ANN approach to sorption hysteresis within a coupled hygro-thermo-mechanical FE analysis
Gawin, D., Le, M., and Schrefler, B. A.
2001 International journal for numerical methods in engineering, 50:299-323
Gawin, D., Le, M., and Schrefler, B. A., (2001), "ANN approach to sorption hysteresis within a coupled hygro-thermo-mechanical FE analysis", International journal for numerical methods in engineering, 50:299-323.
Abstract:
SUMMARY
Non-linear deformable porous media with sorption (capillary condensation) hysteresis are considered. An artifcial neural network with two hidden layers is trained to interpolate the sorption hysteresis using a set of experimental data. The performance of the ANN, which is applied as a procedure in the FE code, is investigated, both from numerical, as well as from physical viewpoint. The ANN-FE code has been developed and tested for 1-D and 2-D problems concerning cyclic wetting{drying of concrete elements. In general, the application of the ANN procedure inside the classical FE program does not have any negative elect on the numerical performance of the code. The results obtained indicate that the sorption isotherm hysteresis is of importance during analysis of hygrothermal and mechanical behaviour of capillary-porous materials. The most distinct differences are observed for the saturation and displacement solutions. The ANN-FE approach seems to be an effcient way to take into account the influence of hysteresis during analysis of hygro-thermal behaviour of capillary-porous materials.
This publication in whole or part might be found online. Check the sources on the related article below. Or use search engines on the web.
DOE--Department of Energy "The Department of Energy's overarching mission is enhancing national security. Responsibility for accomplishing this mission is shared between four principal program lines."
Schrefler, B. A. Poland. Bernhard A. Schrefler is a professor in the Department of Structures and Transportation Engineering, University of Padova, Padova,
Italy.
