×

Data-driven inverse modelling through neural network (deep learning) and computational heat transfer. (English) Zbl 1506.74503

Summary: In this work, the potential of carrying out inverse problems with linear and non-linear behaviour is investigated using deep learning methods. In inverse problems, the boundary conditions are determined using sparse measurement of a variable such as velocity or temperature. Although this is mathematically tractable for simple problems, it can be extremely challenging for complex problems. To overcome the non-linear and complex effects, a brute force approach was used on a trial and error basis to find an approximate solution. With the advent of machine learning algorithms it may now be possible to model inverse problems faster and more accurately. In order to demonstrate that machine learning can be used in solving inverse problems, we propose a fusion between computational mechanics and machine learning. The forward problems are solved first to create a database. This database is then used to train the machine learning algorithms. The trained algorithm is then used to determine the boundary conditions of a problem from assumed measurements. The proposed method is tested for the linear/non-linear heat conduction, convection-conduction, and natural convection problems in which the boundary conditions are determined by providing three, four, and five temperature measurements. This study demonstrates that the proposed fusion of computational mechanics and machine learning is an effective way of tackling complex inverse problems.

MSC:

74S99 Numerical and other methods in solid mechanics
65J22 Numerical solution to inverse problems in abstract spaces
74A15 Thermodynamics in solid mechanics
80A19 Diffusive and convective heat and mass transfer, heat flow
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Ozisik, M. N.; Orlande, H. R.B., Inverse Heat Transfer (2000), Taylor and Francis
[2] Tikhonov, A. N.; Goncharsky, A. V.; Stepanov, V. V.; Yagola, A. G., Numerical Methods for the Solution of Ill-Posed Problems (1995), Kluwer, Springer: Kluwer, Springer Dordrecht · Zbl 0831.65059
[3] Engl, H. W.; Hanke, M.; Neubauer, A., (Regularization of Inverse Problems. Regularization of Inverse Problems, Mathematics and Its Applications, vol. 375 (2000), Kluwer Academic Publishers Group: Kluwer Academic Publishers Group Dordrecht)
[4] Ippoliti, E., Heuristic reasoning, (Studies in Applied Philosophy, Epistemology and Rational Ethics (2015), Springer International Publishing: Springer International Publishing Switzerland), 1-2
[5] Pearl, J., Heuristics: Intelligent Search Strategies for Computer Problem Solving, 3 (1984), United States:Addison-Wesley Pub. Co., Inc: United States:Addison-Wesley Pub. Co., Inc Reading, MA, Retrieved June 13, 2017
[6] Fellows, M. R.; Fomin, F. V.; Lokshtanov, D.; Rosamond, F.; Saurabh, S.; Villanger, Y., Local search: Is brute-force avoidable?, J. Comput. System Sci., 78, 707-719 (2012) · Zbl 1244.68070
[7] Jaluria, Y., Solution of inverse problems and thermal system, J. Thermal Sci. Eng. Appl. (2018), TSEA-18-1485
[8] Jaluria, Y., Design and Optimization of Thermal Systems (2008), CRC Press: CRC Press Boca Raton, FL · Zbl 1171.80001
[9] Bangian-Tabrizi, A.; Jaluria, Y., An optimization strategy for the inverse solution of a convection heat transfer problem, Int. J. Heat Mass Transfer, 124, 1147-1155 (2018)
[10] Zhang, Y.; Shuihua, W.; Ji, G., A comprehensive survey on particle swarm optimization algorithm and its applications, Math. Probl. Eng., 2015, 1-38 (2015) · Zbl 1394.90588
