A deep learning -- genetic algorithm approach for aerodynamic inverse design via optimization of pressure distribution

Numerical optimization and variational techniques (65K10) General aerodynamics and subsonic flows (76G25) Flow control and optimization for compressible fluids and gas dynamics (76N25)

Cites Work

On consistency of minimum description length model selection for piecewise autoregressions
Constraints handling in Nash/adjoint optimization methods for multi-objective aerodynamic design
Stabilisation of discrete steady adjoint solvers
Occam's razor
Inverse design in subsonic and transonic external flow regimes using elastic surface algorithm
Determination of desired geometry by a novel extension of ball spine algorithm inverse method to conjugate heat transfer problems
Multilayer feedforward networks are universal approximators
Bayesian methods for neural networks and related models
Aerodynamic shape optimization of aircraft components using an advanced multi-objective evolutionary approach
Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization
Projection-based model reduction of dynamical systems using space-time subspace and machine learning
Monte Carlo fPINNs: deep learning method for forward and inverse problems involving high dimensional fractional partial differential equations
Inverse design of shell-based mechanical metamaterial with customized loading curves based on machine learning and genetic algorithm
Solving inverse problems in stochastic models using deep neural networks and adversarial training
Machine Learning for Fluid Mechanics
Inverse shape design method based on pressure and shear stress for separated flow via Elastic Surface Algorithm
Bézier curves and surfaces with shape parameters
Reynolds averaged turbulence modelling using deep neural networks with embedded invariance