Active- and transfer-learning applied to microscale-macroscale coupling to simulate viscoelastic flows

Journal Article · Tue Dec 15 00:00:00 EST 2020 · Journal of Computational Physics

DOI:https://doi.org/10.1016/j.jcp.2020.110069· OSTI ID:1853300

Zhao, Lifei ^[1]; Li, Zhen ^[2]; Wang, Zhicheng ^[3]; Caswell, Bruce ^[4]; Ouyang, Jie ^[5]; Karniadakis, George Em ^[3]

---

1. Northwestern Polytechnical Univ., Xi'an, Shaanxi (China). Dept. of Applied Mathematics; Brown Univ., Providence, RI (United States). Dept. of Applied Mathematics; Clemson Univ., SC (United States)
2. Clemson Univ., SC (United States). Dept. of Mechanical Engineering
3. Brown Univ., Providence, RI (United States). Dept. of Applied Mathematics
4. Brown Univ., Providence, RI (United States). School of Engineering
5. Northwestern Polytechnical Univ., Xi'an, Shaanxi (China). Dept. of Applied Mathematics

Active- and transfer-learning are applied to microscale dynamics of polymer flows for the multiscale discovery of effective constitutive approximations required in viscoelastic flow simulation. The result is macroscopic rheology directly connected to a microstructural model. Micro and macroscale simulations are adaptively coupled by means of Gaussian process regression (GPR) to run the expensive microscale computations only as necessary. This multiscale method is demonstrated with flows of a polymer solution as a model system. At the microscale level dissipative particle dynamics (DPD) is employed to model the fluid as a suspension of bead-spring micro-structures subjected to steady shear flow. The results yield the non-Newtonian viscosity and the first normal stress difference at strain rates as training data used in a GPR model. DPD parameters are calibrated with respect to experimental data for a real polymer solution. Compliance with these data requires adjustment of the DPD model's cutoff radius, which then becomes a function of the second invariant of the strain rate tensor. The FENE-P model is chosen for the macroscale description using the spectral element method (SEM) to simulate channel flow and flow past a circular cylinder. The DPD results at the lowest possible shear strain rate yield an estimate of the zero-shear rate viscosity, which allows the initiation of the macroscale flow by SEM as a Newtonian fluid. The resulting strain-rate field is surveyed to determine additional shear strain rate sampling points for the DPD system. This new information allows an initial fitting of parameters of the constitutive equation followed by new SEM simulations at the macroscale. Additionally, guided by active-learning GPR to select new sampling points, this process continues until convergence is achieved. The effectiveness of this new simulation paradigm for viscoelastic flows is tested with different macroscale operating conditions. The effective closure learned in the channel simulation is then transferred directly to the flow past a circular cylinder at low Reynolds number, where the results show that only two additional DPD simulations are required to achieve a satisfactory constitutive model. With an increase of the Reynolds number, the active-learning scheme automatically detects the inaccuracy of the learned constitutive model, and initiates additional DPD simulations for the extra data needed to once again close the microscale-macroscale coupled system. This new paradigm of active- and transfer-learning for multiscale modeling is readily applicable to other microscale-macroscale coupled simulations of complex fluids and other materials. Furthermore, the coupling between microscale and macroscale solvers can be seamlessly implemented with our open source multiscale universal interface (MUI) library.

• Research Organization: Brown Univ., Providence, RI (United States); Brown University, Providence, RI (United States)
• Sponsoring Organization: US Army Research Office (ARO); USDOE; USDOE Office of Science (SC)
• Grant/Contract Number: SC0019453
• OSTI ID: 1853300
• Alternate ID(s): OSTI ID: 1775927; OSTI ID: 23203502; OSTI ID: 2281783
• Journal Information: Journal of Computational Physics, Journal Name: Journal of Computational Physics Journal Issue: C Vol. 427; ISSN 0021-9991
• Publisher: Elsevier
• Country of Publication: United States
• Language: English

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
97 MATHEMATICS AND COMPUTING
Computer Science
Gaussian process regression
Physics
machine learning
non-Newtonian
soft matter
viscoelasticity