Application of Generalized Regression Neural Network and Gaussian Process Regression for Modelling Hybrid Micro-Electric Discharge Machining: A Comparative Study

Micro-Electric Discharge Machining (μ-EDM) is one of the widely applied micromanufacturing processes. However, it has several limitations, such as a low cutting rate, difficult debris removal, and poor surface integrity, etc. Hybridization of the μ-EDM is proposed as an alternative to overcome the p...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Processes 2022-04, Vol.10 (4), p.755
Hauptverfasser: Singh, Siddhartha Kumar, Mali, Harlal Singh, Unune, Deepak Rajendra, Wojciechowski, Szymon, Wilczyński, Dominik
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 4
container_start_page 755
container_title Processes
container_volume 10
creator Singh, Siddhartha Kumar
Mali, Harlal Singh
Unune, Deepak Rajendra
Wojciechowski, Szymon
Wilczyński, Dominik
description Micro-Electric Discharge Machining (μ-EDM) is one of the widely applied micromanufacturing processes. However, it has several limitations, such as a low cutting rate, difficult debris removal, and poor surface integrity, etc. Hybridization of the μ-EDM is proposed as an alternative to overcome the process limitations. Conversely, it complicates the process nature and poses a challenge for modelling and predicting critical process responses. Therefore, in this work, two distinct, nonparametric, previously unreported, workpiece material independent models using a Generalized Regression Neural Network (GRNN) and Gaussian Process Regression (GPR) were developed and compared to assess their performance with limited training data. Various smoothing factors and kernels were tested for GRNN and GPR, respectively. The prediction of models was compared in terms of the mean absolute percentage error, root mean square error, and coefficient of determination. The results showed that GPR outperforms GRNN and accurately predicts the μ-EDM process responses. The GRNN’s performance was better for less stochastic output with a discernible pattern than other outputs. The Automatic Relevance Determination (ARD) squared exponential kernel was found to be the best performing kernel among those chosen. GPR models can be used with reasonable accuracy to predetermine critical process outputs as they have R2 values above 0.90 for both training and validation data for all outputs. This work paves the way for future industrial implementation of GPR to model and predict the outputs of complex hybrid machining processes.
doi_str_mv 10.3390/pr10040755
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2653018805</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2653018805</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2105-dd543b18086b644685957e61ec4206063a2aef59638d3a2e6ba36bce2ec1c1363</originalsourceid><addsrcrecordid>eNpNkdtKw0AQhhdRUGpvfIIF74ToHrKbxLtSayu0Kh6uw2YzaVfTbNxNlPo2vqlbKti5mZ-ZjznwI3RGySXnGblqHSUkJokQB-iEMZZEWUKTwz19jIbev5EQGeWpkCfoZ9S2tdGqM7bBtsJTaMCp2nxDiZ9g6cD7bece-lANqfuy7h2rpsRT1YeeavCjszpg-3hlHV7YEuraNEs82xTOlHhhtLPRpAbdOaPxjfF6pdwS8ELplWkCeY1HeGzXrXLhnk_Az11fbk7RUaVqD8O_PECvt5OX8SyaP0zvxqN5pBklIipLEfOCpiSVhYxjmYpMJCAp6JgRSSRXTEElMsnTMmiQheKy0MBAU0255AN0vpvbOvvRg-_yN9u7JqzMmRSc0DQlIlAXOyr84r2DKm-dWSu3ySnJty7k_y7wX20Ye7A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2653018805</pqid></control><display><type>article</type><title>Application of Generalized Regression Neural Network and Gaussian Process Regression for Modelling Hybrid Micro-Electric Discharge Machining: A Comparative Study</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Singh, Siddhartha Kumar ; Mali, Harlal Singh ; Unune, Deepak Rajendra ; Wojciechowski, Szymon ; Wilczyński, Dominik</creator><creatorcontrib>Singh, Siddhartha Kumar ; Mali, Harlal Singh ; Unune, Deepak Rajendra ; Wojciechowski, Szymon ; Wilczyński, Dominik</creatorcontrib><description>Micro-Electric Discharge Machining (μ-EDM) is one of the widely applied micromanufacturing processes. However, it has several limitations, such as a low cutting