Simulation and experimental study of inverse heat conduction problem

L. Chen, S. Askarian, M. Mohammadzaheri, F. Samadi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper, a neural network method is proposed to solve a one dimensional inverse heat conduction problem (IHCP). The method relies on input/output data of an unknown system to create an intelligent neural network model. Multi layer perceptrons with recurrent properties are utilised in the model. Prepared input/output data are used to train the neural network. Reliable checking processes are also offered to justify the robustness of the method. A numerical sequential function specification (SFS) method is used as another technique to solve the IHCP. The numerical result is compared with that of the proposed method and good agreement is shown between the two methods. However, the numerical method can be only used to solve the IHCP off-line due to the high computation requirement. The proposed neural network method can be used in real-time situations as shown in the experimental tests.

Original languageEnglish
Title of host publicationFundamental of Chemical Engineering
Pages2820-2823
Number of pages4
Volume233-235
DOIs
Publication statusPublished - 2011
Event2011 International Conference on Chemical Engineering and Advanced Materials, CEAM 2011 - Changsha, China
Duration: May 28 2011May 30 2011

Publication series

NameAdvanced Materials Research
Volume233-235
ISSN (Print)1022-6680

Other

Other2011 International Conference on Chemical Engineering and Advanced Materials, CEAM 2011
CountryChina
CityChangsha
Period5/28/115/30/11

Fingerprint

Heat conduction
Neural networks
Multilayer neural networks
Numerical methods
Specifications

Keywords

  • ANSYS parametric design language
  • Artificial neural network
  • Inverse heat conduction problem
  • Sequential function specification

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Chen, L., Askarian, S., Mohammadzaheri, M., & Samadi, F. (2011). Simulation and experimental study of inverse heat conduction problem. In Fundamental of Chemical Engineering (Vol. 233-235, pp. 2820-2823). (Advanced Materials Research; Vol. 233-235). https://doi.org/10.4028/www.scientific.net/AMR.233-235.2820

Simulation and experimental study of inverse heat conduction problem. / Chen, L.; Askarian, S.; Mohammadzaheri, M.; Samadi, F.

Fundamental of Chemical Engineering. Vol. 233-235 2011. p. 2820-2823 (Advanced Materials Research; Vol. 233-235).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, L, Askarian, S, Mohammadzaheri, M & Samadi, F 2011, Simulation and experimental study of inverse heat conduction problem. in Fundamental of Chemical Engineering. vol. 233-235, Advanced Materials Research, vol. 233-235, pp. 2820-2823, 2011 International Conference on Chemical Engineering and Advanced Materials, CEAM 2011, Changsha, China, 5/28/11. https://doi.org/10.4028/www.scientific.net/AMR.233-235.2820
Chen L, Askarian S, Mohammadzaheri M, Samadi F. Simulation and experimental study of inverse heat conduction problem. In Fundamental of Chemical Engineering. Vol. 233-235. 2011. p. 2820-2823. (Advanced Materials Research). https://doi.org/10.4028/www.scientific.net/AMR.233-235.2820
Chen, L. ; Askarian, S. ; Mohammadzaheri, M. ; Samadi, F. / Simulation and experimental study of inverse heat conduction problem. Fundamental of Chemical Engineering. Vol. 233-235 2011. pp. 2820-2823 (Advanced Materials Research).
@inproceedings{e95cc883ec9c4e259fe5e1c1d9af193c,
title = "Simulation and experimental study of inverse heat conduction problem",
abstract = "In this paper, a neural network method is proposed to solve a one dimensional inverse heat conduction problem (IHCP). The method relies on input/output data of an unknown system to create an intelligent neural network model. Multi layer perceptrons with recurrent properties are utilised in the model. Prepared input/output data are used to train the neural network. Reliable checking processes are also offered to justify the robustness of the method. A numerical sequential function specification (SFS) method is used as another technique to solve the IHCP. The numerical result is compared with that of the proposed method and good agreement is shown between the two methods. However, the numerical method can be only used to solve the IHCP off-line due to the high computation requirement. The proposed neural network method can be used in real-time situations as shown in the experimental tests.",
keywords = "ANSYS parametric design language, Artificial neural network, Inverse heat conduction problem, Sequential function specification",
author = "L. Chen and S. Askarian and M. Mohammadzaheri and F. Samadi",
year = "2011",
doi = "10.4028/www.scientific.net/AMR.233-235.2820",
language = "English",
isbn = "9783037851197",
volume = "233-235",
series = "Advanced Materials Research",
pages = "2820--2823",
booktitle = "Fundamental of Chemical Engineering",

}

TY - GEN

T1 - Simulation and experimental study of inverse heat conduction problem

AU - Chen, L.

AU - Askarian, S.

AU - Mohammadzaheri, M.

AU - Samadi, F.

PY - 2011

Y1 - 2011

N2 - In this paper, a neural network method is proposed to solve a one dimensional inverse heat conduction problem (IHCP). The method relies on input/output data of an unknown system to create an intelligent neural network model. Multi layer perceptrons with recurrent properties are utilised in the model. Prepared input/output data are used to train the neural network. Reliable checking processes are also offered to justify the robustness of the method. A numerical sequential function specification (SFS) method is used as another technique to solve the IHCP. The numerical result is compared with that of the proposed method and good agreement is shown between the two methods. However, the numerical method can be only used to solve the IHCP off-line due to the high computation requirement. The proposed neural network method can be used in real-time situations as shown in the experimental tests.

AB - In this paper, a neural network method is proposed to solve a one dimensional inverse heat conduction problem (IHCP). The method relies on input/output data of an unknown system to create an intelligent neural network model. Multi layer perceptrons with recurrent properties are utilised in the model. Prepared input/output data are used to train the neural network. Reliable checking processes are also offered to justify the robustness of the method. A numerical sequential function specification (SFS) method is used as another technique to solve the IHCP. The numerical result is compared with that of the proposed method and good agreement is shown between the two methods. However, the numerical method can be only used to solve the IHCP off-line due to the high computation requirement. The proposed neural network method can be used in real-time situations as shown in the experimental tests.

KW - ANSYS parametric design language

KW - Artificial neural network

KW - Inverse heat conduction problem

KW - Sequential function specification

UR - http://www.scopus.com/inward/record.url?scp=79958263174&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958263174&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMR.233-235.2820

DO - 10.4028/www.scientific.net/AMR.233-235.2820

M3 - Conference contribution

AN - SCOPUS:79958263174

SN - 9783037851197

VL - 233-235

T3 - Advanced Materials Research

SP - 2820

EP - 2823

BT - Fundamental of Chemical Engineering

ER -