Journal of Physics & Astronomy

Open Access Open Access  Restricted Access Subscription Access

Investigation of Stabilities and Instabilities at Tokamak Plasma Behaviour and Machine Learning with Big Data


Affiliations
1 Control Systems Group, Cetingradska, 10110 Zagreb, Croatia
 

We investigate the problem of stability and instability at tokamak plasma behaviour. Generally, Jaynes maximum entropy method and Bayesian decision can be applied for recognizing the shape of the plasma. In the case of the power law behaviour and the instabilities of plasma we introduce a new method. The maximization of mathematical expectations for events and fuzzy entropy is used for applications of fuzzy Bayesian neural networks for optimization and simulation without assumption on recurrence. In this case, it is possible to consider also the non-Gibbsian probability distribution functions with the power law case. The new calibration method for the non-equilibrium systems has been given.

Keywords

Stability, Instability, Tokamak, Bayesian Learning.
User
Notifications
Font Size

  • Strait EJ. Magnetic control of magnetohydrodynamic instabilities in tokamaks. Phys Plasmas. 2015;22:21803.

  • Cessac B, Blanchard PH, Kruger T, et al. Self-organized criticality and thermodynamic formalism. Jrl of Stat Phys. 2004;115:1283-326.

  • Wookey DS, Konidaris GD. Regularized feature selection in reinforcement learning. Mach Learn. 2015;100:655-76.

  • Sen AK, Nagashima M, Longman RW. Optimal control of Tokamak resistive wall modes in the presence of noise. Phys Plasmas. 2003;10:4350.

  • Rastovic D. Fuzzy scaling and stability of tokamaks. J Fusion Energy. 2009;28:101-6.

  • Beresnyak A. Asymmetric diffusion of magnetic field lines in turbulence. Phys Scr. 2014;89:118001.

  • Garabedian PR. A unified theory of tokamaks and stellarators. Comm Pure Appl Math. 1994;47:281-92.

  • Mouhot C, Villani C. Landau damping. J Math Phys. 2010;51:015204.

  • Rastovic D. Targeting and synchronization of tokamak with recurrent artificial neural networks. J Neural Comp & Appl. 2012;21:1065-69.

  • Rastovic D. On stochastic control of tokamak and artificial intelligence. J Fusion Energy. 2007;26:337-42.

  • Rastovic D. Feedback stabilization of some classes of nonlinear transport systems. Rend Circ Mat Palermo. 2002; 51:325-32.

  • Rastovic D. A note on stability properties of integrated semigroups. Acta Math Inf Univ. Ostraviensis. 1995;3:61-65.

  • Kaufmann A. Introduction to the Theory of Fuzzy Subsets. Academic Press Inc. New York. 1975.

  • Zheng P. Fully implicit iterative solving method for the Fokker-Planck equation in tokamak plasmas. Plasma Sci Technol. 2014;16:1000-9.

  • Biau G, Cerou F, Guyader A. New insights into approximate Bayesian computation. Annal Inst Henri Poincare. 2015;51:376-403.

  • Soria-Olivas E. BELM: Bayesian Extreme Learning Machine. IEEE Trans. Neural Networks. 2011;22:505-10.

  • Rastovic D. From non-Markovian processes to Stochastic real time control for Tokamak plasma turbulence via artificial intelligence techniques. J Fusion Energy. 2015;34:207-15.

  • Morabito FC. Equilibrium parameters recovery for experimental data in ASDEX upgrade elongated plasmas, Neural Networks. Proc IEEE Int Conf. 1995;27.

  • Rastovic D. Infinite fuzzy logic controller and maximum entropy principle. InterStat. Virginia. 2003.

  • Ambrosino G. Plasma vertical stabilization in the ITER tokamak via constrained static output feedback. IEEEE Trans Control Systems Technology. 2011;19:376-89.

  • Lister JB, Schnurrenberger H. Fast non-linear extraction of plasma equilibrium parameters using a neural network mapping. Nucl Fusion. 1991;31:1291-1300.

  • Dong Li, Yi Liu, Svensson J, et al. Bayesian soft x-ray tomography and MHD mode analysis on HL-2A. Nucl Fusion. 2016;56:036012.

  • Rastovic D. Approach with different entropies to the problem of plasma confinement. Journal of Physics & Astronomy. 2016;4:1-5.

  • Rastovic D. Physics electronics and entropies for plasma confinement. Journal of Physics & Astronomy. 2013;2:75-80.

  • Rastovic D. Tokamak design as one sustainable system. Neural Network World. 2011;6:493-504.


Abstract Views: 272

PDF Views: 1




  • Investigation of Stabilities and Instabilities at Tokamak Plasma Behaviour and Machine Learning with Big Data

Abstract Views: 272  |  PDF Views: 1

Authors

D. Rastovic
Control Systems Group, Cetingradska, 10110 Zagreb, Croatia

Abstract


We investigate the problem of stability and instability at tokamak plasma behaviour. Generally, Jaynes maximum entropy method and Bayesian decision can be applied for recognizing the shape of the plasma. In the case of the power law behaviour and the instabilities of plasma we introduce a new method. The maximization of mathematical expectations for events and fuzzy entropy is used for applications of fuzzy Bayesian neural networks for optimization and simulation without assumption on recurrence. In this case, it is possible to consider also the non-Gibbsian probability distribution functions with the power law case. The new calibration method for the non-equilibrium systems has been given.

Keywords


Stability, Instability, Tokamak, Bayesian Learning.

References