rate, difficult debris removal, and poor surface integrity, etc. Hybridization of the μ-EDM is proposed as an alternative to overcome the process limitations. Conversely, it complicates the process nature and poses a challenge for modelling and predicting critical process responses. Therefore, in this work, two distinct, nonparametric, previously unreported, workpiece material independent models using a Generalized Regression Neural Network (GRNN) and Gaussian Process Regression (GPR) were developed and compared to assess their performance with limited training data. Various smoothing factors and kernels were tested for GRNN and GPR, respectively. The prediction of models was compared in terms of the mean absolute percentage error, root mean square error, and coefficient of determination. The results showed that GPR outperforms GRNN and accurately predicts the μ-EDM process responses. The GRNN’s performance was better for less stochastic output with a discernible pattern than other outputs. The Automatic Relevance Determination (ARD) squared exponential kernel was found to be the best performing kernel among those chosen. GPR models can be used with reasonable accuracy to predetermine critical process outputs as they have R2 values above 0.90 for both training and validation data for all outputs. This work paves the way for future industrial implementation of GPR to model and predict the outputs of complex hybrid machining processes.</description><identifier>ISSN: 2227-9717</identifier><identifier>EISSN: 2227-9717</identifier><identifier>DOI: 10.3390/pr10040755</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Comparative studies ; Data smoothing ; Electric discharge machining ; Electrodes ; Energy ; Experiments ; Friction stir welding ; Gaussian process ; Hybridization ; Kernels ; Machine learning ; Manufacturing ; Modelling ; Neural networks ; Regression ; Regression analysis ; Shear strength ; Stochasticity ; Training ; Workpieces</subject><ispartof>Processes, 2022-04, Vol.10 (4), p.755</ispartof><rights>2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2105-dd543b18086b644685957e61ec4206063a2aef59638d3a2e6ba36bce2ec1c1363</citedby><cites>FETCH-LOGICAL-c2105-dd543b18086b644685957e61ec4206063a2aef59638d3a2e6ba36bce2ec1c1363</cites><orcidid>0000-0002-9341-1962 ; 0000-0002-3985-0403 ; 0000-0002-8152-3553 ; 0000-0002-3380-4588 ; 0000-0003-1758-6063</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Singh, Siddhartha Kumar</creatorcontrib><creatorcontrib>Mali, Harlal Singh</creatorcontrib><creatorcontrib>Unune, Deepak Rajendra</creatorcontrib><creatorcontrib>Wojciechowski, Szymon</creatorcontrib><creatorcontrib>Wilczyński, Dominik</creatorcontrib><title>Application of Generalized Regression Neural Network and Gaussian Process Regression for Modelling Hybrid Micro-Electric Discharge Machining: A Comparative Study</title><title>Processes</title><description>Micro-Electric Discharge Machining (μ-EDM) is one of the widely applied micromanufacturing processes. However, it has several limitations, such as a low cutting rate, difficult debris removal, and poor surface integrity, etc. Hybridization of the μ-EDM is proposed as an alternative to overcome the process limitations. Conversely, it complicates the process nature and poses a challenge for modelling and predicting critical process responses. Therefore, in this work, two distinct, nonparametric, previously unreported, workpiece material independent models using a Generalized Regression Neural Network (GRNN) and Gaussian Process Regression (GPR) were developed and compared to assess their performance with limited training data. Various smoothing factors and kernels were tested for GRNN and GPR, respectively. The prediction of models was compared in terms of the mean absolute percentage error, root mean square error, and coefficient of determination. The results showed that GPR outperforms GRNN and accurately predicts the μ-EDM process responses. The GRNN’s performance was better for less stochastic output with a discernible pattern than other outputs. The Automatic Relevance Determination (ARD) squared exponential kernel was found to be the best performing kernel among those chosen. GPR models can be used with reasonable accuracy to predetermine critical process outputs as they have R2 values above 0.90 for both training and validation data for all outputs. This work paves the way for future industrial implementation of GPR to model and predict the outputs of complex hybrid machining processes.