Online identification of heat dissipaters using artificial neural networks

1889 Views
1205 Downloads
Export citation: ABNT
LALOT, Sylvain ;LECOEUCHE, Stéphane .
Online identification of heat dissipaters using artificial neural networks. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 47, n.8, p. 411-416, july 2017. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/online-identification-of-heat-dissipaters-using-artificial-neural-networks/>. Date accessed: 10 dec. 2024. 
doi:http://dx.doi.org/.
Lalot, S., & Lecoeuche, S.
(2001).
Online identification of heat dissipaters using artificial neural networks.
Strojniški vestnik - Journal of Mechanical Engineering, 47(8), 411-416.
doi:http://dx.doi.org/
@article{.,
	author = {Sylvain  Lalot and Stéphane  Lecoeuche},
	title = {Online identification of heat dissipaters using artificial neural networks},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {47},
	number = {8},
	year = {2001},
	keywords = {heat dissipaters; artificial neural networks; },
	abstract = {This paper focuses on the feasibility of online identification of thermal systems. The transfer function is not looked for, but a black box model is obtained. In the first part, the principles of online identification are reminded. This leads to the definition of the regression vector and of the regressors. Then these principles are applied to neural based techniques which are adapted from standard ARX (AutoRegressive structure with eXtra inputs) and OE (Output-Error) models. For the Neural Network ARX (NNARX) model, only one example is given, which leads to a not fully satisfactory identification. This identification is based on the response of the system to random heat rates during random times. The validation is based on the response to another set of random heat rates and on the response of the system to a step function. For Neural Network OE (NNOE) model, the influence of the number of regressors is presented along with the influence of the number of neurons on the hidden layer. It is shown that many architectures lead to a good identification, but that some particular models may lead to a very poor result. To make the comparison possible between the proposed models, a distance criterion is computed. This leads to the choice of the best adapted architecture.},
	issn = {0039-2480},	pages = {411-416},	doi = {},
	url = {https://www.sv-jme.eu/article/online-identification-of-heat-dissipaters-using-artificial-neural-networks/}
}
Lalot, S.,Lecoeuche, S.
2001 July 47. Online identification of heat dissipaters using artificial neural networks. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 47:8
%A Lalot, Sylvain 
%A Lecoeuche, Stéphane 
%D 2001
%T Online identification of heat dissipaters using artificial neural networks
%B 2001
%9 heat dissipaters; artificial neural networks; 
%! Online identification of heat dissipaters using artificial neural networks
%K heat dissipaters; artificial neural networks; 
%X This paper focuses on the feasibility of online identification of thermal systems. The transfer function is not looked for, but a black box model is obtained. In the first part, the principles of online identification are reminded. This leads to the definition of the regression vector and of the regressors. Then these principles are applied to neural based techniques which are adapted from standard ARX (AutoRegressive structure with eXtra inputs) and OE (Output-Error) models. For the Neural Network ARX (NNARX) model, only one example is given, which leads to a not fully satisfactory identification. This identification is based on the response of the system to random heat rates during random times. The validation is based on the response to another set of random heat rates and on the response of the system to a step function. For Neural Network OE (NNOE) model, the influence of the number of regressors is presented along with the influence of the number of neurons on the hidden layer. It is shown that many architectures lead to a good identification, but that some particular models may lead to a very poor result. To make the comparison possible between the proposed models, a distance criterion is computed. This leads to the choice of the best adapted architecture.
%U https://www.sv-jme.eu/article/online-identification-of-heat-dissipaters-using-artificial-neural-networks/
%0 Journal Article
%R 
%& 411
%P 6
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 47
%N 8
%@ 0039-2480
%8 2017-07-07
%7 2017-07-07
Lalot, Sylvain, & Stéphane  Lecoeuche.
"Online identification of heat dissipaters using artificial neural networks." Strojniški vestnik - Journal of Mechanical Engineering [Online], 47.8 (2001): 411-416. Web.  10 Dec. 2024
TY  - JOUR
AU  - Lalot, Sylvain 
AU  - Lecoeuche, Stéphane 
PY  - 2001
TI  - Online identification of heat dissipaters using artificial neural networks
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 
KW  - heat dissipaters; artificial neural networks; 
