Skip to main content
Log in

Targeting and synchronization at tokamak with recurrent artificial neural networks

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In this study, we propose an adaptive recurrent neural networks synchronization of H-mode and edge localized modes that is important for obtaining a long-pulse tokamak without disruption regime. The deterministic part of the plasma behavior should be synchronized with stochastic part by introducing stochastic artificial neural network.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Garabedian PR (1994) A unified theory of tokamaks and stellarators. Commun Pure Appl Math 47(3):281–292

    Article  MathSciNet  MATH  Google Scholar 

  2. Rastovic D (2007) Optimal control of tokamak and stellarator plasma behaviour. Chaos Solitons Fractals 32(2):676–681

    Article  Google Scholar 

  3. Baek J (2010) Adaptive fuzzy bilinear feedback control design for synchronization of TS fuzzy bilinear generalized Lorentz system with uncertain parameters. Phys Lett A. doi:10.1016/j.physleta.2010.02.014

  4. Wang L, Ding W, Chen D (2010) Synchronization schemes of a class of fuzzy cellular neural networks based on adaptive control. Phys Lett A. doi:10.1016/j.physleta.2010.01.029

  5. Rastovic D (1999) Fuzzy simulation of spatiotemporal behavior. Stabil Contr Theory Appl 2(1–2):53–58

    Google Scholar 

  6. Jaynes ET (1957) Information theory and statistical mechanics. Phys Rev 106(4):620–630

    Article  MathSciNet  MATH  Google Scholar 

  7. Rodder W (2000) Conditional logic and the principle of entropy. Artif Intell 117:83–106

    Article  MathSciNet  Google Scholar 

  8. Rastovic D (2003) Infinite fuzzy logic controller and maximum entropy principle. InterStat(Virginia)

  9. Rastovic D (1999) Elastic fuzzy logic controllers in the space L¹[I]. Development and practice of artificial intelligence techniques, IAAMSAD, Durban, pp 267–268

    Google Scholar 

  10. Rastovic D (1993) Compensators for contractive systems. Cybernetica 36(1):11–15

    MATH  Google Scholar 

  11. Tino P, Cernanski M, Benuskova L (2004) Markovian architectural bias of recurrent neural networks. IEEE Trans Neural Netw 15(1):6–15

    Article  Google Scholar 

  12. Rastovic D (2009) Fuzzy scaling and stability of tokamaks. J Fusion Energy 28(1):101–106

    Article  MathSciNet  Google Scholar 

  13. Rastovic D (2008) Analytical description of long–pulse tokamaks. J Fusion Energy 27(4):285–291

    Article  Google Scholar 

  14. Unterberg EA, Schmitz O, Evans TE et al (2010) The effects of an open and closed diverter on particle exhaust during edge-localized mode suppression by resonant magnetic perturbations in DIII-D. Nucl Fusion 50:034011–034020

    Article  Google Scholar 

  15. Katsuro-Hopkins O, Sabbagh SA, Bialek JM et al (2010) Equilibrium and global MHD stability study of KSTAR high beta plasmas under passive and active mode control. Nucl Fusion 50:025019–025028

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Danilo Rastovic.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Rastovic, D. Targeting and synchronization at tokamak with recurrent artificial neural networks. Neural Comput & Applic 21, 1065–1069 (2012). https://doi.org/10.1007/s00521-011-0527-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-011-0527-4

Keywords

Navigation