</description><subject>Comparative studies</subject><subject>Data smoothing</subject><subject>Electric discharge machining</subject><subject>Electrodes</subject><subject>Energy</subject><subject>Experiments</subject><subject>Friction stir welding</subject><subject>Gaussian process</subject><subject>Hybridization</subject><subject>Kernels</subject><subject>Machine learning</subject><subject>Manufacturing</subject><subject>Modelling</subject><subject>Neural networks</subject><subject>Regression</subject><subject>Regression analysis</subject><subject>Shear strength</subject><subject>Stochasticity</subject><subject>Training</subject><subject>Workpieces</subject><issn>2227-9717</issn><issn>2227-9717</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNpNkdtKw0AQhhdRUGpvfIIF74ToHrKbxLtSayu0Kh6uw2YzaVfTbNxNlPo2vqlbKti5mZ-ZjznwI3RGySXnGblqHSUkJokQB-iEMZZEWUKTwz19jIbev5EQGeWpkCfoZ9S2tdGqM7bBtsJTaMCp2nxDiZ9g6cD7bece-lANqfuy7h2rpsRT1YeeavCjszpg-3hlHV7YEuraNEs82xTOlHhhtLPRpAbdOaPxjfF6pdwS8ELplWkCeY1HeGzXrXLhnk_Az11fbk7RUaVqD8O_PECvt5OX8SyaP0zvxqN5pBklIipLEfOCpiSVhYxjmYpMJCAp6JgRSSRXTEElMsnTMmiQheKy0MBAU0255AN0vpvbOvvRg-_yN9u7JqzMmRSc0DQlIlAXOyr84r2DKm-dWSu3ySnJty7k_y7wX20Ye7A</recordid><startdate>20220413</startdate><enddate>20220413</enddate><creator>Singh, Siddhartha Kumar</creator><creator>Mali, Harlal Singh</creator><creator>Unune, Deepak Rajendra</creator><creator>Wojciechowski, Szymon</creator><creator>Wilczyński, Dominik</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SR</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JG9</scope><scope>KB.</scope><scope>LK8</scope><scope>M7P</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><orcidid>https://orcid.org/0000-0002-9341-1962</orcidid><orcidid>https://orcid.org/0000-0002-3985-0403</orcidid><orcidid>https://orcid.org/0000-0002-8152-3553</orcidid><orcidid>https://orcid.org/0000-0002-3380-4588</orcidid><orcidid>https://orcid.org/0000-0003-1758-6063</orcidid></search><sort><creationdate>20220413</creationdate><title>Application of Generalized Regression Neural Network and Gaussian Process Regression for Modelling Hybrid Micro-Electric Discharge Machining: A Comparative Study</title><author>Singh, Siddhartha Kumar ; Mali, Harlal Singh ; Unune, Deepak Rajendra ; Wojciechowski, Szymon ; Wilczyński, Dominik</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2105-dd543b18086b644685957e61ec4206063a2aef59638d3a2e6ba36bce2ec1c1363</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Comparative studies</topic><topic>Data smoothing</topic><topic>Electric discharge machining</topic><topic>Electrodes</topic><topic>Energy</topic><topic>Experiments</topic><topic>Friction stir welding</topic><topic>Gaussian process</topic><topic>Hybridization</topic><topic>Kernels</topic><topic>Machine learning</topic><topic>Manufacturing</topic><topic>Modelling</topic><topic>Neural networks</topic><topic>Regression</topic><topic>Regression analysis</topic><topic>Shear strength</topic><topic>Stochasticity</topic><topic>Training</topic><topic>Workpieces</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Singh, Siddhartha Kumar</creatorcontrib><creatorcontrib>Mali, Harlal Singh</creatorcontrib><creatorcontrib>Unune, Deepak Rajendra</creatorcontrib><creatorcontrib>Wojciechowski, Szymon</creatorcontrib><creatorcontrib>Wilczyński, Dominik</creatorcontrib><collection>CrossRef</collection><collection>Engineered Materials Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>Materials Research Database</collection><collection>Materials Science Database</collection><collection>ProQuest Biological Science Collection</collection><collection>Biological