Estimation of finish cooling temperature by artificial neural networks of backpropagation during accelerated control cooling process

Hwan Suk Lim, Yong Tae Kang

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Artificial Neuron Networks (ANN) is considered one of the most practical technologies in the fields of intelligent manufacturing. In this study, the conventional heat transfer model and multilayer ANN analysis are compared to analyze the accelerated control cooling process, and the accuracy improvement of finish cooling temperature prediction by the ANN is evaluated. The temperature prediction error from the heat transfer model tends to increase with increasing the start cooling temperature in Curie temperature. It is found that the specific heat for low carbon steel shows a nonlinear tendency in Curie temperature. The ANN of backpropagation is applied to solve the nonlinear tendency of the specific heat. In the ANN analysis, the key parameters such as dimensions of plate, chemistry, start cooling temperature, air cooling time, water cooling time are selected as the input values. The hyperbolic tangent, sigmoid and linear functions are applied for the activation functions. The weights training was conducted 100,000 times, the weights were trained to satisfy the standard deviation of finish cooling temperature within 10.56 K. It was found that the accuracy from the ANN analysis was improved 2.74 times than the heat transfer model with least square method. It was concluded that the ANN with multilayer type could train the weights by the effect of the nonlinear trend of specific heat according to temperature. It is recommended that the heat transfer model should be replaced by the neural networks method of 3 layers (one input-layer, one hidden-layer, one output-layer) with the trained weights for the precise control cooling.

Original languageEnglish
Pages (from-to)579-588
Number of pages10
JournalInternational Journal of Heat and Mass Transfer
Volume126
DOIs
Publication statusPublished - 2018 Nov 1

Fingerprint

Backpropagation
neurons
Neurons
Cooling
Neural networks
cooling
network analysis
Electric network analysis
heat transfer
Heat transfer
Specific heat
Temperature
specific heat
Curie temperature
temperature
Multilayers
tendencies
air cooling
low carbon steels
liquid cooling

Keywords

  • Accelerated control cooling
  • Artificial neural networks
  • Finish cooling temperature
  • Heat transfer model
  • Temperature prediction accuracy

ASJC Scopus subject areas

  • Condensed Matter Physics
  • Mechanical Engineering
  • Fluid Flow and Transfer Processes

Cite this

@article{6e4b4a23a1f54f2c9edeb1083dc1f006,
title = "Estimation of finish cooling temperature by artificial neural networks of backpropagation during accelerated control cooling process",
abstract = "Artificial Neuron Networks (ANN) is considered one of the most practical technologies in the fields of intelligent manufacturing. In this study, the conventional heat transfer model and multilayer ANN analysis are compared to analyze the accelerated control cooling process, and the accuracy improvement of finish cooling temperature prediction by the ANN is evaluated. The temperature prediction error from the heat transfer model tends to increase with increasing the start cooling temperature in Curie temperature. It is found that the specific heat for low carbon steel shows a nonlinear tendency in Curie temperature. The ANN of backpropagation is applied to solve the nonlinear tendency of the specific heat. In the ANN analysis, the key parameters such as dimensions of plate, chemistry, start cooling temperature, air cooling time, water cooling time are selected as the input values. The hyperbolic tangent, sigmoid and linear functions are applied for the activation functions. The weights training was conducted 100,000 times, the weights were trained to satisfy the standard deviation of finish cooling temperature within 10.56 K. It was found that the accuracy from the ANN analysis was improved 2.74 times than the heat transfer model with least square method. It was concluded that the ANN with multilayer type could train the weights by the effect of the nonlinear trend of specific heat according to temperature. It is recommended that the heat transfer model should be replaced by the neural networks method of 3 layers (one input-layer, one hidden-layer, one output-layer) with the trained weights for the precise control cooling.",
keywords = "Accelerated control cooling, Artificial neural networks, Finish cooling temperature, Heat transfer model, Temperature prediction accuracy",
author = "Lim, {Hwan Suk} and Kang, {Yong Tae}",
year = "2018",
month = "11",
day = "1",
doi = "10.1016/j.ijheatmasstransfer.2018.06.022",
language = "English",
volume = "126",
pages = "579--588",
journal = "International Journal of Heat and Mass Transfer",
issn = "0017-9310",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Estimation of finish cooling temperature by artificial neural networks of backpropagation during accelerated control cooling process

AU - Lim, Hwan Suk

AU - Kang, Yong Tae

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Artificial Neuron Networks (ANN) is considered one of the most practical technologies in the fields of intelligent manufacturing. In this study, the conventional heat transfer model and multilayer ANN analysis are compared to analyze the accelerated control cooling process, and the accuracy improvement of finish cooling temperature prediction by the ANN is evaluated. The temperature prediction error from the heat transfer model tends to increase with increasing the start cooling temperature in Curie temperature. It is found that the specific heat for low carbon steel shows a nonlinear tendency in Curie temperature. The ANN of backpropagation is applied to solve the nonlinear tendency of the specific heat. In the ANN analysis, the key parameters such as dimensions of plate, chemistry, start cooling temperature, air cooling time, water cooling time are selected as the input values. The hyperbolic tangent, sigmoid and linear functions are applied for the activation functions. The weights training was conducted 100,000 times, the weights were trained to satisfy the standard deviation of finish cooling temperature within 10.56 K. It was found that the accuracy from the ANN analysis was improved 2.74 times than the heat transfer model with least square method. It was concluded that the ANN with multilayer type could train the weights by the effect of the nonlinear trend of specific heat according to temperature. It is recommended that the heat transfer model should be replaced by the neural networks method of 3 layers (one input-layer, one hidden-layer, one output-layer) with the trained weights for the precise control cooling.

AB - Artificial Neuron Networks (ANN) is considered one of the most practical technologies in the fields of intelligent manufacturing. In this study, the conventional heat transfer model and multilayer ANN analysis are compared to analyze the accelerated control cooling process, and the accuracy improvement of finish cooling temperature prediction by the ANN is evaluated. The temperature prediction error from the heat transfer model tends to increase with increasing the start cooling temperature in Curie temperature. It is found that the specific heat for low carbon steel shows a nonlinear tendency in Curie temperature. The ANN of backpropagation is applied to solve the nonlinear tendency of the specific heat. In the ANN analysis, the key parameters such as dimensions of plate, chemistry, start cooling temperature, air cooling time, water cooling time are selected as the input values. The hyperbolic tangent, sigmoid and linear functions are applied for the activation functions. The weights training was conducted 100,000 times, the weights were trained to satisfy the standard deviation of finish cooling temperature within 10.56 K. It was found that the accuracy from the ANN analysis was improved 2.74 times than the heat transfer model with least square method. It was concluded that the ANN with multilayer type could train the weights by the effect of the nonlinear trend of specific heat according to temperature. It is recommended that the heat transfer model should be replaced by the neural networks method of 3 layers (one input-layer, one hidden-layer, one output-layer) with the trained weights for the precise control cooling.

KW - Accelerated control cooling

KW - Artificial neural networks

KW - Finish cooling temperature

KW - Heat transfer model

KW - Temperature prediction accuracy

UR - http://www.scopus.com/inward/record.url?scp=85048571362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048571362&partnerID=8YFLogxK

U2 - 10.1016/j.ijheatmasstransfer.2018.06.022

DO - 10.1016/j.ijheatmasstransfer.2018.06.022

M3 - Article

AN - SCOPUS:85048571362

VL - 126

SP - 579

EP - 588

JO - International Journal of Heat and Mass Transfer

JF - International Journal of Heat and Mass Transfer

SN - 0017-9310

ER -