- author = "Julia Reuter and Manoj Cendrollu and Fabien Evrard and Sanaz Mostaghim and Berend {van Wachem}",
- title = "Towards Improving Simulations of Flows around Spherical Particles Using Genetic Programming",
- booktitle = "2022 IEEE Congress on Evolutionary Computation (CEC)",
- year = "2022",
- editor = "Carlos A. Coello Coello and Sanaz Mostaghim",
- address = "Padua, Italy",
- month = "18-23 " # jul,
- keywords = "genetic algorithms, genetic programming, Computational modeling, Fluid dynamics, Training data, Evolutionary computation, Benchmark testing, Mathematical models, Stokes Flow, Explainability, viscous flow, 2 spheres, Stokeslet, Wendland, NSGA-II, MOGP, multi-layer perceptron, DEAP, pint",
- isbn13 = "978-1-6654-6708-7",
-
URL = "
https://human-competitive.org/sites/default/files/reuter.txt",
-
URL = "
https://human-competitive.org/sites/default/files/paper1.pdf",
-
DOI = "
doi:10.1109/CEC55065.2022.9870301",
- size = "8 pages",
- abstract = "The simulation of particle laden flows is a crucial task in fluid dynamics, requiring high computational cost owing to the complex interactions between numerous particles. Typically, the flow velocity is described with the equations proposed by Stokes. While there is an analytical solution for the Stokes flows around a single spherical particle, the Stokes flows around many particles are still unsolved. In this paper, we study Genetic Programming (GP) for symbolic regressions to explore the potentials of multiobjective GP in recovering analytical expressions for two and, in the future, N particles. We propose a new GP approach containing building blocks to scale up the problem and provide a new benchmark with 22 cases for this application. To identify the strengths and limitations of GP, we generate fully resolved training data from simulations. We compare the results of our algorithm to the superimposition method and a multilayer perceptron as two baseline methods. The results show that GP can find comparable and sometimes better solutions with smaller failure rates than the two baseline methods. In addition, the produced solutions by GP are explainable and certain function patterns inline with physical laws can be identified across the benchmark problems.",
-
notes = "Finalist 2023 HUMIES Also known as
\cite{9870301}
Viscous flow, Re << 1, eg microscopic scale. particle = sphere. Eg two close by droplets of the same size in line. Closed form solution.
DEAP Distributed Evolutionary Algorithms in Python. 'no overfitting' 'The sympy package was used to simplify the equations' 'GP found slight modifications to the superimposition method to generate better results'.",
