Soft-Sensing in Batch Annealing Based on Finite Differential Method and Support Vector Regression

Kačur, Ján; Durdán, Milan; Laciak, Marek; Flegner, Patrik

doi:10.12913/22998624/112542

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!
Sesja wygasła!
Sesja wygasła!

Artykuł - szczegóły

Tytuł artykułu

Soft-Sensing in Batch Annealing Based on Finite Differential Method and Support Vector Regression

Autorzy

Kačur Ján , Durdán Milan , Laciak Marek , Flegner Patrik

Treść / Zawartość

Pełne teksty:

Pobierz

Identyfikatory

DOI

10.12913/22998624/112542

Warianty tytułu

Języki publikacji

Abstrakty

The temperature of annealed steel coils is a determining variable of the future steel sheets quality. This variable also determines the energy consumption in operation. Unfortunately, the monitoring of coil inner temperature is problematic due to the furnace environment with high temperature, coil structure, and annealing principle. Currently, there are no measuring principles that can measure the temperature inside the heat-treated product in a non-destructive manner. In this paper, the soft sensing of inner temperature based on the theory of non-stationary heat conduction and approach based on Support Vector Regression (SVR) was presented. The results showed that a black-box approach based on the SVR could replace an analytic approach, though with lesser performance. Several annealing experiments were performed to create a training data set and model performance improvement in the estimation of inner coil temperatures. The proposed software based on non-stationary heat conduction can calculate the behavior of inner coil temperature from the measured boundary temperatures that are measured by thermocouples. The soft-sensing principles presented in this paper were verified under laboratory conditions and on the data obtained from a real annealing plant.

Słowa kluczowe

annealing steel coil temperature measurement soft-sensing finite differences method support vector regression

wyżarzanie cewka stalowa pomiar temperatury wyczuwanie metoda różnic skończonych regresja wektora nośnego

Wydawca

Lublin University of Technology
Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin

Czasopismo

Advances in Science and Technology. Research Journal

Rocznik

2019

Tom

Vol. 13, no 4

Strony

70--86

Opis fizyczny

Bibliogr. 34 poz., fig., tab.

Twórcy

autor

Kačur Ján

jan.kacur@tuke.sk

Technical University of Košice, Faculty BERG, Institute of Control and Informatization of Production Processes, Němcovej 3, 042 00 Košice, Slovak Republic

autor

Durdán Milan

Technical University of Košice, Faculty BERG, Institute of Control and Informatization of Production Processes, Němcovej 3, 042 00 Košice, Slovak Republic

autor

Laciak Marek

Technical University of Košice, Faculty BERG, Institute of Control and Informatization of Production Processes, Němcovej 3, 042 00 Košice, Slovak Republic

autor

Flegner Patrik

Technical University of Košice, Faculty BERG, Institute of Control and Informatization of Production Processes, Němcovej 3, 042 00 Košice, Slovak Republic

