MARINKOVIĆ, Velibor . Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies. Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 55, n.1, p. 64-75, august 2017. ISSN 0039-2480. Available at: <https://www.sv-jme.eu/article/application-of-artificial-neural-network-for-modeling-the-flash-land-dimensions-in-the-forging-dies/>. Date accessed: 22 dec. 2024. doi:http://dx.doi.org/.
Marinković, V. (2009). Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies. Strojniški vestnik - Journal of Mechanical Engineering, 55(1), 64-75. doi:http://dx.doi.org/
@article{.,
author = {Velibor Marinković},
title = {Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {55},
number = {1},
year = {2009},
keywords = {forging; forging dies; modeling; neural networks; },
abstract = {In designing technological process and forging dies, the determination of the flash land dimensions represents one of the most important and most complex problems. Namely, it is on the flash land dimensions that the appropriate (''laminar'') flow of metal and the complete filling of the die cavity largely depend on. The literature abounds with purely theoretical or semi-empirical formulae for calculating the flash land dimensions which are either too complex to be applied in engineering practice or insufficiently accurate. On the other hand, an important quantity of data as well as recommendations for selecting the flash land dimensions are available in the handbooks of metal forming, which do not take into consideration all the conditions and complexity of the forging process. This paper proposes an approach to modeling the flash land by applying artificial neural network (ANN). A three-layer feed-forward ANN, with backpropagation algorithm for supervised learning is created. A sigmoid type of non-linearity is applied to neurons. In the reference literature there are many examples showing that the prediction model developed by means of ANN is more accurate than the one developed by the regression analysis. The trained ANN has shown a high level of prediction so that it can be used for designing and optimizing the conventional forging process.},
issn = {0039-2480}, pages = {64-75}, doi = {},
url = {https://www.sv-jme.eu/article/application-of-artificial-neural-network-for-modeling-the-flash-land-dimensions-in-the-forging-dies/}
}
Marinković, V. 2009 August 55. Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 55:1
%A Marinković, Velibor
%D 2009
%T Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies
%B 2009
%9 forging; forging dies; modeling; neural networks;
%! Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies
%K forging; forging dies; modeling; neural networks;
%X In designing technological process and forging dies, the determination of the flash land dimensions represents one of the most important and most complex problems. Namely, it is on the flash land dimensions that the appropriate (''laminar'') flow of metal and the complete filling of the die cavity largely depend on. The literature abounds with purely theoretical or semi-empirical formulae for calculating the flash land dimensions which are either too complex to be applied in engineering practice or insufficiently accurate. On the other hand, an important quantity of data as well as recommendations for selecting the flash land dimensions are available in the handbooks of metal forming, which do not take into consideration all the conditions and complexity of the forging process. This paper proposes an approach to modeling the flash land by applying artificial neural network (ANN). A three-layer feed-forward ANN, with backpropagation algorithm for supervised learning is created. A sigmoid type of non-linearity is applied to neurons. In the reference literature there are many examples showing that the prediction model developed by means of ANN is more accurate than the one developed by the regression analysis. The trained ANN has shown a high level of prediction so that it can be used for designing and optimizing the conventional forging process.
