Application of KNN and ANN Metamodeling for RTM Filling Process Prediction
Process simulation is frequently adopted to facilitate the optimization of the resin transfer molding process. However, it is computationally costly to simulate the multi-physical, multi-scale process, making it infeasible for applications involving huge datasets. In this study, the application of K...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Materials |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1944/16/18/6115 |
_version_ | 1797579085522665472 |
---|---|
author | Boon Xian Chai Boris Eisenbart Mostafa Nikzad Bronwyn Fox Ashley Blythe Kyaw Hlaing Bwar Jinze Wang Yuntong Du Sergey Shevtsov |
author_facet | Boon Xian Chai Boris Eisenbart Mostafa Nikzad Bronwyn Fox Ashley Blythe Kyaw Hlaing Bwar Jinze Wang Yuntong Du Sergey Shevtsov |
author_sort | Boon Xian Chai |
collection | DOAJ |
description | Process simulation is frequently adopted to facilitate the optimization of the resin transfer molding process. However, it is computationally costly to simulate the multi-physical, multi-scale process, making it infeasible for applications involving huge datasets. In this study, the application of K-nearest neighbors and artificial neural network metamodels is proposed to build predictive surrogate models capable of relating the mold-filling process input-output correlations to assist mold designing. The input features considered are the resin injection location and resin viscosity. The corresponding output features investigated are the number of vents required and the resultant maximum injection pressure. Upon training, both investigated metamodels demonstrated desirable prediction accuracies, with a low prediction error range of 5.0% to 15.7% for KNN metamodels and 6.7% to 17.5% for ANN metamodels. The good prediction results convincingly indicate that metamodeling is a promising option for composite molding applications, with encouraging prospects for data-intensive applications such as process digital twinning. |
first_indexed | 2024-03-10T22:30:59Z |
format | Article |
id | doaj.art-514e36f384394b80a799d1888c713eba |
institution | Directory Open Access Journal |
issn | 1996-1944 |
language | English |
last_indexed | 2024-03-10T22:30:59Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Materials |
spelling | doaj.art-514e36f384394b80a799d1888c713eba2023-11-19T11:43:05ZengMDPI AGMaterials1996-19442023-09-011618611510.3390/ma16186115Application of KNN and ANN Metamodeling for RTM Filling Process PredictionBoon Xian Chai0Boris Eisenbart1Mostafa Nikzad2Bronwyn Fox3Ashley Blythe4Kyaw Hlaing Bwar5Jinze Wang6Yuntong Du7Sergey Shevtsov8Faculty of Science, Engineering and Technology, Swinburne University of Technology, Hawthorn, VIC 3122, AustraliaFaculty of Science, Engineering and Technology, Swinburne University of Technology, Hawthorn, VIC 3122, AustraliaFaculty of Science, Engineering and Technology, Swinburne University of Technology, Hawthorn, VIC 3122, AustraliaCSIRO, Clayton, VIC 3168, AustraliaFaculty of Science, Engineering and Technology, Swinburne University of Technology, Hawthorn, VIC 3122, AustraliaFaculty of Science, Engineering and Technology, Swinburne University of Technology, Hawthorn, VIC 3122, AustraliaFaculty of Science, Engineering and Technology, Swinburne University of Technology, Hawthorn, VIC 3122, AustraliaChina Ship Scientific Research Center, Wuxi 214082, ChinaDepartment of Transport, Composite Materials and Structures, Southern Center of Russian Academy of Science, 344006 Rostov-on-Don, RussiaProcess simulation is frequently adopted to facilitate the optimization of the resin transfer molding process. However, it is computationally costly to simulate the multi-physical, multi-scale process, making it infeasible for applications involving huge datasets. In this study, the application of K-nearest neighbors and artificial neural network metamodels is proposed to build predictive surrogate models capable of relating the mold-filling process input-output correlations to assist mold designing. The input features considered are the resin injection location and resin viscosity. The corresponding output features investigated are the number of vents required and the resultant maximum injection pressure. Upon training, both investigated metamodels demonstrated desirable prediction accuracies, with a low prediction error range of 5.0% to 15.7% for KNN metamodels and 6.7% to 17.5% for ANN metamodels. The good prediction results convincingly indicate that metamodeling is a promising option for composite molding applications, with encouraging prospects for data-intensive applications such as process digital twinning.https://www.mdpi.com/1996-1944/16/18/6115numerical analysisprocess simulationresin transfer molding (RTM)resin flow |
spellingShingle | Boon Xian Chai Boris Eisenbart Mostafa Nikzad Bronwyn Fox Ashley Blythe Kyaw Hlaing Bwar Jinze Wang Yuntong Du Sergey Shevtsov Application of KNN and ANN Metamodeling for RTM Filling Process Prediction Materials numerical analysis process simulation resin transfer molding (RTM) resin flow |
title | Application of KNN and ANN Metamodeling for RTM Filling Process Prediction |
title_full | Application of KNN and ANN Metamodeling for RTM Filling Process Prediction |
title_fullStr | Application of KNN and ANN Metamodeling for RTM Filling Process Prediction |
title_full_unstemmed | Application of KNN and ANN Metamodeling for RTM Filling Process Prediction |
title_short | Application of KNN and ANN Metamodeling for RTM Filling Process Prediction |
title_sort | application of knn and ann metamodeling for rtm filling process prediction |
topic | numerical analysis process simulation resin transfer molding (RTM) resin flow |
url | https://www.mdpi.com/1996-1944/16/18/6115 |
work_keys_str_mv | AT boonxianchai applicationofknnandannmetamodelingforrtmfillingprocessprediction AT boriseisenbart applicationofknnandannmetamodelingforrtmfillingprocessprediction AT mostafanikzad applicationofknnandannmetamodelingforrtmfillingprocessprediction AT bronwynfox applicationofknnandannmetamodelingforrtmfillingprocessprediction AT ashleyblythe applicationofknnandannmetamodelingforrtmfillingprocessprediction AT kyawhlaingbwar applicationofknnandannmetamodelingforrtmfillingprocessprediction AT jinzewang applicationofknnandannmetamodelingforrtmfillingprocessprediction AT yuntongdu applicationofknnandannmetamodelingforrtmfillingprocessprediction AT sergeyshevtsov applicationofknnandannmetamodelingforrtmfillingprocessprediction |