000885828 001__ 885828
000885828 005__ 20230215201830.0
000885828 020__ $$a978-3-030-59850-1
000885828 020__ $$a978-3-030-59851-8 (electronic)
000885828 0247_ $$2doi$$a10.1007/978-3-030-59851-8_6
000885828 0247_ $$2Handle$$a2128/25963
000885828 0247_ $$2altmetric$$aaltmetric:92800616
000885828 037__ $$aFZJ-2020-04119
000885828 041__ $$aEnglish
000885828 1001_ $$0P:(DE-Juel1)177985$$aRüttgers, Mario$$b0$$eCorresponding author
000885828 1112_ $$aISC High Performance 2020$$cFrankfurt$$d2020-06-22 - 2020-06-25$$gISC 2020$$wGermany
000885828 245__ $$aPrediction of Acoustic Fields Using a Lattice-Boltzmann Method and Deep Learning
000885828 260__ $$aCham$$bSpringer$$c2020
000885828 29510 $$aHigh Performance Computing. ISC High Performance 2020. Lecture Notes in Computer Science
000885828 300__ $$a81-101
000885828 3367_ $$2ORCID$$aCONFERENCE_PAPER
000885828 3367_ $$033$$2EndNote$$aConference Paper
000885828 3367_ $$2BibTeX$$aINPROCEEDINGS
000885828 3367_ $$2DRIVER$$aconferenceObject
000885828 3367_ $$2DataCite$$aOutput Types/Conference Paper
000885828 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1676461485_10243
000885828 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000885828 4900_ $$aLecture Notes in Computer Science$$v12321
000885828 520__ $$aUsing traditional computational fluid dynamics and aeroacoustics methods, the accurate simulation of aeroacoustic sources requires high compute resources to resolve all necessary physical phenomena. In contrast, once trained, artificial neural networks such as deep encoder-decoder convolutional networks allow to predict aeroacoustics at lower cost and, depending on the quality of the employed network, also at high accuracy. The architecture for such a neural network is developed to predict the sound pressure level in a 2D square domain. It is trained by numerical results from up to 20,000 GPU-based lattice-Boltzmann simulations that include randomly distributed rectangular and circular objects, and monopole sources. Types of boundary conditions, the monopole locations, and cell distances for objects and monopoles serve as input to the network. Parameters are studied to tune the predictions and to increase their accuracy. The complexity of the setup is successively increased along three cases and the impact of the number of feature maps, the type of loss function, and the number of training data on the prediction accuracy is investigated. An optimal choice of the parameters leads to network-predicted results that are in good agreement with the simulated findings. This is corroborated by negligible differences of the sound pressure level between the simulated and the network-predicted results along characteristic lines and by small mean errors.
000885828 536__ $$0G:(DE-HGF)POF3-511$$a511 - Computational Science and Mathematical Methods (POF3-511)$$cPOF3-511$$fPOF III$$x0
000885828 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x1
000885828 536__ $$0G:(DE-Juel1)PHD-NO-GRANT-20170405$$aPhD no Grant - Doktorand ohne besondere Förderung (PHD-NO-GRANT-20170405)$$cPHD-NO-GRANT-20170405$$x2
000885828 588__ $$aDataset connected to CrossRef Book Series, Journals: juser.fz-juelich.de
000885828 7001_ $$0P:(DE-Juel1)176474$$aKoh, Seong-Ryong$$b1
000885828 7001_ $$0P:(DE-Juel1)158080$$aJitsev, Jenia$$b2$$ufzj
000885828 7001_ $$0P:(DE-HGF)0$$aSchröder, Wolfgang$$b3
000885828 7001_ $$0P:(DE-Juel1)165948$$aLintermann, Andreas$$b4
000885828 773__ $$a10.1007/978-3-030-59851-8_6$$v12321
000885828 8564_ $$uhttps://juser.fz-juelich.de/record/885828/files/High%20Performance%20Computing%2C%20Proceedings%20of%20the%2035th%20International%20Conference%2C%20ISC%20High%20Performance%202020%20-%202020%20-%20Prediction%20of%20Acoustic.pdf$$yOpenAccess
000885828 8564_ $$uhttps://juser.fz-juelich.de/record/885828/files/High%20Performance%20Computing%2C%20Proceedings%20of%20the%2035th%20International%20Conference%2C%20ISC%20High%20Performance%202020%20-%202020%20-%20Prediction%20of%20Acoustic.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000885828 909CO $$ooai:juser.fz-juelich.de:885828$$popenaire$$pVDB$$popen_access$$pdnbdelivery$$pdriver
000885828 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177985$$aForschungszentrum Jülich$$b0$$kFZJ
000885828 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176474$$aForschungszentrum Jülich$$b1$$kFZJ
000885828 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)158080$$aForschungszentrum Jülich$$b2$$kFZJ
000885828 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b3$$kRWTH
000885828 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165948$$aForschungszentrum Jülich$$b4$$kFZJ
000885828 9131_ $$0G:(DE-HGF)POF3-511$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vComputational Science and Mathematical Methods$$x0
000885828 9131_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x1
000885828 9141_ $$y2020
000885828 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000885828 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000885828 920__ $$lyes
000885828 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000885828 980__ $$acontrib
000885828 980__ $$aVDB
000885828 980__ $$acontb
000885828 980__ $$aI:(DE-Juel1)JSC-20090406
000885828 980__ $$aUNRESTRICTED
000885828 9801_ $$aFullTexts