%U https://www.sv-jme.eu/article/application-of-artificial-neural-network-for-modeling-the-flash-land-dimensions-in-the-forging-dies/
%0 Journal Article
%R
%& 64
%P 12
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 55
%N 1
%@ 0039-2480
%8 2017-08-21
%7 2017-08-21
Marinković, Velibor. "Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies." Strojniški vestnik - Journal of Mechanical Engineering [Online], 55.1 (2009): 64-75. Web. 22 Dec. 2024
TY - JOUR
AU - Marinković, Velibor
PY - 2009
TI - Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies
JF - Strojniški vestnik - Journal of Mechanical Engineering
DO -
KW - forging; forging dies; modeling; neural networks;
N2 - In designing technological process and forging dies, the determination of the flash land dimensions represents one of the most important and most complex problems. Namely, it is on the flash land dimensions that the appropriate (''laminar'') flow of metal and the complete filling of the die cavity largely depend on. The literature abounds with purely theoretical or semi-empirical formulae for calculating the flash land dimensions which are either too complex to be applied in engineering practice or insufficiently accurate. On the other hand, an important quantity of data as well as recommendations for selecting the flash land dimensions are available in the handbooks of metal forming, which do not take into consideration all the conditions and complexity of the forging process. This paper proposes an approach to modeling the flash land by applying artificial neural network (ANN). A three-layer feed-forward ANN, with backpropagation algorithm for supervised learning is created. A sigmoid type of non-linearity is applied to neurons. In the reference literature there are many examples showing that the prediction model developed by means of ANN is more accurate than the one developed by the regression analysis. The trained ANN has shown a high level of prediction so that it can be used for designing and optimizing the conventional forging process.
UR - https://www.sv-jme.eu/article/application-of-artificial-neural-network-for-modeling-the-flash-land-dimensions-in-the-forging-dies/
@article{{}{.},
author = {Marinković, V.},
title = {Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {55},
number = {1},
year = {2009},
doi = {},
url = {https://www.sv-jme.eu/article/application-of-artificial-neural-network-for-modeling-the-flash-land-dimensions-in-the-forging-dies/}
}
TY - JOUR
AU - Marinković, Velibor
PY - 2017/08/21
TI - Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies
JF - Strojniški vestnik - Journal of Mechanical Engineering; Vol 55, No 1 (2009): Strojniški vestnik - Journal of Mechanical Engineering
DO -
KW - forging, forging dies, modeling, neural networks,
N2 - In designing technological process and forging dies, the determination of the flash land dimensions represents one of the most important and most complex problems. Namely, it is on the flash land dimensions that the appropriate (''laminar'') flow of metal and the complete filling of the die cavity largely depend on. The literature abounds with purely theoretical or semi-empirical formulae for calculating the flash land dimensions which are either too complex to be applied in engineering practice or insufficiently accurate. On the other hand, an important quantity of data as well as recommendations for selecting the flash land dimensions are available in the handbooks of metal forming, which do not take into consideration all the conditions and complexity of the forging process. This paper proposes an approach to modeling the flash land by applying artificial neural network (ANN). A three-layer feed-forward ANN, with backpropagation algorithm for supervised learning is created. A sigmoid type of non-linearity is applied to neurons. In the reference literature there are many examples showing that the prediction model developed by means of ANN is more accurate than the one developed by the regression analysis. The trained ANN has shown a high level of prediction so that it can be used for designing and optimizing the conventional forging process.
UR - https://www.sv-jme.eu/article/application-of-artificial-neural-network-for-modeling-the-flash-land-dimensions-in-the-forging-dies/
Marinković, Velibor"Application of Artificial Neural Network for Modeling the Flash Land Dimensions in the Forging Dies" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 55 Number 1 (21 August 2017)
Strojniški vestnik - Journal of Mechanical Engineering 55(2009)1, 64-75
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.
In designing technological process and forging dies, the determination of the flash land dimensions represents one of the most important and most complex problems. Namely, it is on the flash land dimensions that the appropriate (''laminar'') flow of metal and the complete filling of the die cavity largely depend on. The literature abounds with purely theoretical or semi-empirical formulae for calculating the flash land dimensions which are either too complex to be applied in engineering practice or insufficiently accurate. On the other hand, an important quantity of data as well as recommendations for selecting the flash land dimensions are available in the handbooks of metal forming, which do not take into consideration all the conditions and complexity of the forging process. This paper proposes an approach to modeling the flash land by applying artificial neural network (ANN). A three-layer feed-forward ANN, with backpropagation algorithm for supervised learning is created. A sigmoid type of non-linearity is applied to neurons. In the reference literature there are many examples showing that the prediction model developed by means of ANN is more accurate than the one developed by the regression analysis. The trained ANN has shown a high level of prediction so that it can be used for designing and optimizing the conventional forging process.