A mixture of experts approach to handle ambiguities in parameter identification problems in material modeling

Abstract To simulate the mechanical behavior of a material, it is essential to calibrate the internal parameters of the used material model to experimental measurements. This is typically done in a trail-and-error approach by hand or automatically using optimization algorithms. As an alternative to trial-and-error, neural network-based approaches can be used to imitate the inverse mapping. This is usually realized in a grey-box model, combining neural networks, deterministic models, and domain knowledge. However, the proposed neural network-based approaches found in literature do not address the challenge that is posed when the parameter identification problem is non-unique. In the present paper this problem is discussed and an improved approach is proposed using a mixture of experts model. Mixture of experts is an ensemble technique based on a dynamically structured framework of submodels aiming to partition the non-unique problem into unique subtasks.

[1]  Bernhard A. Schrefler,et al.  Application of Artificial Neural Network for Identification of Parameters of a Constitutive Law for Soils , 2003, IEA/AIE.

[2]  Zoubin Ghahramani,et al.  Solving inverse problems using an EM approach to density estimation , 1993 .

[3]  J. Chaboche,et al.  On the Plastic and Viscoplastic Constitutive Equations—Part I: Rules Developed With Internal Variable Concept , 1983 .

[4]  Ch. Tsakmakis,et al.  Determination of constitutive properties fromspherical indentation data using neural networks. Part i:the case of pure kinematic hardening in plasticity laws , 1999 .

[5]  R. Taylor,et al.  Thermomechanical analysis of viscoelastic solids , 1970 .

[6]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[7]  Dimitris N. Metaxas,et al.  Learning Ambiguities Using Bayesian Mixture of Experts , 2006, 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06).

[8]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[9]  Frank Klawonn,et al.  Detecting Ambiguities in Regression Problems using TSK Models , 2006, Soft Comput..

[10]  Bernhard A. Schrefler,et al.  Artificial neural network for parameter identifications for an elasto-plastic model of superconducting cable under cyclic loading , 2002 .

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[12]  Volker Tresp,et al.  Mixtures of Gaussian Processes , 2000, NIPS.

[13]  Genki Yagawa,et al.  Neural networks in computational mechanics , 1996 .

[14]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[15]  Jan Pagenkopf,et al.  Bestimmung der plastischen Anisotropie von Blechwerkstoffen durch ortsaufgelöste Simulationen auf Gefügeebene , 2018 .

[16]  Material‐based process‐chain optimization in metal forming , 2017 .

[17]  Joseph N. Wilson,et al.  Twenty Years of Mixture of Experts , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[19]  M. D. McKay,et al.  A comparison of three methods for selecting values of input variables in the analysis of output from a computer code , 2000 .

[20]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[21]  Carsten Könke,et al.  An inverse parameter identification procedure assessing the quality of the estimates using Bayesian neural networks , 2011, Appl. Soft Comput..

[22]  Thomas J. Santner,et al.  The Design and Analysis of Computer Experiments , 2003, Springer Series in Statistics.

[23]  Christopher M. Bishop,et al.  Bayesian Hierarchical Mixtures of Experts , 2002, UAI.

[24]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[25]  Rolf Mahnken,et al.  Identification of Material Parameters for Constitutive Equations , 2004 .

[26]  D. Helm.  Stress computation in finite thermoviscoplasticity , 2006 .

[27]  C. Bishop.  Mixture density networks , 1994 .

[28]  Rolf Mahnken,et al.  A unified approach for parameter identification of inelastic material models in the frame of the finite element method , 1996 .

[29]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[30]  Rolf Mahnken,et al.  Parameter identification for viscoplastic models based on analytical derivatives of a least-squares functional and stability investigations , 1996 .

[31]  Jocelyn Sietsma,et al.  Creating artificial neural networks that generalize , 1991, Neural Networks.

[32]  Michael I. Jordan,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1994, Neural Computation.

[33]  Ch. Tsakmakis,et al.  Determination of constitutive properties fromspherical indentation data using neural networks. Part ii:plasticity with nonlinear isotropic and kinematichardening , 1999 .

[34]  Steve R. Waterhouse,et al.  Bayesian Methods for Mixtures of Experts , 1995, NIPS.