Transfer Learning Applied to Characteristic Prediction of Injection Molded Products

This study addresses some issues regarding the problems of applying CAE to the injection molding production process where quite complex factors inhibit its effective utilization. In this study, an artificial neural network, namely a backpropagation neural network (BPNN), is utilized to render result...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yan-Mao Huang, Wen-Ren Jong, Shia-Chung Chen
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	injection molding CAE machine learning transfer learning Organic chemistry QD241-441
Acceso en línea:	https://doaj.org/article/88904077b7fc4856a55c5cbec3aaa53e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:88904077b7fc4856a55c5cbec3aaa53e
record_format	dspace
spelling	oai:doaj.org-article:88904077b7fc4856a55c5cbec3aaa53e2021-11-25T18:47:50ZTransfer Learning Applied to Characteristic Prediction of Injection Molded Products10.3390/polym132238742073-4360https://doaj.org/article/88904077b7fc4856a55c5cbec3aaa53e2021-11-01T00:00:00Zhttps://www.mdpi.com/2073-4360/13/22/3874https://doaj.org/toc/2073-4360This study addresses some issues regarding the problems of applying CAE to the injection molding production process where quite complex factors inhibit its effective utilization. In this study, an artificial neural network, namely a backpropagation neural network (BPNN), is utilized to render results predictions for the injection molding process. By inputting the plastic temperature, mold temperature, injection speed, holding pressure, and holding time in the molding parameters, these five results are more accurately predicted: EOF pressure, maximum cooling time, warpage along the <i>Z</i>-axis, shrinkage along the <i>X</i>-axis, and shrinkage along the <i>Y</i>-axis. This study first uses CAE analysis data as training data and reduces the error value to less than 5% through the Taguchi method and the random shuffle method, which we introduce herein, and then successfully transfers the network, which CAE data analysis has predicted to the actual machine for verification with the use of transfer learning. This study uses a backpropagation neural network (BPNN) to train a dedicated prediction network using different, large amounts of data for training the network, which has proved fast and can predict results accurately using our optimized model.Yan-Mao HuangWen-Ren JongShia-Chung ChenMDPI AGarticleinjection moldingCAEmachine learningtransfer learningOrganic chemistryQD241-441ENPolymers, Vol 13, Iss 3874, p 3874 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	injection molding CAE machine learning transfer learning Organic chemistry QD241-441
spellingShingle	injection molding CAE machine learning transfer learning Organic chemistry QD241-441 Yan-Mao Huang Wen-Ren Jong Shia-Chung Chen Transfer Learning Applied to Characteristic Prediction of Injection Molded Products
description	This study addresses some issues regarding the problems of applying CAE to the injection molding production process where quite complex factors inhibit its effective utilization. In this study, an artificial neural network, namely a backpropagation neural network (BPNN), is utilized to render results predictions for the injection molding process. By inputting the plastic temperature, mold temperature, injection speed, holding pressure, and holding time in the molding parameters, these five results are more accurately predicted: EOF pressure, maximum cooling time, warpage along the <i>Z</i>-axis, shrinkage along the <i>X</i>-axis, and shrinkage along the <i>Y</i>-axis. This study first uses CAE analysis data as training data and reduces the error value to less than 5% through the Taguchi method and the random shuffle method, which we introduce herein, and then successfully transfers the network, which CAE data analysis has predicted to the actual machine for verification with the use of transfer learning. This study uses a backpropagation neural network (BPNN) to train a dedicated prediction network using different, large amounts of data for training the network, which has proved fast and can predict results accurately using our optimized model.
format	article
author	Yan-Mao Huang Wen-Ren Jong Shia-Chung Chen
author_facet	Yan-Mao Huang Wen-Ren Jong Shia-Chung Chen
author_sort	Yan-Mao Huang
title	Transfer Learning Applied to Characteristic Prediction of Injection Molded Products
title_short	Transfer Learning Applied to Characteristic Prediction of Injection Molded Products
title_full	Transfer Learning Applied to Characteristic Prediction of Injection Molded Products
title_fullStr	Transfer Learning Applied to Characteristic Prediction of Injection Molded Products
title_full_unstemmed	Transfer Learning Applied to Characteristic Prediction of Injection Molded Products
title_sort	transfer learning applied to characteristic prediction of injection molded products
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/88904077b7fc4856a55c5cbec3aaa53e
work_keys_str_mv	AT yanmaohuang transferlearningappliedtocharacteristicpredictionofinjectionmoldedproducts AT wenrenjong transferlearningappliedtocharacteristicpredictionofinjectionmoldedproducts AT shiachungchen transferlearningappliedtocharacteristicpredictionofinjectionmoldedproducts
_version_	1718410722578268160

Transfer Learning Applied to Characteristic Prediction of Injection Molded Products

Ejemplares similares