We present an ultrafast neural network (NN) model, QLKNN, which predicts core tokamak transport heat and particle fluxes. QLKNN is a surrogate model based on a database of 300 million flux calculations of the quasilinear gyrokinetic transport model QuaLiKiz. The database covers a wide range of realistic tokamak core parameters. Physical features such as the existence of a critical gradient for the onset of turbulent transport were integrated into the neural network training methodology. We have coupled QLKNN to the tokamak modelling framework JINTRAC and rapid control-oriented tokamak transport solver RAPTOR. The coupled frameworks are demonstrated and validated through application to three JET shots covering a representative spread of H-mode operating space, predicting turbulent transport of energy and particles in the plasma core. JINTRAC-QLKNN and RAPTOR-QLKNN are able to accurately reproduce JINTRAC-QuaLiKiz T i,e and n e profiles, but 3 to 5 orders of magnitude faster. Simulations which take hours are reduced down to only a few tens of seconds. The discrepancy in the final source-driven predicted profiles between QLKNN and QuaLiKiz is on the order 1%-15%. Also the dynamic behaviour was well captured by QLKNN, with differences of only 4%-10% compared to JINTRAC-QuaLiKiz observed at mid-radius, for a study of density buildup following the L-H transition. Deployment of neural network surrogate models in multi-physics integrated tokamak modelling is a promising route towards enabling accurate and fast tokamak scenario optimization, Uncertainty Quantification, and control applications.

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

RFXmod is a Reversed Field Pinch device that allowed performing experiments in regimes with a plasma current up to 2 MA, thanks to its MHD active control system. Experiments have shown that improved plasma performances are obtained when in the resonant part of the m = 1 spectrum one dominant tearing mode is much higher than the other secondary ones (quasi single helicity states). Tearing modes play a crucial role in determining energy and particle transport. Based on the present understanding of the interplay between passive conductive boundaries and tearing modes in an RFP, an upgrade of RFXmod machine assembly has been designed, dubbed RFXmod2, and it is now being implemented. The highly resistive Inconel vessel will be removed, graphite tiles will be attached to the copper stabilizing shell and the stainless steel support structure will be modified in order to be vacuum tight. In RFXmod2, the shellplasma proximity decreases from b/a = 1.11 to b/a = 1.04 and copper, instead of Inconel, will be the continuous conducting structure nearest to the plasma. MHD nonlinear simulations show that secondary tearing modes amplitude and the edge bulging due to their phase locking will decrease; moreover the plasma current threshold for tearing modes wall locking will also significantly increase.

No abstract

A novel partial element equivalent circuit (PEEC) formulation for solving full-Maxwell’s equations, with piecewise homogeneous\ud and linear conductive, dielectric, and magnetic media, is presented. It is based on the cell method which by using integral variables\ud as problem unknowns is naturally suited for developing circuit-like approaches such as PEEC. Volume meshing allows complex\ud 3-D geometries, with electric and magnetic materials, to be discretized. Electromagnetic couplings in the air domain are modeled\ud by integral equations