Science Database</collection><collection>Materials Science Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Processes</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Singh, Siddhartha Kumar</au><au>Mali, Harlal Singh</au><au>Unune, Deepak Rajendra</au><au>Wojciechowski, Szymon</au><au>Wilczyński, Dominik</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Application of Generalized Regression Neural Network and Gaussian Process Regression for Modelling Hybrid Micro-Electric Discharge Machining: A Comparative Study</atitle><jtitle>Processes</jtitle><date>2022-04-13</date><risdate>2022</risdate><volume>10</volume><issue>4</issue><spage>755</spage><pages>755-</pages><issn>2227-9717</issn><eissn>2227-9717</eissn><abstract>Micro-Electric Discharge Machining (μ-EDM) is one of the widely applied micromanufacturing processes. However, it has several limitations, such as a low cutting rate, difficult debris removal, and poor surface integrity, etc. Hybridization of the μ-EDM is proposed as an alternative to overcome the process limitations. Conversely, it complicates the process nature and poses a challenge for modelling and predicting critical process responses. Therefore, in this work, two distinct, nonparametric, previously unreported, workpiece material independent models using a Generalized Regression Neural Network (GRNN) and Gaussian Process Regression (GPR) were developed and compared to assess their performance with limited training data. Various smoothing factors and kernels were tested for GRNN and GPR, respectively. The prediction of models was compared in terms of the mean absolute percentage error, root mean square error, and coefficient of determination. The results showed that GPR outperforms GRNN and accurately predicts the μ-EDM process responses. The GRNN’s performance was better for less stochastic output with a discernible pattern than other outputs. The Automatic Relevance Determination (ARD) squared exponential kernel was found to be the best performing kernel among those chosen. GPR models can be used with reasonable accuracy to predetermine critical process outputs as they have R2 values above 0.90 for both training and validation data for all outputs. This work paves the way for future industrial implementation of GPR to model and predict the outputs of complex hybrid machining processes.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/pr10040755</doi><orcidid>https://orcid.org/0000-0002-9341-1962</orcidid><orcidid>https://orcid.org/0000-0002-3985-0403</orcidid><orcidid>https://orcid.org/0000-0002-8152-3553</orcidid><orcidid>https://orcid.org/0000-0002-3380-4588</orcidid><orcidid>https://orcid.org/0000-0003-1758-6063</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2227-9717
ispartof Processes, 2022-04, Vol.10 (4), p.755
issn 2227-9717
2227-9717
language eng
recordid cdi_proquest_journals_2653018805
source MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals
subjects Comparative studies
Data smoothing
Electric discharge machining
Electrodes
Energy
Experiments
Friction stir welding
Gaussian process
Hybridization
Kernels
Machine learning
Manufacturing
Modelling
Neural networks
Regression
Regression analysis
Shear strength
Stochasticity
Training
Workpieces
title Application of Generalized Regression Neural Network and Gaussian Process Regression for Modelling Hybrid Micro-Electric Discharge Machining: A Comparative Study
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T06%3A46%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Application%20of%20Generalized%20Regression%20Neural%20Network%20and%20Gaussian%20Process%20Regression%20for%20Modelling%20Hybrid%20Micro-Electric%20Discharge%20Machining:%20A%20Comparative%20Study&rft.jtitle=Processes&rft.au=Singh,%20Siddhartha%20Kumar&rft.date=2022-04-13&rft.volume=10&rft.issue=4&rft.spage=755&rft.pages=755-&rft.issn=2227-9717&rft.eissn=2227-9717&rft_id=info:doi/10.3390/pr10040755&rft_dat=%3Cproquest_cross%3E2653018805%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2653018805&rft_id=info:pmid/&rfr_iscdi=true