Plasticity theory aims at describing the yield loci and work hardening of a material under general deformation states. Most of its complexity arises from the nontrivial dependence of the yield loci on the complete strain history of a material and its microstructure. This motivated 3 ingenious simplifications that underpinned a century of developments in this field: 1) yield criteria describing yield loci location; 2) associative or nonassociative flow rules defining the direction of plastic flow; and 3) effective stress-strain laws consistent with the plastic work equivalence principle. However, 2 key complications arise from these simplifications. First, finding equations that describe these 3 assumptions for materials with complex microstructures is not trivial. Second, yield surface evolution needs to be traced iteratively, i.e., through a return mapping algorithm. Here, we show that these assumptions are not needed in the context of sequence learning when using recurrent neural networks, diverting the above-mentioned complications. This work offers an alternative to currently established plasticity formulations by providing the foundations for finding history- and microstructure-dependent constitutive models through deep learning.

Thin film composition spreads of Mg-Ni were deposited by co-sputtering on micromachined Si-cantilevers. The investigated compositions range from about Mg ₆₀ Ni ₄₀ to about Mg ₈₀ Ni ₂₀ . Structural properties as well as mechanical stress before and after hydrogenation were measured with X-ray diffraction (XRD) and laser profilometry, respectively. The composition spreads were hydrogenated in a special pressure vessel, which allows measuring optically the hydrogen-induced deflection (stress-change) of 16 cantilevers as a function of hydrogen pressure and/or temperature. It was found that the hydrogen-induced stress is correlated with the composition and microstructure of the films. Highest hydrogen-induced stress changes were found for compositions close to the crystalline Mg ₂ Ni phase.