×

Applicability and comparison of surrogate techniques for modeling of selected heating problems. (English) Zbl 1443.74172

Summary: Possibilities of using surrogate techniques for modeling selected strongly nonlinear coupled problems of heating are evaluated. The main purpose is to significantly reduce the computing time in the case of computations of many variants of a given task by the finite element method on the condition of obtaining results of a still acceptable accuracy. Frequently used surrogate techniques (based on Kriging, neural network etc.) are tested on a particular problem of induction-assisted laser welding that represents a very complicated 3D problem. Here, the most important output quantities are the internal structure of weld (decisive for its mechanical parameters) and its depth that depend on a number of input parameters (power of laser beam, velocity of shift of the welded parts, overall geometry and material properties etc.) and must be known before the process of welding itself. The paper presents both full model of this process and considered surrogate algorithms, and compares the results obtained. It is shown that a careful selection of the surrogate technique together with suitable choice of its input data is very beneficial and may result in high savings in design of the process. Implementation performance and suitability of particular techniques of this kind are also evaluated.

MSC:

74F05 Thermal effects in solid mechanics
62G08 Nonparametric regression and quantile regression
82D40 Statistical mechanics of magnetic materials

Software:

ISLR; PRMLT; Scikit
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Mackwood, A. P.; Crafer, R. C., Thermal modelling of laser welding and related processes: a literature review, Opt. Laser Technol., 37, 99-115 (2005)
[2] Garg, S.; Banwait, S. S.; Kumar, R., Optimization of high frequency seam welding parameters by taguchi method, Asian J. Eng. Appl. Technol., 2, 78-83 (2013)
[3] Jahn, A.; Krätzsch, M.; Brenner, B., Induction assisted laser beam welding of hsla steel sheets, Modelling for Electromagnetic Processing, 195-200 (2008)
[4] Mahrle, A., Hybrid laser beam welding - classification, characteristics, and applications, J. Laser Appl., 18 (2006)
[5] Mach, M.; Schülbe, H.; Nacke, B., Investigation and design of induction assisted welding processes, Electr. Rev., 84, 228-231 (2008)
[6] Li, X.; Wang, L.; Yang, L.; Wang, J.; Li, K., Modeling of temperature field and pool formation during linear laser welding of dp1000 steel, J. Mater Process. Technol., 214, 1844-1851 (2014)
[7] Kuczmann, M.; Iványi, A., The Finite Element Method in Magnetics (2008), Académiai Kiadó: Académiai Kiadó Budapest
[8] Stratton, A., Electromagnetic Theory (2008), Adams Press: Adams Press New York · JFM 67.1119.01
[9] Holman, P., Heat Transfer (2002), McGraw-Hill: McGraw-Hill New York
[10] Pánek, D.; Kotlan, V.; Hamar, R.; Doležel, I., Novel algorithm for modeling combined laser and induction welding respecting keyhole effect, Appl. Math. Comput., 319, 254-263 (2018) · Zbl 1426.80012
[11] Kleijnen, J. P.; Sargent, R. G., A methodology for fitting and validating metamodels in simulation, European J. Oper. Res., 120, 1, 14-29 (2000) · Zbl 0985.65007
[12] S. W Doebling, F. Hemez, J. Schultze, A. L Cundy, A metamodel-based approach to model validation for nonlinear finite element simulations, 2001.; S. W Doebling, F. Hemez, J. Schultze, A. L Cundy, A metamodel-based approach to model validation for nonlinear finite element simulations, 2001.
[13] Forrester, A.; Keane, A., Engineering Design via Surrogate Modelling: A Practical Guide (2008), John Wiley & Sons
[14] Gong, J.; Berbecea, A. C.; Gillon, F.; Brochet, P., Multiobjective optimization of a linear induction motor using 3d fem, COMPEL, 31, 3, 958-971 (2012) · Zbl 1358.78054
[15] Koziel, S.; Bekasiewicz, A., Strategies for computationally feasible multi-objective simulation-driven design of compact RF/microwave components, Eng. Comput., 33, 1, 184-201 (2016)
[16] Hawe, G.; Sykulski, J., Considerations of accuracy and uncertainty with kriging surrogate models in single-objective electromagnetic design optimisation, IET Sci. Measur. Technol., 1, 1, 37-47 (2007)
[17] Queipo, N. V.; Haftka, R. T.; Shyy, W.; Goel, T.; Vaidyanathan, R.; Tucker, P. K., Surrogate-based analysis and optimization, Prog. Aerosp. Sci., 41, 1, 1-28 (2005)
[18] Xiao, S.; Rotaru, M.; Sykulski, J. K., Exploration versus exploitation using kriging surrogate modelling in electromagnetic design, COMPEL, 31, 5, 1541-1551 (2012)
[19] Koziel, S., Surrogate-based Modeling and Optimization : Applications in Engineering (2013), Springer: Springer New York, NY · Zbl 1269.00012
[20] Z. Qian, C. Seepersad, V.R. Joseph, J. Allen, C. F. Jeff Wu, Building Surrogate Models Based on Detailed and Approximate Simulations, 128.; Z. Qian, C. Seepersad, V.R. Joseph, J. Allen, C. F. Jeff Wu, Building Surrogate Models Based on Detailed and Approximate Simulations, 128.
[21] Wessing, S.; Rudolph, G.; Turck, S.; Klimmek, C.; Schäfer, S. C.; Schneider, M.; Lehmann, U., Replacing FEA for sheet metal forming by surrogate modeling, Cogent Eng., 1, 1, 950853 (2014)
[22] Rasmussen, C. E.; Williams, C. K.I., Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning series) (2005), The MIT Press
[23] Bishop, C. M., Pattern Recognition and Machine Learning (Information Science and Statistics) (2006), Springer-Verlag New York, Inc.: Springer-Verlag New York, Inc. Secaucus, NJ, USA · Zbl 1107.68072
[24] Duvenaud, D., Automatic Model Construction with Gaussian Processes (2014), University of Cambridge, (Ph.D. thesis)
[25] Williams, C. K.; Rasmussen, C. E., Gaussian processes for regression, Advances in Neural Information Processing Systems, 514-520 (1996)
[26] Rosenblatt, F., The perceptron: a probabilistic model for information storage and organization in the brain., Psychol. Rev., 65, 6, 386 (1958)
[27] Haykin, S., Neural Networks and Learning Machines (2009), Prentice Hall/Pearson: Prentice Hall/Pearson New York
[28] Hagan, M. T.; Demuth, H. B.; Beale, M. H.; De Jesús, O., Neural Network Design, Vol. 20 (1996), Pws Pub. Boston
[29] Kubat, M., An Introduction to Machine Learning (2015), Springer: Springer Cham · Zbl 1330.68003
[30] Mitchell, T., Machine Learning (1997), McGraw-Hill: McGraw-Hill New York · Zbl 0913.68167
[31] Criminisi, A.; Shotton, J.; Konukoglu, E., Decision forests: a unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning, Found. Trends. Comput. Graph. Vision, 7, 2-3, 81-227 (2012) · Zbl 1243.68235
[32] Breiman, L., Random forests, Mach. Learn., 45, 1, 5-32 (2001) · Zbl 1007.68152
[33] Pedregosa, F., Scikit-learn: machine learning in Python, J. Mach. Learn. Res., 12, 2825-2830 (2011) · Zbl 1280.68189
[34] James, G.; Witten, D.; Hastie, T.; Tibshirani, R., An Introduction to Statistical Learning: with Applications in R (Springer Texts in Statistics) (2013), Springer · Zbl 1281.62147
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.