roughness for double vibropolishing in trough system
title_full Predictive modelling of surface roughness for double vibropolishing in trough system
title_fullStr Predictive modelling of surface roughness for double vibropolishing in trough system
title_full_unstemmed Predictive modelling of surface roughness for double vibropolishing in trough system
title_short Predictive modelling of surface roughness for double vibropolishing in trough system
title_sort predictive modelling of surface roughness for double vibropolishing in trough system
topic Numerical Modelling
Vibratory Finishing
DRNTU::Engineering::Mechanical engineering
url https://hdl.handle.net/10356/89945
http://hdl.handle.net/10220/47158
work_keys_str_mv AT alcarazjoselitoyamtomacder predictivemodellingofsurfaceroughnessfordoublevibropolishingintroughsystem
AT mankarav predictivemodellingofsurfaceroughnessfordoublevibropolishingintroughsystem
AT ahluwaliakunal predictivemodellingofsurfaceroughnessfordoublevibropolishingintroughsystem
AT medirattarijul predictivemodellingofsurfaceroughnessfordoublevibropolishingintroughsystem
AT majumdarkausikkumar predictivemodellingofsurfaceroughnessfordoublevibropolishingintroughsystem
AT yeosweehock predictivemodellingofsurfaceroughnessfordoublevibropolishingintroughsystem