skip to main content

Explore Research Products in the NSF-PAR

Title: Deep learning predicts path-dependent plasticity
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.  more » « less
Award ID(s):
1646592
NSF-PAR ID:
10129616
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Proceedings of the National Academy of Sciences
Volume:
116
Issue:
52
ISSN:
0027-8424
Page Range / eLocation ID:
26414 to 26420
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ( , Journal of Applied Mechanics)
    null (Ed.)
    Conventionally, neural network constitutive laws for path-dependent elasto-plastic solids are trained via supervised learning performed on recurrent neural network, with the time history of strain as input and the stress as input. However, training neural network to replicate path-dependent constitutive responses require significant more amount of data due to the path dependence. This demand on diverse and abundance of accurate data, as well as the lack of interpretability to guide the data generation process, could become major roadblocks for engineering applications. In this work, we attempt to simplify these training processes and improve the interpretability of the trained models by breaking down the training of material models into multiple supervised machine learning programs for elasticity, initial yielding and hardening laws that can be conducted sequentially. To predict pressure-sensitivity and rate dependence of the plastic responses, we reformulate the Hamliton-Jacobi equation such that the yield function is parametrized in the product space spanned by the principle stress, the accumulated plastic strain and time. To test the versatility of the neural network meta-modeling framework, we conduct multiple numerical experiments where neural networks are trained and validated against (1) data generated from known benchmark models, (2) data obtained from physical experiments and (3) data inferred from homogenizing sub-scale direct numerical simulations of microstructures. The neural network model is also incorporated into an offline FFT-FEM model to improve the efficiency of the multiscale calculations. 
    more » « less
  2. ; ; ; ( , Continuum Mechanics and Thermodynamics)
    null (Ed.)
    This paper is devoted to the development of a continuum theory for materials having granular microstructure and accounting for some dissipative phenomena like damage and plasticity. The continuum description is constructed by means of purely mechanical concepts, assuming expressions of elastic and dissipation energies as well as postulating a hemi-variational principle, without incorporating any additional postulate like flow rules. Granular micromechanics is connected kinematically to the continuum scale through Piola's ansatz. Mechanically meaningful objective kinematic descriptors aimed at accounting for grain-grain relative displacements in finite deformations are proposed. Karush-Kuhn-Tucker (KKT) type conditions, providing evolution equations for damage and plastic variables associated to grain-grain interactions, are derived solely from the fundamental postulates. Numerical experiments have been performed to investigate the applicability of the model. Cyclic loading-unloading histories have been considered to elucidate the material-hysteretic features of the continuum, which emerge from simple grain-grain interactions. We also assess the competition between damage and plasticity, each having an effect on the other. Further, the evolution of the load-free shape is shown not only to assess the plastic behavior, but also to make tangible the point that, in the proposed approach, plastic strain is found to be intrinsically compatible with the existence of a placement function. 
    more » « less
  3. ; ; ; ; ( , arXivorg)
    Study of the plastic flow and strain-induced phase transformations (PTs) under high pressure with diamond anvils is important for material and geophysics. We introduce rough diamond anvils and apply them to Zr, which drastically change the plastic flow, microstructure, and PTs. Multiple steady microstructures independent of pressure, plastic strain, and strain path are reached. Maximum friction equal to the yield strength in shear is achieved. This allows determination of the pressure-dependence of the yield strength and proves that omega-Zr behaves like perfectly plastic, isotropic, and strain path-independent immediately after PT. Record minimum pressure for alpha-omega PT was identified. Kinetics of strain-induced PT depends on plastic strain and time. Crystallite size and dislocation density in omega-Zr during PT depend solely on the volume fraction of omega-Zr. 
    more » « less
  4. ; ; ; ; ( , ArXivorg)
    Study of the plastic flow and strain-induced phase transformations (PTs) under high pressure with diamond anvils is important for material and geophysics. We introduce rough diamond anvils and apply them to Zr, which drastically change the plastic flow, microstructure, and PTs. Multiple steady microstructures independent of pressure, plastic strain, and strain path are reached. Maximum friction equal to the yield strength in shear is achieved. This allows determination of the pressure-dependence of the yield strength and proves that ω-Zr behaves like perfectly plastic, isotropic, and strain path-independent immediately after PT. Record minimum pressure for α-ω PT was identified. Kinetics of strain-induced PT depends on plastic strain and time. Crystallite size and dislocation density in ω-Zr during PT depend solely on the volume fraction of ω-Zr. 
    more » « less
  5. ; ( , Report No. UCD/CGM-18/01, Center for Geotechnical Modeling, Department of Civil and Environmental Engineering, University of California, Davis, CA, 108 pp.)
    The PM4Silt plasticity model for representing low-plasticity silts and clays in geotechnical earthquake engineering applications is presented herein. The PM4Silt model builds on the framework of the stress-ratio controlled, critical state compatible, bounding surface plasticity PM4Sand model (version 3) described in Boulanger and Ziotopoulou (2015) and Ziotopoulou and Boulanger (2016). Modifications to the model were developed and implemented to improve its ability to approximate undrained monotonic and cyclic loading responses of low-plasticity silts and clays, as opposed to those for purely nonplastic silts or sands. Emphasis was given to obtaining reasonable approximations of undrained monotonic shear strengths, undrained cyclic shear strengths, and shear modulus reduction and hysteretic damping responses across a range of initial static shear stress and overburden stress conditions. The model does not include a cap, and therefore is not suited for simulating consolidation settlements or strength evolution with consolidation stress history. The model is cast in terms of the state parameter relative to a linear critical state line in void ratio versus logarithm of mean effective stress. The primary input parameters are the undrained shear strength ratio (or undrained shear strength), the shear modulus coefficient, the contraction rate parameter, and an optional post-strong-shaking shear strength reduction factor. All secondary input parameters are assigned default values based on a generalized calibration. Secondary parameters that are most likely to warrant adjustment based on site-specific laboratory test data include the shear modulus exponent, plastic modulus coefficient (adjusts modulus reduction with shear strain), bounding stress ratio parameters (affect peak friction angles and undrained stress paths), fabric related parameters (affect rate of shear strain accumulation at larger strains and shape of stress-strain hysteresis loops), maximum excess pore pressure ratio, initial void ratio, and compressibility index. The model is coded as a user defined material in a dynamic link library (DLL) for use with the commercial program FLAC 8.0 (Itasca 2016). The numerical implementation and DLL module are described. The behavior of the model is illustrated by simulations of element loading tests covering a range of conditions, including undrained monotonic and cyclic loading under a range of initial confining and shear stress conditions. The model is shown to provide reasonable approximations of behaviors important to many earthquake engineering applications and to be relatively easy to calibrate. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email