Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Inelastic Constitutive Modeling for Viscoplastcity Using Neural Networks

  • Lee, Joon-Seong (Division of Mechanical System Design Engineering, Kyonggi University) ;
  • Lee, Yang-Chang (Division of Mechanical System Design Engineering, Kyonggi University) ;
  • Furukawa, Tomonari (Dept. of Mechanical Engineering, The Univ. of New South Wales, Sydney)
  • Published : 2005.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Up to now, a number of models have been proposed and discussed to describe a wide range of inelastic behaviors of materials. The fetal problem of using such models is however the existence of model errors, and the problem remains inevitably as far as a material model is written explicitly. In this paper, the authors define the implicit constitutive model and propose an implicit viscoplastic constitutive model using neural networks. In their modeling, inelastic material behaviors are generalized in a state space representation and the state space form is constructed by a neural network using input output data sets. A technique to extract the input-output data from experimental data is also described. The proposed model was first generated from pseudo-experimental data created by one of the widely used constitutive models and was found to replace the model well. Then, having been tested with the actual experimental data, the proposed model resulted in a negligible amount of model errors indicating its superiority to all the existing explicit models in accuracy.

Keywords

References

  1. Bodner, S.R. 'Constitutive Equation for Elastic- Viscoplastic Strain Hardening Materials', J. of Applied Mechanics, Vol. 42, pp. 385-389, 1975 https://doi.org/10.1115/1.3423586
  2. Chaboche, J.L.,'Constitutive Equations for Cyclic Plasticity', Int. J. of Plasticity, Vol. 5, pp. 247-254, 1990
  3. Miller, A.K., 'An Inelastic Constitutive Model for Monotonic, Cyclic and Creep Deformation', ASME J. of Eng. Materials, Vol. 98, pp. 97-107, 1986
  4. Choboche, J.L. and Rousselier, G., 'On the Plastic and Viscoplastic Equation', Trans. of the ASME, J. of PVT, Vol. 105, pp. 153-164, 1999
  5. Ramberg, W. and Osgood, W.R., 'Description of Stress-Strain Curves by Three Parameters', NACA, Technical Note, No. 902, 1943
  6. Cernocky, E.P. and Krempl, E., 'A Non-Linear Uniaxial Integral Constitutive Equation Incorporating Rate Effects, Creep and Relaxation', Int. J. of Nonlinear Mechanics, Vol. 14, pp. 183-203, 1989
  7. Schmit, C.G. and Miller, A.K., 'A Unified Phenomenological Model for Non-Elastic Deformation of Thpe 316 Stainless Steel, Part I : Development of the Model and Calculation of the Material Constants', Research Mechanics, Vol. 3, pp. 109-175, 1997
  8. Walker, K.P., 'Representation of Hastelloy-X Behavior at Elevated Temperature with a Functional Theory of Viscoplasticity', ASME/ PVP Century 2 Emerging Technology Conference, 1990
  9. Hishida, H., 'Prediction of Life Time of the First Wall on Thermal Fatigue Based on Viscoplastic Deformation', Trans. of Seismic Isolation Structures, pp. 289-294, 1998
  10. Cailletaud, G. and Pilvin, P., 'Identification and Inverse Problems Related to Material Behavior', Inverse Problems in Engineering Mechanics, pp. 79-86, 1994
  11. Furukawa, T. and Yagawa. G., 'A Neural Network Constitutive Law Based on Yield and Back Stresses', The 8th Computational Mechanics Conference, Vol. 95-4, pp. 121-122, 1995
  12. Funahashi, K., 'On the Approximate Realization of Continuous Mapping by Neural Networks', Neural Networks, Vol. 2, pp. 183-192, 1998 https://doi.org/10.1016/0893-6080(89)90003-8
  13. Franklin, G.F., Feedback Control of Dynamic Systems, Addison Sesley, 1991

Cited by

  1. Constitutive Parameter Identification of Inelastic Equations Using an Evolutionary Algorithm vol.19, pp.1, 2009, https://doi.org/10.5391/JKIIS.2009.19.1.096