ANN approach to sorption hysteresis within a coupled hygro-thermo-mechanical FE analysis

Non-linear deformable porous media with sorption (capillary condensation) hysteresis are considered. An arti cial 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 e ect 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 di erences are observed for the saturation and displacement solutions. The ANN-FE approach seems to be an e cient way to take into account the in uence of hysteresis during analysis of hygro-thermal behaviour of capillary-porous materials