Wang Qi's repositories
CFDPython
A sequence of Jupyter notebooks featuring the "12 Steps to Navier-Stokes" http://lorenabarba.com/
deeponet
Learning nonlinear operators via DeepONet
dominant-balance
Methods and code for J. L. Callaham, J. N. Kutz, B. W. Brunton, and S. L. Brunton (2020)
drl_shape_optimization
Deep reinforcement learning to perform shape optimization
engauge-digitizer
Extracts data points from images of graphs
fenics-DRL
Repository from the paper https://arxiv.org/abs/1908.04127, to train Deep Reinforcement Learning in Fluid Mechanics Setup.
FluTO
Graded Multiscale Fluid Topology Optimization using Neural Networks
fourier_neural_operator
Use Fourier transform to learn operators in differential equations.
graph-pde
Using graph network to solve PDEs
gym
A toolkit for developing and comparing reinforcement learning algorithms.
jax-cfd
Computational Fluid Dynamics in JAX
learn2learn
A PyTorch Library for Meta-learning Research
leedeeprl-notes
李宏毅《深度强化学习》笔记，在线阅读地址：https://datawhalechina.github.io/leedeeprl-notes/
machine-learning-applied-to-cfd
Examples of how to use machine learning algorithms in computational fluid dynamics.
morphogenesis-resources
Comprehensive list of resources on the topic of digital morphogenesis (the creation of form through code). Includes links to major articles, code repos, creative projects, books, software, and more.
MTO
Parallel solver for thermal-fluid-structural topology optimization on structured grids.
MTO_new
New parallel solver on unstructured grids！
NeuralPDE.jl
Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
pytorch-maml-rl
Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch
Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions
Solutions of Reinforcement Learning, An Introduction
smarties
Lightweight and scalable framework for Reinforcement Learning
T-Blade3
T-Blade3 VERSION 1.2: T-Blade3 is a general parametric 3D blade geometry builder. The tool can create a variety of 3D blade geometries based on few basic parameters and limited interaction with a CAD system. The geometric and aerodynamic parameters are used to create 2D airfoils and these airfoils are stacked on the desired stacking axis. The tool generates a specified number of 2D blade sections in a 3D Cartesian coordinate system. The geometry modeler can also be used for generating 3D blades with special features like bent tip, split tip and other concepts, which can be explored with minimum changes to the blade geometry. The use of control points for the definition of splines makes it easy to modify the blade shapes quickly and smoothly to obtain the desired blade model. The second derivative of the mean-line (related to the curvature) is controlled using B-splines to create the airfoils. This is analytically integrated twice to obtain the mean-line. A smooth thickness distribution is then added to the airfoil with two options either the Wennerstrom distribution or a quartic B-spline thickness distribution. B-splines have also been implemented to achieve customized airfoil leading and trailing edges.
tensorforce
Tensorforce: a TensorFlow library for applied reinforcement learning