Machine learning driven interpretation of computational fluid dynamics simulations to develop student intuition

Nathan J. Patterson

doi:10.1002/cae.22216

journal article Mar 03, 2020

Machine learning driven interpretation of computational fluid dynamics simulations to develop student intuition

Nathan J. Patterson

Computer Applications in Engineering Education Vol. 28 No. 3 pp. 490-496 · Wiley

View at Publisher Save 10.1002/cae.22216

Abstract

AbstractEmployers need engineers capable of leveraging CFD simulations to make intelligent design decisions, but undergraduate computational fluid dynamics (CFD) courses are not adequately preparing students for this type of work. CFD courses commonly familiarize students with topics, such as method derivation, domain creation, boundary conditions, mesh convergence, turbulence models, numerical convergence, and error analysis. This approach is an effective way to teach novices how CFD software works and how to prepare CFD analyses. However, it neglects development of higher level CFD skills and intuition important to engineering analysis and design, deferring this task to future study and training. This paper introduces the “Machine Learning Driven Interpretation of Fluid Dynamics Simulations to Develop Student Intuition” (MIFoS) software, a program designed to help CFD novices develop the high‐level skills and intuition that employers need in their engineers. A data‐driven approach was used to create the MIFoS software, which allows the submission of arbitrary geometries, automates an external flow simulation, and returns expert‐level graphical interpretation of simulation data. MIFoS's automated CFD simulation and feedback space allows novices to experiment with expert‐level suggestions on their own designs, enabling the skill and intuition development typically gained through years of study, practice, and expert guidance.

Topics

No keywords indexed for this article. Browse by subject →

References

37

[1]

(2019)

[2]

ANSYS FLUENT User's Guide.ANSYS FLUENT 12.0 user's guide—26.13.1 monitoring residuals May 22 2019 available athttp://www.afs.enea.it/project/neptunius/docs/fluent/html/ug/node812.htm

[3]

M.AzabandC.Ollivier Gooch High order aerodynamic optimization using new hybrid sequential quadratic programing‐particle swarm intelligence technique. 50th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition. Nashville Tennessee: American Institute of Aeronautics and Astronautics;2012.https://doi.org/10.2514/6.2012‐730 10.2514/6.2012-730

[4]

Baker A. J. "Computational fluid dynamics: A two‐edged sword" ASHRAE J N Y. (1997)

[5]

P.Baquéet al. Geodesic convolutional shape optimization. ArXiv180204016 Cs February 2018 avaialable athttp://arxiv.org/abs/1802.04016

[6]

T. J.Barber The use of advanced simulation tools in capstone design projects. Proceedings of the 6th WSEAS International Conference on Engineering Education. EDUCATION’09. Stevens Point Wisconsin USA: World Scientific and Engineering Academy and Society (WSEAS); 2009:58–63 available athttp://dl.acm.org/citation.cfm?id=1864130.1864146

[7]

10.1016/s0952-1976(98)00009-8

[8]

S.Chidambaramet al. Shape structuralizer: Design fabrication and user‐driven iterative refinement of 3D mesh models. Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems—CHI’19. Glasgow Scotland Uk: ACM Press;2019:1–12.https://doi.org/10.1145/3290605.3300893 10.1145/3290605.3300893

[9]

F.Cholletet al. Keras 2015 available athttps://keras.io

[10]

Chollet F. (2017)

[11]

R. L.Collins Engineering graduate preparedness for the workplace: Employer assessments of outcome based education.2008 available athttps://search.proquest.com/docview/275863051/abstract/462C8916EBEB4E4EPQ/1

[12]

10.1017/s0022112080000419

[13]

10.2514/2.3189

[14]

The WEKA data mining software

Mark Hall, Eibe Frank, Geoffrey Holmes et al.

ACM SIGKDD Explorations Newsletter 10.1145/1656274.1656278

[15]

O.Hennigh Lat‐Net: Compressing lattice boltzmann flow simulations using deep neural networks. arXiv.org May 2017. Available athttp://arxiv.org/abs/1705.09036

[16]

Hirsch C. (2007)

[17]

Houghton E. L. (2003)

[18]

10.2514/1.c032150

[19]

10.2514/1.j052754

[20]

10.5465/amle.2005.17268566

[21]

B. D.Lutz Into the workplace: Exploring the learning experiences of newcomer engineers during the school‐to‐work transition June2017 available athttps://vtechworks.lib.vt.edu/handle/10919/78276

[22]

J. E.Manzo E. A.Leylek andE.Garcia Drawing insight from nature: A bat wing for morphing aircraft. (2008) no.43321 671‐678.https://doi.org/10.1115/SMASIS2008‐613 10.1115/smasis2008-613

[23]

MATLAB Release (2018)

[24]

10.1017/s0890060416000524

[25]

I.NedyalkovandM.Wosnik Computational fluid dynamics in undergraduate engineering education: A short introductory tutorial to OpenFOAM. (2016) no.50282 V01AT03A017.https://doi.org/10.1115/FEDSM2016‐7747

[26]

10.1007/bf02942594

[27]

T.Parra‐Santoset al. Practical learning on computational fluid dynamics at undergraduate level. (2016) no.50282 V01AT03A001.https://doi.org/10.1115/FEDSM2016‐7542

[28]

Pedregosa F. "Scikit‐learn: machine learning in Python" J. Mach. Learn. Res. (2011)

[29]

Shollenberger K. A. "Computational fluid dynamics (CFD) within undergraduate programs" Computational Fluid Dynamics (CFD) Within Undergraduate Programs (2007)

[30]

10.1016/j.asoc.2017.09.030

[31]

SOLIDWORKS.Waltham MA: Dassault systemes solidworks corporation; 2019 available athttps://www.solidworks.com/

[32]

10.1016/0959-4752(94)90003-5

[33]

J.Tompsonet al. Accelerating Eulerian fluid simulation with convolutional networks Proceedings of the 34th International Conference on Machine Learning Volume 70. ICML’17. JMLR.org;2017:3424–3433 available athttp://dl.acm.org/citation.cfm?id=3305890.3306035

[34]

10.1145/3197517.3201325

[35]

Wenger E. (2014)

[36]

Witten I. H. (2016)

[37]

D. H.WolpertandW. G.Macready No free lunch theorems for search 1995.

Metrics

7

Citations

37

References

Details

Published: Mar 03, 2020
Vol/Issue: 28(3)
Pages: 490-496
License: View

Authors

N

Nathan J. Patterson

Mechanical Engineering Department Milwaukee School of Engineering Milwaukee Wisconsin

Cite This Article

Nathan J. Patterson (2020). Machine learning driven interpretation of computational fluid dynamics simulations to develop student intuition. Computer Applications in Engineering Education, 28(3), 490-496. https://doi.org/10.1002/cae.22216

Machine learning driven interpretation of computational fluid dynamics simulations to develop student intuition

You May Also Like