03116nas a2200289 4500008004100000022001400041245012700055210006900182260001200251490000800263520211800271653003002389653001802419653002602437653002402463653004302487653003602530653003102566100001602597700002302613700002402636700002102660700002402681700002402705700002102729856007602750 2022 eng d a0168-874X00aFinite element based Model Order Reduction for parametrized one-way coupled steady state linear thermo-mechanical problems0 aFinite element based Model Order Reduction for parametrized onew c12/20220 v2123 a

This contribution focuses on the development of Model Order Reduction (MOR) for one-way coupled steady state linear thermo-mechanical problems in a finite element setting. We apply Proper Orthogonal Decomposition (POD) for the computation of reduced basis space. On the other hand, for the evaluation of the modal coefficients, we use two different methodologies: the one based on the Galerkin projection (G) and the other one based on Artificial Neural Network (ANN). We aim to compare POD-G and POD-ANN in terms of relevant features including errors and computational efficiency. In this context, both physical and geometrical parametrization are considered. We also carry out a validation of the Full Order Model (FOM) based on customized benchmarks in order to provide a complete computational pipeline. The framework proposed is applied to a relevant industrial problem related to the investigation of thermo-mechanical phenomena arising in blast furnace hearth walls.

10aArtificial Neural Network10aBlast furnace10aFinite Element Method10aGalerkin projection10aGeometric and physical parametrization10aProper orthogonal decomposition10aThermo-mechanical problems1 aShah, Nirav1 aGirfoglio, Michele1 aQuintela, Peregrina1 aRozza, Gianluigi1 aLengomin, Alejandro1 aBallarin, Francesco1 aBarral, Patricia uhttps://www.sciencedirect.com/science/article/abs/pii/S0168874X2200110X