Skip to main content
Log in

Neurocomputing method based on structural finite element analysis of discrete model

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Based on structural finite element analysis of discrete models, a neurocomputing strategy is developed in this paper. Dynamic iterative equations are constructed in terms of neural networks of discrete models. Determination of the iterative step size, which is important for convergence, is investigated based on the positive definiteness of the finite element stiffness matrix. Consequently, a method of choosing the step size of dynamic equations is proposed and the computational formula of the best step size is derived. The analysis of the computing model shows that the solution of finite element system equations can be obtained by the method of neural network computation efficiently. The proposed method can be used for parallel computation of structural finite element in a large-scale integrated circuit (LSI).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Li X, Mo Z, Hu Q (2004) The design and analysis of expandable parallel computation. National Defence Industry Press, Beijing

  2. Liu Y, Zhou W, Liu F (2005) Parallel computing analysis of arch dam and foundation system using 3-D FEM with element-by-element approach. J Tsinghua Univ 45(6):772–775

    Google Scholar 

  3. Hajela P, Berke L (1991) Neurobiological computational models in structural analysis and design. Comput Struct 41(4):657–667

    Article  MATH  Google Scholar 

  4. Lee SC, Park SK, Lee BH (2001) Development of the approximate analytical model for the stub-girder system using neural networks. Comput Struct 79:1013–1025

    Google Scholar 

  5. Li S (2000) Global flexibility simulation and element stiffness simulation in finite element analysis with neural network. Comput Methods Appl Mech Engrg 186:101–108

    Google Scholar 

  6. Takeuchi J, Kosugi Y (1994) Neural network representation of finite element method. Neural Netw 7(2):389–395

    Google Scholar 

  7. Consolazio Gary R (2000) Iterative equation solver for bridge analysis using neural networks. Comput-Aided Civ Infrastr Eng 15:107–119

    Article  Google Scholar 

  8. Li S (2001) SCNN solver for finite element analysis with neural network elements. Proceedings of the sixth international conference on application of artificial intelligence to civil & structural engineering, pp 33–34

  9. Zeng P (1996) Chinese mechanics tending towards 21st century: reports of 9th “The Forum of Young Scientist” of China association for science and technology. Beijing, Tsinghua University Press

  10. Yagawa G, Okuda H (1996) Finite element solutions with feedback network mechanics through direct minimization of energy functionals. Int J Numer Methods Eng 39(5):867–883

    Article  MATH  MathSciNet  Google Scholar 

  11. Lou KN, Perez PA (1995) A novel application of artificial neural networks to structural analysis. Artif Intell Eng 9(3):211–219

    Article  Google Scholar 

  12. Sun D, Hu Q, Xu H (2000) A neurocomputing model for the elastoplasticity. Comput Methods Appl Mech Eng 182(1–2):177–186

    Google Scholar 

  13. Gao HS, Zhang J, Qin WY (2008) On applying CG network to structural analysis. Proceedings of 4th international conference on natural computation, ICNC 2: 560–563

  14. Li HB, Huang HZ (2004) Finite element analysis of structures based on linear saturated system model. Lect Notes Comput Sci 3174:820–825

    Google Scholar 

Download references

Acknowledgments

This research was partially supported by the National Natural Science Foundation of China under the contract number 50775026 and Higher education research projects in Inner Mongolia of the contract number NJZY08058. Constructive suggestions and comments from the referees and editors are very much appreciated. The authors would also like to acknowledge constructive revision suggestions and help with English by Professor Hae Chang Gea, Department of Mechanical and Aerospace Engineering, Rutgers, The State University of New Jersey and Dr. Christopher Hoyle, Department of Mechanical Engineering, Northwestern University, USA.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Hong-Zhong Huang.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Li, H., Duan, W. & Huang, HZ. Neurocomputing method based on structural finite element analysis of discrete model. Neural Comput & Applic 19, 875–882 (2010). https://doi.org/10.1007/s00521-010-0353-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-010-0353-0

Keywords

Navigation