N2  - This paper focuses on the feasibility of online identification of thermal systems. The transfer function is not looked for, but a black box model is obtained. In the first part, the principles of online identification are reminded. This leads to the definition of the regression vector and of the regressors. Then these principles are applied to neural based techniques which are adapted from standard ARX (AutoRegressive structure with eXtra inputs) and OE (Output-Error) models. For the Neural Network ARX (NNARX) model, only one example is given, which leads to a not fully satisfactory identification. This identification is based on the response of the system to random heat rates during random times. The validation is based on the response to another set of random heat rates and on the response of the system to a step function. For Neural Network OE (NNOE) model, the influence of the number of regressors is presented along with the influence of the number of neurons on the hidden layer. It is shown that many architectures lead to a good identification, but that some particular models may lead to a very poor result. To make the comparison possible between the proposed models, a distance criterion is computed. This leads to the choice of the best adapted architecture.
UR  - https://www.sv-jme.eu/article/online-identification-of-heat-dissipaters-using-artificial-neural-networks/
@article{{}{.},
	author = {Lalot, S., Lecoeuche, S.},
	title = {Online identification of heat dissipaters using artificial neural networks},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {47},
	number = {8},
	year = {2001},
	doi = {},
	url = {https://www.sv-jme.eu/article/online-identification-of-heat-dissipaters-using-artificial-neural-networks/}
}
TY  - JOUR
AU  - Lalot, Sylvain 
AU  - Lecoeuche, Stéphane 
PY  - 2017/07/07
TI  - Online identification of heat dissipaters using artificial neural networks
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 47, No 8 (2001): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 
KW  - heat dissipaters, artificial neural networks, 
N2  - This paper focuses on the feasibility of online identification of thermal systems. The transfer function is not looked for, but a black box model is obtained. In the first part, the principles of online identification are reminded. This leads to the definition of the regression vector and of the regressors. Then these principles are applied to neural based techniques which are adapted from standard ARX (AutoRegressive structure with eXtra inputs) and OE (Output-Error) models. For the Neural Network ARX (NNARX) model, only one example is given, which leads to a not fully satisfactory identification. This identification is based on the response of the system to random heat rates during random times. The validation is based on the response to another set of random heat rates and on the response of the system to a step function. For Neural Network OE (NNOE) model, the influence of the number of regressors is presented along with the influence of the number of neurons on the hidden layer. It is shown that many architectures lead to a good identification, but that some particular models may lead to a very poor result. To make the comparison possible between the proposed models, a distance criterion is computed. This leads to the choice of the best adapted architecture.
UR  - https://www.sv-jme.eu/article/online-identification-of-heat-dissipaters-using-artificial-neural-networks/
Lalot, Sylvain, AND Lecoeuche, Stéphane.
"Online identification of heat dissipaters using artificial neural networks" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 47 Number 8 (07 July 2017)

Authors

Affiliations

  • M.E.T.I.E.R., Ecole d'Ingénieurs du Pas-de-calais, France
  • M.E.T.I.E.R., Ecole d'Ingénieurs du Pas-de-calais, France

Paper's information

Strojniški vestnik - Journal of Mechanical Engineering 47(2001)8, 411-416
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.

This paper focuses on the feasibility of online identification of thermal systems. The transfer function is not looked for, but a black box model is obtained. In the first part, the principles of online identification are reminded. This leads to the definition of the regression vector and of the regressors. Then these principles are applied to neural based techniques which are adapted from standard ARX (AutoRegressive structure with eXtra inputs) and OE (Output-Error) models. For the Neural Network ARX (NNARX) model, only one example is given, which leads to a not fully satisfactory identification. This identification is based on the response of the system to random heat rates during random times. The validation is based on the response to another set of random heat rates and on the response of the system to a step function. For Neural Network OE (NNOE) model, the influence of the number of regressors is presented along with the influence of the number of neurons on the hidden layer. It is shown that many architectures lead to a good identification, but that some particular models may lead to a very poor result. To make the comparison possible between the proposed models, a distance criterion is computed. This leads to the choice of the best adapted architecture.

heat dissipaters; artificial neural networks;