Cargando…

Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function

With the improvement of industrial requirements for the quality of cold rolled strips, flatness has become one of the most important indicators for measuring the quality of cold rolled strips. In this paper, the strip production data of a 1250 mm tandem cold mill in a steel plant is modeled by an im...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Jingyi, Song, Shuni, Wang, Jiayi, Balaiti, Maimutimin, Song, Nina, Li, Sen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8780483/
https://www.ncbi.nlm.nih.gov/pubmed/35062616
http://dx.doi.org/10.3390/s22020656
_version_ 1784637849816006656
author Liu, Jingyi
Song, Shuni
Wang, Jiayi
Balaiti, Maimutimin
Song, Nina
Li, Sen
author_facet Liu, Jingyi
Song, Shuni
Wang, Jiayi
Balaiti, Maimutimin
Song, Nina
Li, Sen
author_sort Liu, Jingyi
collection PubMed
description With the improvement of industrial requirements for the quality of cold rolled strips, flatness has become one of the most important indicators for measuring the quality of cold rolled strips. In this paper, the strip production data of a 1250 mm tandem cold mill in a steel plant is modeled by an improved deep neural network (the improved DNN) to improve the accuracy of strip shape prediction. Firstly, the type of activation function is analyzed, and the monotonicity of the activation function is deemed independent of the convexity of the loss function in the deep network. Regardless of whether the activation function is monotonic, the loss function is not strictly convex. Secondly, the non-convex optimization of the loss functionextended from the deep linear network to the deep nonlinear network, is discussed, and the critical point of the deep nonlinear network is identified as the global minimum point. Finally, an improved Swish activation function based on batch normalization is proposed, and its performance is evaluated on the MNIST dataset. The experimental results show that the loss of an improved Swish function is lower than that of other activation functions. The prediction accuracy of a deep neural network (DNN) with an improved Swish function is 0.38% more than that of a deep neural network (DNN) with a regular Swish function. For the DNN with the improved Swish function, the mean square error of the prediction for the flatness of cold rolled strip is reduced to 65% of the regular DNN. The accuracy of the improved DNN is up to and higher than the industrial requirements. The shape prediction of the improved DNN will assist and guide the industrial production process, reducing the scrap yield and industrial cost.
format Online
Article
Text
id pubmed-8780483
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87804832022-01-22 Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function Liu, Jingyi Song, Shuni Wang, Jiayi Balaiti, Maimutimin Song, Nina Li, Sen Sensors (Basel) Article With the improvement of industrial requirements for the quality of cold rolled strips, flatness has become one of the most important indicators for measuring the quality of cold rolled strips. In this paper, the strip production data of a 1250 mm tandem cold mill in a steel plant is modeled by an improved deep neural network (the improved DNN) to improve the accuracy of strip shape prediction. Firstly, the type of activation function is analyzed, and the monotonicity of the activation function is deemed independent of the convexity of the loss function in the deep network. Regardless of whether the activation function is monotonic, the loss function is not strictly convex. Secondly, the non-convex optimization of the loss functionextended from the deep linear network to the deep nonlinear network, is discussed, and the critical point of the deep nonlinear network is identified as the global minimum point. Finally, an improved Swish activation function based on batch normalization is proposed, and its performance is evaluated on the MNIST dataset. The experimental results show that the loss of an improved Swish function is lower than that of other activation functions. The prediction accuracy of a deep neural network (DNN) with an improved Swish function is 0.38% more than that of a deep neural network (DNN) with a regular Swish function. For the DNN with the improved Swish function, the mean square error of the prediction for the flatness of cold rolled strip is reduced to 65% of the regular DNN. The accuracy of the improved DNN is up to and higher than the industrial requirements. The shape prediction of the improved DNN will assist and guide the industrial production process, reducing the scrap yield and industrial cost. MDPI 2022-01-15 /pmc/articles/PMC8780483/ /pubmed/35062616 http://dx.doi.org/10.3390/s22020656 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Liu, Jingyi
Song, Shuni
Wang, Jiayi
Balaiti, Maimutimin
Song, Nina
Li, Sen
Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function
title Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function
title_full Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function
title_fullStr Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function
title_full_unstemmed Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function
title_short Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function
title_sort flatness prediction of cold rolled strip based on deep neural network with improved activation function
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8780483/
https://www.ncbi.nlm.nih.gov/pubmed/35062616
http://dx.doi.org/10.3390/s22020656
work_keys_str_mv AT liujingyi flatnesspredictionofcoldrolledstripbasedondeepneuralnetworkwithimprovedactivationfunction
AT songshuni flatnesspredictionofcoldrolledstripbasedondeepneuralnetworkwithimprovedactivationfunction
AT wangjiayi flatnesspredictionofcoldrolledstripbasedondeepneuralnetworkwithimprovedactivationfunction
AT balaitimaimutimin flatnesspredictionofcoldrolledstripbasedondeepneuralnetworkwithimprovedactivationfunction
AT songnina flatnesspredictionofcoldrolledstripbasedondeepneuralnetworkwithimprovedactivationfunction
AT lisen flatnesspredictionofcoldrolledstripbasedondeepneuralnetworkwithimprovedactivationfunction