Neural and finite element analysis of a plane steel frame reliability by the classical Monte Carlo method. (English) Zbl 1058.74566
Rutkowski, Leszsk (ed.) et al., Artificial intelligence and soft computing – ICAISC 2004. 7th international conference, Zakopane, Poland, June 7–11, 2004. Proceedings. Berlin: Springer (ISBN 3-540-22123-9/pbk). Lecture Notes in Computer Science 3070. Lecture Notes in Artificial Intelligence, 1081-1086 (2004).
Summary: The paper is a continuation of [M. Papadrakakis, V. Papadopoulos and N. D. Lagaros,
Comput. Methods Appl. Mech. Eng. 136, 145–163 (1996; Zbl 0893.73079)], where a feed-forward neural network was used for generating samples in the Monte Carlo methods. The patterns for network training and testing were computed by an FEM program. A high numerical efficiency of neural generating MC samples does not correspond to the much more time consuming FEM computation of patterns. This question and an evaluation of the number of random inputs is discussed in the presented paper on an example of a plane steel frame, called previously a calibrating frame.
For the entire collection see [Zbl 1052.68007].
For the entire collection see [Zbl 1052.68007].
MSC:
| 74K10 | Rods (beams, columns, shafts, arches, rings, etc.) |
| 74S30 | Other numerical methods in solid mechanics (MSC2010) |
| 74R99 | Fracture and damage |
| 65C05 | Monte Carlo methods |
| 68T05 | Learning and adaptive systems in artificial intelligence |
