Determination of relaxation modulus of time-dependent materials using neural networks
Tóm tắt
Health monitoring systems for plastic based structures require the capability of real time tracking of changes in response to the time-dependent behavior of polymer based structures. The paper proposes artificial neural networks as a tool of solving inverse problem appearing within time-dependent material characterization, since the conventional methods are computationally demanding and cannot operate in the real time mode. Abilities of a Multilayer Perceptron (MLP) and a Radial Basis Function Neural Network (RBFN) to solve ill-posed inverse problems on an example of determination of a time-dependent relaxation modulus curve segment from constant strain rate tensile test data are investigated. The required modeling data composed of strain rate, tensile and related relaxation modulus were generated using existing closed-form solution. Several neural networks topologies were tested with respect to the structure of input data, and their performance was compared to an exponential fitting technique. Selected optimal topologies of MLP and RBFN were tested for generalization and robustness on noisy data; performance of all the modeling methods with respect to the number of data points in the input vector was analyzed as well. It was shown that MLP and RBFN are capable of solving inverse problems related to the determination of a time dependent relaxation modulus curve segment. Particular topologies demonstrate good generalization and robustness capabilities, where the topology of RBFN with data provided in parallel proved to be superior compared to other methods.
Tài liệu tham khảo
Adler, A., Guardo, R.: A Neural Network Image Reconstruction Technique for Electrical Impedance Tomography. IEEE Trans. Med. Imaging 13(4), 594–600 (1994)
Baddari, K., et al.: Acoustic impedance inversion by feedback artificial neural network. J. Pet. Sci. Eng. 71(3–4), 106–111 (2010)
Czél, B., Woodbury, K.A., Gróf, G.: Inverse identification of temperature-dependent volumetric heat capacity by neural networks. Int. J. Thermophys. 34(2), 284–305 (2013)
Demuth, H., Beale, M., Hagan, M.: Neural Network ToolboxTM 6 User’s Guide (2009)
Elshafiey, I., Udpa, L., Udpa, S.S.: Application of neural networks to inverse problems in electromagnetics. IEEE Trans. Magn. 30(5), 0 (1994)
Elshafiey, I., Udpa, L., Udpa, S.S.: Solution of inverse problems in electromagnetics using Hopfield neural networks. IEEE Trans. Magn. 31(1), 852–861 (1995)
Ferry, J.D.: Viscoelastic properties of polymers, 650 (1980)
Hagan, M.T., Demuth, H.B., Beale, M.H.: Neural network design (1996)
Haj-Ali, R., et al.: Nonlinear constitutive models from nanoindentation tests using artificial neural networks. Int. J. Plast. 24(3), 371–396 (2008)
Haykin, S.: Neural networks: a comprehensive foundation (1999)
ISO 527-1: Plastics—determination of tensile properties—part 1: general principles (2012)
Jung, S., Ghaboussi, J.: Neural network constitutive model for rate-dependent materials. Comput. Struct. 84(15–16), 955–963 (2006)
Knauss, W.G., Zhao, J.: Improved relaxation time coverage in ramp-strain histories. Mech. Time-Depend. Mater. 11(3–4), 199–216 (2007)
Lampinen, J., Vehtari, A.: Using Bayesian Neural Network to Solve the Inverse Problem in Electrical Impedance Tomography. In: Proceedings of the Scandinavian Conference on Image Analysis, p. 1 (1999)
Li, M.M., et al.: Intelligent methods for solving inverse problems of backscattering spectra with noise: a comparison between neural networks and simulated annealing. Neural Comput. Appl. 18(5), 423–430 (2009)
Li, M.M., et al.: RBF neural networks for solving the inverse problem of backscattering spectra. Neural Comput. Appl. 17(4), 391–397 (2008)
MacKay, D.J.C.: Bayesian Interpolation. Neural Comput. 4(3), 415–447 (1992)
Nguyen, D., Widrow, B.: Improving the Learning Speed of 2-Layer Neural Networks by choosing Initial Values of the Adaptive Weights. In: IJCNN International Joint Conference on Neural Networks, vol. 3, pp. 21–26 (1990)
Samarskii, A.A., Vabishchevich, P.N., De, W.: Numerical Methods for Solving Inverse Problems of Mathematical Physics. Walter de Gruyter, Berlin (2009)
Sammany, M., Pelican, E., Harak, T.A.: Hybrid neuro-genetic based method for solving ill-posed inverse problem occurring in synthesis of electromagnetic fields. Computing 91(4), 353–364 (2010)
Sammut, C., Webb, G.: Topology of neural Network. In: Encyclopedia of Machine Learning, pp. 988–989 (2011). Chapter 19
Saprunov, I., Gergesova, M., Emri, I.: Prediction of viscoelastic material functions from constant stress- or strain-rate experiments. Mech. Time-Depend. Mater. 18(2), 349–372 (2014)
Sjoberg, J., Ljung, L.: Overtraining, Regularization and Searching for Minimum in Neural Networks, 1–16 (1992)
Tikhonov, A., Arsenin, V.: Solutions of Inverse Problems. John Wiley & Sons, Washington (1977)
Tscharnuter, D., Jerabek, M., Major, Z., Lang, R.W.: On the determination of the relaxation modulus of PP compounds from arbitrary strain histories. Mech. Time-Depend. Mater. 15(1), 1–14 (2011)
Werbos, P.: The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting. Wiley, New York (1994)
Xiao, W., et al.: Real-time identification of optimal operating points in photovoltaic power systems. IEEE Trans. Ind. Electron. 53(4), 1017–1026 (2006)