Bibliografia

1. Bell Furnance Patents, RussianPatents.com. 2019. https://russianpatents.com/patent/217/ 2173718.html.
2. Bhadeshia, H. K. D. H. Neural networks in materials science. ISIJ International, 39(10), 1999, 966–979.
3. Boser, B. E., Guyon, I. M., Vapnik, V. N. A training algorithm for optimal margin classifiers. Proc. of the 5th Annual ACM Workshop on Computational Learning Theory - COLT’92 (Pittsburgh, PA, ACM Press), 1992, 144–152.
4. Col, M., Ertunc, H. M., Yılmaz, M. An artificial neural network model for toughness properties in microalloyed steel in consideration of Industrial production conditions. Materials and Design, 28(2), 2007, 488–495.
5. Corus. Corus Strip Products UK Finance Document Library. Cours Strip Products, UK, 2008.
6. Das, S., Singh, S. B., Mohanty, O. N., Bhadeshia, H. K. D. K. Understanding the complexities of bake hardening. Materials Science and Technology, 24(1), 2004, 107–111. https://doi. org/10.1179/174367507X247511.
7. Dehghani, K., Shafiei A. Predicting the bake hardenability of steels using neural network modeling. Materials Letters, 62(2), 2008, 173–178.
8. Durdán, M., Kačur, J. System for indirect measurement of the heat flows at annealing of the steel coils. Acta Metallurgica Slovaca 19(2), 2013, 112–121.
9. Durdán, M., Kačur, J., Laciak, M., and Flegner, P. Thermophysical Properties Estimation in Annealing Process Using the Iterative Dynamic Programming Method and Gradient Method, Energies, 12(3267), MDPI, 2019, 1–24. http://dx.doi. org/10.3390/en12173267.
10. Durdán, M., Mojžišová, A., Laciak, M., Kačur, J. System for indirect temperature measurement in annealing process. Measurement, 47(1), Elsevier, 2014, 911–918. http://dx.doi.org/10.1016/j.measurement.2013.10.013.
11. Durdán M, Stehlíková, B., Pástor, M., Kačur, J., Laciak, M., Flegner, P. Research of annealing process in laboratory conditions. Measurement. 73(1), Elsevier, 2015, 607–618. http://dx.doi.org/10.1016/j. measurement.2015.06.008.
12. Evans, P. J., Gutieerez, I, Petite, M. M., Larburu, J. I., Zaitegui, J., Hutchinson, W. B., Artymowicz, D., Spurr, G., Bhadeshia, H. K. D. H., Cheste, N. Modeling of Microstructural Development During Continuous Annealing Process. EU Report, ECSC 7210-EU/808, 1998.
13. Garrert, P. H. Neural network directed steel annealing, High Performance Instrumentation and Automation, CRC Press, 2005, 209–216. http://dx.doi. org/10.1201/ 9781420037357.ch12.
14. Haouam, A., Bigerelle, M., Merzoug, B. Simplex Enhanced Numerical Modeling of the Temperature Dis-tribution in a Hydrogen Cooled Steel Coil Annealing Process. IX International Conference on Computational Heat and Mass Transfer, ICCHMT2016, Procedia Engineering, 157(1), Elsevier, 2016. 50–57. http://dx.doi.org/10.1016/j.proeng.2016.08.337.
15. Chen, M. Y., Linkens, D. A., A systematic neuro-fuzzy modeling framework with application to material property prediction. IEEE Transactions on Systems Man Cybernetics Part B-Cybernetics, 31(5), 781–790.
16. Chen, M. Y., Linkens, D. A., Bannister, A. Numerical analysis of factors influencing Charpy impact properties of TMCR structural steels using fuzzy modelling. Materials Science and Technology, 20(5), 2004, 627–633.
17. Jones, D. M. The Modelling of Mechanical Properties of Steel from Processing Parameters at the Port Talbot Hot Strip Mill. Thesis submitted to Cardiff University for the degree of EngD, Cardiff University, Engineering Department. 2006.
18. Kačur, J., Durdán, M., Flegner, P., Laciak, M., Bogdanovská, G. Pulse-width modulation control of experimental bell furnace. International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM 2018, Section Informatics, 649–656.
19. Kačur, J., Laciak, M., Durdán, M., Flegner, P. Utilization of Machine Learning Method in Prediction of UCG Data. In: 18th International Carpathian Control Conference (ICCC 2017), Sinaia, IEEE 2017, 278–283. http://dx.doi.org/ 10.1109/CarpathianCC.2017.7970411.
20. Kačur, J., Laciak, M., Flegner, P., Terpák, J., Durdán, M., Tréfa, G. Application of Support Vector Regression for Data-Driven Modeling of Melt Temperature and Carbon Content in LD Converter. 20th International Carpathian Control Conference (ICCC 2019), Krakow-Wieliczka, Poland, IEEE, 2019, 1–6. http://dx.doi.org/10.1109/CarpathianCC.2019.8765956.
21. Kostúr K., Process check of annealing process of coiled sheets by indirect measurement. Metalurgija, 56(1–2), 2017, 229–232.
22. Kostúr, K. Simulačné modely tepelných agregátov, Štroffek, Košice, 1997.
23. Kostúr, K., Laciak, M., Truchlý, M. Systémy nepriameho merania, Košice, TU Košice, 2005.
24. Llewellyn, D. T. Steels Metallurgy & Applications. Butterworth-Heinemann Ltd., 1992.
25. MathWorks, Statistics and Machine Learning Toolbox (R2018b), The MathWorks Inc., 2018.
26. MathWorks, Understanding Support Vector Machine Regression, Statistics and Machine Learning Toolbox User’s Guide (R2018b)., The Mathworks Inc., 2018.
27. Müller, K. R, Smola, A. J., Rätsch, G., et al. Predicting time series with support vector machines. In Lecture Notes in Computer Science (Springer Berlin Heidelberg), 1997, 999–1004.
28. Mojžišová, A., Kostúr, K. Model of indirect temperature measurement by neural network. Acta Montanistica Slovaca 13(1), 2008, 105–110.
29. Saraee, M. H., Moghimi, M., Bagheri, A. Modeling batch annealing process using data mining techniques for cold rolled steel sheets. University of Salford Manchester, UK, 2011, 18–22. http:// dx.doi.org/10.1145/ 2018673.2018677.
30. Takahashi, M., Okamoto, A. Effect of Nitrogen on Recrystallization Textures of Extra Low-Carbon Steel Sheet. Transactions of the Iron and Steel Institute of Japan, 19(7), 1979, 391–400.
31. Terpák, J., Dorčák, Ľ. Procesy Prenosu. TU Košice, Faculty BERG, 2001.
32. Vapnik, V. N. Constructing learning algorithms. The Nature of Statistical Learning Theory (Springer Verlag, New York), 1995, 119–166.
33. Vlack Van L. H., Elements of Materials Science and Engineering (6th Edition). Pearson, 1989.
34. Wigley, N. R. Property Prediction of Continuous Annealed Steels. Thesis, Cardiff University, 2012.

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-8d26d95c-dba8-4dc2-8d06-73c7bfbf5594