Imperial College London
Portrait Picture

Prof Francesco Montomoli

Faculty of Engineering, Department of Aeronautics

Professor in Computational Aerodynamics
 
 
 
//

Contact

 

+44 (0)20 7594 5151f.montomoli Website

 
 
//

Location

 

215City and Guilds BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Gaymann:2019:10.1038/s41598-019-51111-1,
author = {Gaymann, A and Montomoli, F},
doi = {10.1038/s41598-019-51111-1},
journal = {Scientific Reports},
pages = {1--16},
title = {Deep Neural Network and Monte Carlo Tree Search applied to Fluid-Structure Topology Optimization},
url = {http://dx.doi.org/10.1038/s41598-019-51111-1},
volume = {9},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - This paper shows the application of Deep Neural Network algorithms for Fluid-Structure Topology Optimization. The strategy offered is a new concept which can be added to the current process used to study Topology Optimization with Cellular Automata, Adjoint and Level-Set methods. The design space is described by a computational grid where every cell can be in two states: fluid or solid. The system does not require human intervention and learns through an algorithm based on Deep Neural Network and Monte Carlo Tree Search. In this work the objective function for the optimization is an incompressible fluid solver but the overall optimization process is independent from the solver. The test case used is a standard duct with back facing step where the optimizer aims at minimizing the pressure losses between inlet and outlet. The results obtained with the proposed approach are compared to the solution via a classical adjoint topology optimization code.
AU  - Gaymann,A
AU  - Montomoli,F
DO  - 10.1038/s41598-019-51111-1
EP  - 16
PY  - 2019///
SN  - 2045-2322
SP  - 1
TI  - Deep Neural Network and Monte Carlo Tree Search applied to Fluid-Structure Topology Optimization
T2  - Scientific Reports
UR  - http://dx.doi.org/10.1038/s41598-019-51111-1
UR  - https://www.nature.com/articles/s41598-019-51111-1
UR  - http://hdl.handle.net/10044/1/73392
VL  - 9
ER  -
Download