Application of artificial neural network in soil parameter identification for deep excavation numerical model
Abstract
In this paper, an artificial neural network (ANN) is used to approximate response of deep excavation numerical model on input parameters. The approximated model is then used in minimization procedure of the inverse problem, i.e. minimization of the differences between the response of the model (now, neural network) and the field measurements. ANN based objective function is continuous and differentiable thus gradient based optimization algorithm can be efficiently used in this problem. It is showed that initial approximation of the numerical model by means of ANN increase efficiency of the identification process without loss of accuracy.
Keywords:
artificial neural network, parameter identification, deep excavationReferences
[1] R.B.J. Brinkgreve, W. Broere, and R. Al-Khoury. Plaxis: 2D, Version 8. Balkema, 2002.
[2] J. Ghaboussi, D.A. Pecknold, and M. Zhang. Autoprogressive training of neural network constitutive models. Int. J. Numer. Meth. Engng., 42: 105–126, 1998.
[3] K. Hornik, M. Stinchcombe, and H. White. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 3: 551–560, 1990.
[4] Y. Hou, J.Wang, and L. Zhang. Three-dimensional numerical modeling of a deep excavation adjacent to Shanghai Metro tunnels. Computational Science – ICCS 2007, pp. 1164–1171, 2007.
[5] I.E. Lagaris, A. Likas, and D.I. Fotiadis. Artificial neural networks for solving ordinary and partial differential equations. Neural Networks, IEEE Transactions on, 9(5): 987–1000, 1998.
[6] A. Nardin, B. Schrefler, and M. Lefik. Application of artificial neural network for identification of parameters of a constitutive law for soils. Lecture Notes in Computer Science, pp. 545–554, 2003.
[7] S.G. Nash. A survey of truncated-Newton methods. Journal of Computational and Applied Mathematics, 124(1–2): 45–59, 2000.
[8] B. Pichler, R. Lackner, and H.A. Mang. Back analysis of model parameters in geotechnical engineering by means of soft computing. International Journal for Numerical Methods in Engineering, 57(14): 1943–1978, 2003.
[9] C. Rechea, S. Levasseur, and R. Finno. Inverse analysis techniques for parameter identification in simulation of excavation support systems. Computers and Geotechnics, 35(3): 331–345, 2008.
[10] A. Siemińska–Lewandowska. The displacements of anchored diaphragm walls. Studia Geotechnica et Mechanica, 27(1–2): 155–167, 2005.
[11] M. Wojciechowski. Feed-forward artificial neural networks and their derivatives – application possibilities in engineering and geotechnics. Ph.D. Thesis, 2009.
[12] M. Wojciechowski. Feed-forward neural network as a tool for solving nonlinear differential equations. Proceedings of CMM-2009 – Computer Methods in Mechanics, Zielona Góra, May 2009.
[13] M. Wojciechowski. Feed-forward neural network for python, http://ffnet.sourceforge.net., 2007.
[2] J. Ghaboussi, D.A. Pecknold, and M. Zhang. Autoprogressive training of neural network constitutive models. Int. J. Numer. Meth. Engng., 42: 105–126, 1998.
[3] K. Hornik, M. Stinchcombe, and H. White. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 3: 551–560, 1990.
[4] Y. Hou, J.Wang, and L. Zhang. Three-dimensional numerical modeling of a deep excavation adjacent to Shanghai Metro tunnels. Computational Science – ICCS 2007, pp. 1164–1171, 2007.
[5] I.E. Lagaris, A. Likas, and D.I. Fotiadis. Artificial neural networks for solving ordinary and partial differential equations. Neural Networks, IEEE Transactions on, 9(5): 987–1000, 1998.
[6] A. Nardin, B. Schrefler, and M. Lefik. Application of artificial neural network for identification of parameters of a constitutive law for soils. Lecture Notes in Computer Science, pp. 545–554, 2003.
[7] S.G. Nash. A survey of truncated-Newton methods. Journal of Computational and Applied Mathematics, 124(1–2): 45–59, 2000.
[8] B. Pichler, R. Lackner, and H.A. Mang. Back analysis of model parameters in geotechnical engineering by means of soft computing. International Journal for Numerical Methods in Engineering, 57(14): 1943–1978, 2003.
[9] C. Rechea, S. Levasseur, and R. Finno. Inverse analysis techniques for parameter identification in simulation of excavation support systems. Computers and Geotechnics, 35(3): 331–345, 2008.
[10] A. Siemińska–Lewandowska. The displacements of anchored diaphragm walls. Studia Geotechnica et Mechanica, 27(1–2): 155–167, 2005.
[11] M. Wojciechowski. Feed-forward artificial neural networks and their derivatives – application possibilities in engineering and geotechnics. Ph.D. Thesis, 2009.
[12] M. Wojciechowski. Feed-forward neural network as a tool for solving nonlinear differential equations. Proceedings of CMM-2009 – Computer Methods in Mechanics, Zielona Góra, May 2009.
[13] M. Wojciechowski. Feed-forward neural network for python, http://ffnet.sourceforge.net., 2007.
