Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture
This paper presents two main novel findings. (1) The first finding is the development of an artificial neural network (ANN) model for thermal shrinkage of seamless steel pipes, which represents a new application for ANNs. Mill operators need such fast and accurate models to predict the final pipe ou...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123023001263 |
| _version_ | 1797884472359649280 |
|---|---|
| author | Raphael Langbauer Georg Nunner Thomas Zmek Jürgen Klarner René Prieler Christoph Hochenauer |
| author_facet | Raphael Langbauer Georg Nunner Thomas Zmek Jürgen Klarner René Prieler Christoph Hochenauer |
| author_sort | Raphael Langbauer |
| collection | DOAJ |
| description | This paper presents two main novel findings. (1) The first finding is the development of an artificial neural network (ANN) model for thermal shrinkage of seamless steel pipes, which represents a new application for ANNs. Mill operators need such fast and accurate models to predict the final pipe outer diameter at ambient temperature based on the hot state immediately after rolling. The goal of this work was to lower the reject rate. However, small relative changes in the diameter are currently difficult to predict by using conventional ANNs. Therefore, a more sensitive target variable and a modified ANN architecture were applied to solve this problem. Data for training and validation were obtained from measurements on a hot-rolling mill. (2) The second finding is based on an investigation performed to determine the number of hidden neurons affected the model response, considering the data used. The knowledge obtained helps to determine the most suitable number of hidden neurons and to prevent overfitting. No generally accepted solution to these problems had previously been proposed in the literature. Consequently, this paper significantly supplements current research studies that describe applications of ANNs. |
| first_indexed | 2024-04-10T04:07:11Z |
| format | Article |
| id | doaj.art-650614a98d1449e0aa074969fb8ee82d |
| institution | Directory Open Access Journal |
| issn | 2590-1230 |
| language | English |
| last_indexed | 2024-04-10T04:07:11Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj.art-650614a98d1449e0aa074969fb8ee82d2023-03-13T04:16:09ZengElsevierResults in Engineering2590-12302023-03-0117100999Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architectureRaphael Langbauer0Georg Nunner1Thomas Zmek2Jürgen Klarner3René Prieler4Christoph Hochenauer5Graz University of Technology, Institute of Thermal Engineering, Inffeldgasse 25/B, 8010, Graz, Austria; Corresponding author.voestalpine Tubulars GmbH & Co KG, Alpinestraße 17, 8652, Kindberg, Austriavoestalpine Tubulars GmbH & Co KG, Alpinestraße 17, 8652, Kindberg, Austriavoestalpine Tubulars GmbH & Co KG, Alpinestraße 17, 8652, Kindberg, AustriaGraz University of Technology, Institute of Thermal Engineering, Inffeldgasse 25/B, 8010, Graz, AustriaGraz University of Technology, Institute of Thermal Engineering, Inffeldgasse 25/B, 8010, Graz, AustriaThis paper presents two main novel findings. (1) The first finding is the development of an artificial neural network (ANN) model for thermal shrinkage of seamless steel pipes, which represents a new application for ANNs. Mill operators need such fast and accurate models to predict the final pipe outer diameter at ambient temperature based on the hot state immediately after rolling. The goal of this work was to lower the reject rate. However, small relative changes in the diameter are currently difficult to predict by using conventional ANNs. Therefore, a more sensitive target variable and a modified ANN architecture were applied to solve this problem. Data for training and validation were obtained from measurements on a hot-rolling mill. (2) The second finding is based on an investigation performed to determine the number of hidden neurons affected the model response, considering the data used. The knowledge obtained helps to determine the most suitable number of hidden neurons and to prevent overfitting. No generally accepted solution to these problems had previously been proposed in the literature. Consequently, this paper significantly supplements current research studies that describe applications of ANNs.http://www.sciencedirect.com/science/article/pii/S2590123023001263Diameter predictionArtificial neural networkModel responseSteel pipeHot rolling |
| spellingShingle | Raphael Langbauer Georg Nunner Thomas Zmek Jürgen Klarner René Prieler Christoph Hochenauer Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture Results in Engineering Diameter prediction Artificial neural network Model response Steel pipe Hot rolling |
| title | Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture |
| title_full | Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture |
| title_fullStr | Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture |
| title_full_unstemmed | Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture |
| title_short | Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture |
| title_sort | modelling of thermal shrinkage of seamless steel pipes using artificial neural networks ann focussing on the influence of the ann architecture |
| topic | Diameter prediction Artificial neural network Model response Steel pipe Hot rolling |
| url | http://www.sciencedirect.com/science/article/pii/S2590123023001263 |
| work_keys_str_mv | AT raphaellangbauer modellingofthermalshrinkageofseamlesssteelpipesusingartificialneuralnetworksannfocussingontheinfluenceoftheannarchitecture AT georgnunner modellingofthermalshrinkageofseamlesssteelpipesusingartificialneuralnetworksannfocussingontheinfluenceoftheannarchitecture AT thomaszmek modellingofthermalshrinkageofseamlesssteelpipesusingartificialneuralnetworksannfocussingontheinfluenceoftheannarchitecture AT jurgenklarner modellingofthermalshrinkageofseamlesssteelpipesusingartificialneuralnetworksannfocussingontheinfluenceoftheannarchitecture AT reneprieler modellingofthermalshrinkageofseamlesssteelpipesusingartificialneuralnetworksannfocussingontheinfluenceoftheannarchitecture AT christophhochenauer modellingofthermalshrinkageofseamlesssteelpipesusingartificialneuralnetworksannfocussingontheinfluenceoftheannarchitecture |