Neural analysis of elastoplastic plane stress problem with unilateral constraints
Abstract
The paper is a development and continuation of paper [8] where the Panagiotopoulos approach was extended for the elastoplastic analysis. In case of elastic analysis the parameters of the Hopfield-Tank Neural Network (HTNN) are calibrated only once but the updating of the elastoplastic stiffness matrix needs an iteration of HTNN and FE system. The main problem is the matrix condensation repeated for each iteration step of the Newton-Raphson method. Besides all the improvements proposed in [15], a new interacting program has been implemented which enables a significant decrease of the processing time (number of iterations) in comparison with the time achieved in [8]. The results of the extensive numerical analysis are discussed for a tension perforated strip with a rigid bolt placed frictionlessly in a circular hole in the middle of the strip.
Keywords
neural network, finite element method, elastoplastic problem, unilateral constraints,References
[1] A.V. Avdelas et al. Neural networks for computing in the elastoplastic analysis of structures. Mechanica, 30: 1-15, 1995.[2] G. Engeln-Mullges, F. Uhlig. Numerical Algorithms with C. Springer, Berlin-Heidelberg, 1996.
[3] J . Ghaboussi et al. Knowledge-based modeling of material behavior with neural networks. ASCE J. Engrg. Mech., 117: 132-153, 1991.
[4] Ł. Kaczmarczyk, Z. Waszczyszyn. Neural procedures for the hybrid FEM/NN analysis of elastoplastic plates. Comput. Assisted Mech. Engrg. Sci., 12: 379- 391, 2005.
[5] S. Kortesis, P.G. Panagiotopoulos. Neural networks for computing in structural analysis - methods and prospects of applications. Int. J. Num. Meth. Engrg., 36: 2305-2318, 1993.
