10 citations · 27 across the 9 of their papers we have counts for
9 papers
Body-Free Simulation of Three-Dimensional Turbulent Cylinder Wakes
Zhicheng Wang, Theo Käufer, Khemraj Shukla +2
We present a body-free simulation framework for three-dimensional turbulent cylinder wakes, in which the upstream cylinder is not explicitly resolved. Instead, the incompressible N…
Turbulence Closure in RANS and Flow Inference around a Cylinder using PINNs and Sparse Experimental Data
Z. Zhang, K. Shukla, Z. Wang +8
Traditional Reynolds-averaged Navier-Stokes (RANS) closures, based on the Boussinesq eddy viscosity hypothesis and calibrated on canonical flows, often yield inaccurate predictions…
Learning Turbulent Flows with Generative Models: Super-resolution, Forecasting, and Sparse Flow Reconstruction
Vivek Oommen, Siavash Khodakarami, Aniruddha Bora +2
Neural operators are promising surrogates for dynamical systems but when trained with standard L2 losses they tend to oversmooth fine-scale turbulent structures. Here, we show that…
Learning and discovering multiple solutions using physics-informed neural networks with random initialization and deep ensemble
Zongren Zou, Zhicheng Wang, George Em Karniadakis
We explore the capability of physics-informed neural networks (PINNs) to discover multiple solutions. Many real-world phenomena governed by nonlinear differential equations (DEs),…
NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elements
Khemraj Shukla, Zongren Zou, Chi Hin Chan +3
Multiphysics problems that are characterized by complex interactions among fluid dynamics, heat transfer, structural mechanics, and electromagnetics, are inherently challenging due…
A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks
Khemraj Shukla, Juan Diego Toscano, Zhicheng Wang +2
Kolmogorov-Arnold Networks (KANs) were recently introduced as an alternative representation model to MLP. Herein, we employ KANs to construct physics-informed machine learning mode…
Data-driven modeling of unsteady flow based on deep operator network
Heming Bai, Zhicheng Wang, Xuesen Chu +2
Time-dependent flow fields are typically generated by a computational fluid dynamics (CFD) method, which is an extremely time-consuming process. However, the latent relationship be…
Operator Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations Characterized by Sharp Solutions
Bin Lin, Zhiping Mao, Zhicheng Wang +1
Physics-informed Neural Networks (PINNs) have been shown as a promising approach for solving both forward and inverse problems of partial differential equations (PDEs). Meanwhile,…
Solution multiplicity and effects of data and eddy viscosity on Navier-Stokes solutions inferred by physics-informed neural networks
Zhicheng Wang, Xuhui Meng, Xiaomo Jiang +2
Physics-informed neural networks (PINNs) have emerged as a new simulation paradigm for fluid flows and are especially effective for inverse and hybrid problems. However, vanilla PI…