A framework for simultaneous model predictive control and online parameter estimation is introduced by treating differentiable physics simulators as computational objects for gradient-based joint optimization.
Learning constitutive models and rheology from partial flow measurements
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
A neural network learns parameter-dependent viscosity models for ice that satisfy physical invariants and generalize from velocity or stress data.
Rheo-SINDy recovers the exact Giesekus constitutive model and approximates FENE dumbbell extensional rheology from simulation data.
citing papers explorer
-
MPC and System Identification with Differentiable Physics: Fluid System and Particle Beam Control
A framework for simultaneous model predictive control and online parameter estimation is introduced by treating differentiable physics simulators as computational objects for gradient-based joint optimization.
-
Learning parameter-dependent shear viscosity from data, with application to sea and land ice
A neural network learns parameter-dependent viscosity models for ice that satisfy physical invariants and generalize from velocity or stress data.
-
Development of Rheological Constitutive Modeling Method Using a Sparse Identification Algorithm: A Case Study for Extensional Flows
Rheo-SINDy recovers the exact Giesekus constitutive model and approximates FENE dumbbell extensional rheology from simulation data.