[11] Voronin, S.; Zaroli, C., Survey of computational methods for inverse problems (2018)
[12] Yaman, F.; Yakhno, V. G.; Potthast, R., A survey on inverse problems for applied sciences, Math. Probl. Eng. (2013), Article ID 976837 · Zbl 1299.35321
[13] Szénási, S.; Felde, I., Using multiple graphics accelerators to solve the two-dimensional inverse heat conduction problem, Comput. Methods Appl. Mech. Engrg., 336, 286-303 (2018) · Zbl 1440.74442
[14] Bengio, Y., Learning deep architectures for AI, Found. Trends Mach. Learn., 2, 1-127 (2009) · Zbl 1192.68503
[15] Capuano, G.; Rimoli, J. J., Smart finite elements: A novel machine learning application, Comput. Methods Appl. Mech. Engrg., 345, 363-381 (2019) · Zbl 1440.65190
[16] Kirchdoerfer, T.; Ortiz, M., Data-driven computational mechanics, Comput. Methods Appl. Mech. Engrg., 304, 81-101 (2016) · Zbl 1425.74503
[17] Chollet, F., Deep Learning with Python (2018), Manning Publications Co.
[18] LeCun, Y.; Bengio, Y.; Hinton, G., Deep learning, Nature, 521, 436-444 (2015)
[19] Yagawa, G.; Okuda, H., Neural networks in computational mechanics, Arch. Comput. Methods Eng., 3, 4, 435-512 (1996)
[20] Yang, K. T., Artificial neural networks (ANNs), A new paradigm for thermal science and engineering, J. Heat Transfer, 130 (2008), / 093001-1
[21] X. Guo, W. Li, F. Iorio, Convolutional neural networks for steady flow approximation, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge, Discovery and Data Mining, 2016, pp. 481-490.
[22] Schmidhuber, J., History of computer vision contests won by deep CNNs on GPU (2017), Retrieved 14 January 2019
[23] Oishi, A.; Yagawa, G., Computational mechanics enhanced by deep learning, Comput. Methods Appl. Mech. Engrg., 327, 327-351 (2017) · Zbl 1439.74458
[24] Chanda, S.; Balaji, C.; Venkateshan, S. P.; Yenni, G. R., Estimation of principal thermal conductivities of layered honeycomb composites using ANN-GA based inverse technique, Int. J. Therm. Sci., 111, 423-436 (2017)
[25] Nithiarasu, P.; Lewis, R. W.; Seetharamu, K. N., Fundamentals of the Finite Element Method for Heat and Fluid Flow (2016), John Wiley and Sons Ltd · Zbl 1348.80001
[26] Nithiarasu, P.; Seetharamu, K. N.; Sundararajan, T., Finite element modelling of flow, heat and mass transfer in fluid saturated porous media, Arch. Comput. Meth. Engng., 9, 1, 3-42 (2002) · Zbl 1001.76059
[27] Urban, G.; Geras, K. J.; Ebrahimi Kahou, S.; Aslan, Ö.; Wang, S.; Caruana, R.; Mohamed, A.; Philipose, M.; Richardson, M., Do deep convolutional nets really need to be deep (or even convolutional)? (2016), CoRR, abs/1603.05691
[28] Kingma, D. P.; Ba, J., Adam: A method for stochastic optimization (2014)
[29] Zienkiewicz, O. C.; Taylor, R. L.; Nithiarasu, P., The Finite Element Method for Fluid Dynamics (2013), Elsevier
[30] Hughes, T. J.R., The Finite Element Method: Linear Static and Dynamic Finite Element Analysis (2012), Courier Corporation
[31] Shapley, L., A value for n-person games, (Contrib. Theory of Games, II. Contrib. Theory of Games, II, Ann. Math. Stud., 28 (1953)), 307-317 · Zbl 0050.14404
[32] Owen, A. B.; Prieur, C., On shapley value for measuring importance of dependent inputs, SIAM/ASA J. Uncertain. Quantif., 5, 1, 986-1002 (2017) · Zbl 1386.65064
[33] Lundberg, S. M.; Lee, S.-I., A unified approach to interpreting model predictions, (Advances in Neural Information Processing Systems, Vol. 30 (2017)), 4765-4774
[34] Ding, D.; Townsend, P.; Webster, M. F., Computer modelling of transient thermal flows of non-Newtonian fluids, J. Non-Newton. Fluid Mech., 47, 239-265 (1993) · Zbl 0774.76004
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.