Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks

Artificial neural networks (ANNs) as simplified model of mankind’s neural system, are capable of simulating and predicting real world complex problems which are challenging and expensive to model physically. In this study the correlation between the flow stresses and strain rate, temperature, stra...

Full description

Bibliographic Details
Main Authors:	Alibeiki, Esmaeil, Rajabi, Jamal, Rajabi, Javad
Format:	Article
Language:	English
Published:	Penerbit Universiti Kebangsaan Malaysia 2019
Online Access:	http://journalarticle.ukm.my/14298/ http://journalarticle.ukm.my/14298/ http://journalarticle.ukm.my/14298/1/06.pdf

id	ukm-14298
recordtype	eprints
spelling	ukm-142982020-02-26T06:28:04Z http://journalarticle.ukm.my/14298/ Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks Alibeiki, Esmaeil Rajabi, Jamal Rajabi, Javad Artificial neural networks (ANNs) as simplified model of mankind’s neural system, are capable of simulating and predicting real world complex problems which are challenging and expensive to model physically. In this study the correlation between the flow stresses and strain rate, temperature, strain in thermomechanical process of 40NICRMO8-4 alloy has been modelled. The results revealed that flow stress for every strain value is less at high temperatures compared to those at low temperatures and material resistance against deformation will also decrease as temperature goes down. Moreover, increasing in strain rate when temperature is constant results in recrystallization to happen in higher strain values at times shorter. The employed neural network for this study was a feed forward multilayer perceptron trained with common back propagation algorithm. Similar to any other ANNs, the employed network receives some parameters as inputs and delivers some as outputs. The inputs given to this model were temperature, strain and strain rate while flow stress parameter was collected as requested output. Outputs, with high precision of approximately 99% accuracy, were predicted and produced during training phase. Likewise, the predicted output of the ANN model achieved an R-value of about 0.99871 compared with of those experimental values. Best results were obtained with an ANN model consist of two hidden layers trained with Levenberg–Marquardt training algorithm. Penerbit Universiti Kebangsaan Malaysia 2019-04 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/14298/1/06.pdf Alibeiki, Esmaeil and Rajabi, Jamal and Rajabi, Javad (2019) Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks. Jurnal Kejuruteraan, 31 (1). pp. 47-56. ISSN 0128-0198 http://www.ukm.my/jkukm/volume-311-2019/
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Kebangasaan Malaysia
building	UKM Institutional Repository
collection	Online Access
language	English
description	Artificial neural networks (ANNs) as simplified model of mankind’s neural system, are capable of simulating and predicting real world complex problems which are challenging and expensive to model physically. In this study the correlation between the flow stresses and strain rate, temperature, strain in thermomechanical process of 40NICRMO8-4 alloy has been modelled. The results revealed that flow stress for every strain value is less at high temperatures compared to those at low temperatures and material resistance against deformation will also decrease as temperature goes down. Moreover, increasing in strain rate when temperature is constant results in recrystallization to happen in higher strain values at times shorter. The employed neural network for this study was a feed forward multilayer perceptron trained with common back propagation algorithm. Similar to any other ANNs, the employed network receives some parameters as inputs and delivers some as outputs. The inputs given to this model were temperature, strain and strain rate while flow stress parameter was collected as requested output. Outputs, with high precision of approximately 99% accuracy, were predicted and produced during training phase. Likewise, the predicted output of the ANN model achieved an R-value of about 0.99871 compared with of those experimental values. Best results were obtained with an ANN model consist of two hidden layers trained with Levenberg–Marquardt training algorithm.
format	Article
author	Alibeiki, Esmaeil Rajabi, Jamal Rajabi, Javad
spellingShingle	Alibeiki, Esmaeil Rajabi, Jamal Rajabi, Javad Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks
author_facet	Alibeiki, Esmaeil Rajabi, Jamal Rajabi, Javad
author_sort	Alibeiki, Esmaeil
title	Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks
title_short	Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks
title_full	Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks
title_fullStr	Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks
title_full_unstemmed	Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks
title_sort	thermomechanical process modelling of 40nicrmo8-4 alloy by artificial neural networks
publisher	Penerbit Universiti Kebangsaan Malaysia
publishDate	2019
url	http://journalarticle.ukm.my/14298/ http://journalarticle.ukm.my/14298/ http://journalarticle.ukm.my/14298/1/06.pdf
first_indexed	2023-09-18T20:06:47Z
last_indexed	2023-09-18T20:06:47Z
_version_	1777407211427856384

Thermomechanical process modelling of 40NICRMO8-4 alloy by artificial neural networks

Similar Items