Skip to main content
Erschienen in:

19.07.2022 | Original Article

Transfer physics informed neural network: a new framework for distributed physics informed neural networks via parameter sharing

verfasst von: Sreehari Manikkan, Balaji Srinivasan

Erschienen in: Engineering with Computers | Ausgabe 4/2023

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

We introduce Transfer Physics Informed Neural Network (TPINN), a neural network-based approach for solving forward and inverse problems in nonlinear partial differential equations (PDEs). In TPINN, one or more layers of physics informed neural network (PINN) corresponding to each non-overlapping subdomains are changed using a unique set of parameters for each PINN. The remaining layers of individual PINNs are the same through parameter sharing. The subdomains can be those obtained by partitioning the global computational domain or subdomains part of the problem definition, which adds to the total computational domain. Solutions from different subdomains are connected while training using problem-specific interface conditions incorporated into the loss function. The proposed method handles forward and inverse problems where PDE formulation changes or when there is a discontinuity in PDE parameters across different subdomains efficiently. Parameter sharing reduces parameter space dimension, memory requirements, computational burden and increases accuracy. The efficacy of the proposed approach is demonstrated by solving various forward and inverse problems, including classical benchmark problems and problems involving parameter heterogeneity from the heat transfer domain. In inverse parameter estimation problems, statistical analysis of estimated parameters is performed by solving the problem independently six times. Noise analysis by varying the noise level in the input data is performed for all inverse problems.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Zurück zum Zitat Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105 Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
42.
Zurück zum Zitat Marchi CH, Suero R, Araki LK (2009) The lid-driven square cavity flow: numerical solution with a 1024 x 1024 grid. J Braz Soc Mech Sci Eng 31(3):186–198CrossRef Marchi CH, Suero R, Araki LK (2009) The lid-driven square cavity flow: numerical solution with a 1024 x 1024 grid. J Braz Soc Mech Sci Eng 31(3):186–198CrossRef
48.
Zurück zum Zitat Kraft D (1988) A software package for sequential quadratic programming. Technical Report DFVLR-FB 88-28 Kraft D (1988) A software package for sequential quadratic programming. Technical Report DFVLR-FB 88-28
49.
Zurück zum Zitat Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, et al. (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467 Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, et al. (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv:​1603.​04467
55.
Zurück zum Zitat Dong S, Li Z (2020) Local extreme learning machines and domain decomposition for solving linear and nonlinear partial differential equations. arXiv:2012.02895 Dong S, Li Z (2020) Local extreme learning machines and domain decomposition for solving linear and nonlinear partial differential equations. arXiv:​2012.​02895
57.
Zurück zum Zitat Yan CA, Vescovini R, Dozio L (2022) A framework based on physics-informed neural networks and extreme learning for the analysis of composite structures. Comput struct 265:106761. 10.1016/j.compstruc.2022.106761 Yan CA, Vescovini R, Dozio L (2022) A framework based on physics-informed neural networks and extreme learning for the analysis of composite structures. Comput struct 265:106761. 10.1016/j.compstruc.2022.106761
59.
Zurück zum Zitat Wang S, Teng Y, Perdikaris P (2020) Understanding and mitigating gradient pathologies in physics-informed neural networks. arXiv:2001.04536 Wang S, Teng Y, Perdikaris P (2020) Understanding and mitigating gradient pathologies in physics-informed neural networks. arXiv:​2001.​04536
61.
Zurück zum Zitat Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. Aistats 9:249–256 Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. Aistats 9:249–256
62.
Zurück zum Zitat Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Reading Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Reading
Metadaten
Titel
Transfer physics informed neural network: a new framework for distributed physics informed neural networks via parameter sharing
verfasst von
Sreehari Manikkan
Balaji Srinivasan
Publikationsdatum
19.07.2022
Verlag
Springer London
Erschienen in
Engineering with Computers / Ausgabe 4/2023
Print ISSN: 0177-0667
Elektronische ISSN: 1435-5663
DOI
https://doi.org/10.1007/s00366-022-01703-9