Self-learning finite elements for inverse estimation of thermal constitutive models

In this work, a new methodology for inverse estimation of thermal constitutive models is introduced. This new methodology combines computational intelligence with finite element analysis for solving inverse heat transfer problems. A neural network (NN) representation of thermal constitutive behavior and its implementation in non-linear finite element analysis are presented. The self-learning methodology uses a novel concept for developing material models using experimental data and iterative finite element analyses. The proposed methodology searches for complete thermal constitutive models as opposed to identifying parameters in predetermined functional forms. The application of this new methodology is illustrated using a simulated steady-state heat conduction problem. It was found in simulated experiments that the self-learning finite element method can inversely recover accurate NN representations of thermal constitutive models using simple temperature measurements. Moreover, the method showed stability in the presence of imperfect or noisy data. It is shown that the use of a NN representation of the constitutive model improves the stability of solutions naturally due to the imprecision tolerance of NN.

[1]  J. F. Stelzer,et al.  Experiences in non‐linear analysis of temperature fields with finite elements , 1987 .

[2]  James H. Garrett,et al.  Knowledge-Based Modeling of Material Behavior with Neural Networks , 1992 .

[3]  Cheng-Hung Huang,et al.  A two-dimensional inverse problem in imaging the thermal conductivity of a non-homogeneous medium , 2000 .

[4]  S. Ashforth-Frost,et al.  Evaluating convective heat transfer coefficients using neural networks , 1996 .

[5]  Pierre Cardaliaguet,et al.  Approximation of a function and its derivative with a neural network , 1992, Neural Networks.

[6]  Jamshid Ghaboussi,et al.  Constitutive modeling of geomaterials from non-uniform material tests , 1998 .

[7]  Jamshid Ghaboussi,et al.  Autoprogressive training of neural network constitutive models , 1998 .

[8]  O. Alifanov.  Inverse heat transfer problems , 1994 .

[9]  Cha'o-Kuang Chen,et al.  Inverse Method for Estimating Thermal Conductivity in One-Dimensional Heat Conduction Problems , 2001 .

[10]  M. Tadi,et al.  Evaluation of a Two-Dimensional Conductivity Function Based on Boundary Measurements , 2000 .

[11]  Yildiz Bayazitoglu,et al.  International Journal of Heat and Mass Transfer , 2013 .

[12]  Mihir Sen,et al.  Dynamic prediction and control of heat exchangers using artificial neural networks , 2001 .

[13]  Genki Yagawa,et al.  Implicit constitutive modelling for viscoplasticity using neural networks , 1998 .

[14]  L. Piazza,et al.  Analysis of forced convection heat transfer to supercritical carbon dioxide inside tubes using neural networks , 2003 .

[15]  Youssef M A Hashash,et al.  Numerical implementation of a neural network based material model in finite element analysis , 2004 .

[16]  Faïçal Larachi,et al.  Prediction of liquid - solid wetting efficiency in trickle flow reactors , 2001 .

[17]  Pawel Strumillo,et al.  Hybrid neural model of thermal drying in a fluidized bed , 1996 .

[18]  B. Blackwell,et al.  Inverse Heat Conduction: Ill-Posed Problems , 1985 .

[19]  Estrella Alvarez,et al.  Model based in neural networks for the prediction of the mass transfer coefficients in bubble columns. Study in Newtonian and non-Newtonianian fluids , 2000 .

[20]  Alain J. Kassab,et al.  CHARACTERIZATION OF SPACE DEPENDENT THERMAL CONDUCTIVITY WITH A BEM-BASED GENETIC ALGORITHM , 2000 .

[21]  S. Ashforth-Frost,et al.  The role of neural networks in fluid mechanics and heat transfer , 1995, Proceedings of 1995 IEEE Instrumentation and Measurement Technology Conference - IMTC '95.