Journal Article

Deep learning predicts path-dependent plasticity

Cao, J., Ehmann, K., Chen, W., Mozaffar, M., Bessa, M. A., Bostanabad, R.

2019

Overview

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.

• Publisher: National Academy of Sciences
• Subject: Algorithms / Complexity / Constitutive models / Deep learning / Engineering / Equivalence principle / Loci / Machine learning / Mapping / Microstructure / Neural networks / Physical Sciences / Plastic flow / Plastic properties / Plasticity / Recurrent neural networks / Strain / Work hardening / Yield criteria