Journal of Interfaces, Thin Films, and Low dimensional systems

Simulation of hard X-ray time evolution in the stable region of plasma tokamak by using the NARX-GA hybrid neural network

Document Type : Original Article

Authors

1 Department of Physics, Shoushtar Branch, Islamic Azad University, Shoushtar, Iran

2 Canadian Light Source Inc., University of Saskatchewan, Saskatoon, Saskatchewan, S7N2V3, Canada

3 Department of Basic Sciences, Garmsar Branch, Islamic Azad University, Garmsar, Iran

4 Department of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran

5 Earth Sciences Department, Faculty of Natural Sciences, University of Tabriz, Tabriz, Iran

Abstract

The time evolution of hard X-ray has been simulated using the NARX-GA hybrid neural network in the stable region of the plasma tokamak. Loop voltage and hard X-ray measured by the tokamak diagnostics tools were selected as network inputs. The NARX network has been trained using the Genetic Algorithm (GA) and the time evolution of the hard X-ray up to 500 μs (MSE = 4.13 × 10-5) is accurately simulated. Increasing the confinement time is the particular purpose of applying tokamak to produce energy through fusion. The real-time application of this methodology brings us closer to this goal. Hard X-ray prediction can prevent plasma energy reduction. It can also reduce the severe damage caused by runaway electrons (RE) colliding with the tokamak wall. Early prediction of hard X-ray time evolution is critical in attempting to mitigate the REs potentially dangerous effects.

Keywords

Main Subjects

Article Title [Persian]

شبیه سازی تحول زمانی اشعه ایکس سخت در ناحیه پایدار پلاسمای توکامک با استفاده از شبکه عصبی مصنوعی هیبریدی NARX-GA

Authors [Persian]

  • امیر علوی 1
  • شروین سعادت 2
  • محمد رضا قنبری 3
  • O علوی 4
  • علی کدخدایی 5

1 گروه فیزیک، دانشگاه آزاد اسلامی، واحد شوشتر، شوشتر، ایران

2 شرکت کانادایی چشمه نور، دانشگاه ساسکاتچوان، ساسکاتون، کانادا

3 گروه علوم پایه، دانشگاه آزاد اسلامی، واحد گرمسار، گرمسار، ایران

4 گروه کامپیوتر، دانشکده مهندسی، دانشگاه شهید چمران اهواز، اهواز، ایران

5 گروه زمین شناسی، دانشکده علوم پایه، دانشگاه تبریز، تبریز، ایران

Abstract [Persian]

تکامل زمانی پرتو ایکس سخت با استفاده از شبکه عصبی هیبریدی NARX-GA در ناحیه پایدار توکامک پلاسما شبیه‌سازی شد. ولتاژ حلقه و اشعه ایکس سخت اندازه گیری شده توسط ابزار تشخیصی توکامک به عنوان ورودی شبکه انتخاب شدند. شبکه NARX با استفاده از الگوریتم ژنتیک (GA) آموزش داده شد و به طور دقیق تکامل زمانی پرتو ایکس سخت را تا 500 میکرو ثانیه شبیه‌سازی کرد (MSE = 4.13×10-5). افزایش زمان محصور سازی هدف ویژه ای در استفاده از توکامک برای تولید انرژی از طریق همجوشی می باشد. کاربرد بلادرنگ این روش ما را به این هدف نزدیکتر می کند. پیش‌بینی سخت اشعه ایکس می‌تواند از کاهش انرژی پلاسما جلوگیری کند. همچنین می تواند آسیب شدید ناشی از برخورد الکترون های گریزان (RE) با دیواره توکامک را کاهش دهد. پیش‌بینی تکامل زمانی پرتو ایکس سخت برای کاهش اثرات بالقوه خطرناک الکترون های گریزان امری حیاتی است.

Keywords [Persian]

  • روش شناسی
  • پرتو ایکس سخت
  • الکترون های گریزان
  • شبکه NARX-GA
[1]    B.N. Breizman, N. Boris., et al. "Physics of runaway electrons in tokamaks." Nuclear Fusion, 59 (2019) 083001.
[2]    M. Bakhtiari, et al. "Role of bremsstrahlung radiation in limiting the energy of runaway electrons in tokamaks." Physical review letters, 94 (2005) 215003.
[3]    R.D. Gill, "Generation and loss of runaway electrons following disruptions in JET." Nuclear Fusion, 33 (1993) 1613.
[4]    R.D. Gill, et al. "Direct observations of runaway electrons during disruptions in the JET tokamak." Nuclear Fusion, 40 (2000) 163.
[5]    L. Novotny, et al. "Runaway electron diagnostics using silicon strip detector." Journal of Instrumentation, 15 (2020) C07015.
[6]    A. Dal Molin, et al. "Novel compact hard x-ray spectrometer with MCps counting rate capabilities for runaway electron measurements on DIII-D." Review of Scientific Instruments, 92 (2021) 043517.
[7]    A. Shevelev, et al. "Study of runaway electrons with Hard X-ray spectrometry of tokamak plasmas." AIP Conference Proceedings, 1612 (2014) 125.
[8]    L-G. Eriksson, et al. "Current dynamics during disruptions in large tokamaks." Physical review letters, 92 (2004) 205004.
[9]    S. Mirnov, et al. "MHD stability, operational limits and disruptions." Nuclear Fusion, 39 (1999) 225.
[10]  A. H. Boozer, "Runaway electrons and ITER." Nuclear Fusion, 57 (2017) 056018.
[11]  R.D Gill, et al. "Behaviour of disruption generated runaways in JET." Nuclear fusion, 42 (2002) 1039.
[12]  O. N. Jarvis, et al. "Photoneutron production accompanying plasma disruptions in JET." Nuclear fusion, 28 (1988) 1981.
 [13] V. V. Plyusnin, et al. "Study of runaway electron generation during major disruptions in JET." Nuclear Fusion, 46 (2006) 277.
[14]  J. A. Wesson, et al. "Disruptions in JET." Nuclear Fusion, 29 (1989) 641.
[15]  C. Reux, et al. "Runaway electron beam generation and mitigation during disruptions at JET-ILW." Nuclear Fusion, 55 (2015) 093013.
[16]  R. Nygren, et al. "Runaway electron damage to the Tore Supra Phase III outboard pump limiter." Journal of nuclear materials, 241 (1997) 522.
[17]  A. H. Boozer, "Theory of runaway electrons in ITER: Equations, important parameters, and implications for mitigation." Physics of Plasmas, 22 (2015) 032504.
[18]  M. Lehnen, et al. "Disruptions in ITER and strategies for their control and mitigation." Journal of Nuclear materials, 463 (2015) 39.
[19]  E. M. Hollmann, et al. "Status of research toward the ITER disruption mitigation system." Physics of Plasmas, 22 (2015) 021802.
[20]  M. Lehnen, et al. "Suppression of runaway electrons by resonant magnetic perturbations in TEXTOR disruptions." Physical review letters, 100 (2008) 255003.
[21]  M. Gobbin, et al. "Runaway electron mitigation by applied magnetic perturbations in RFX-mod tokamak plasmas." Nuclear Fusion, 57 (2016) 016014.
[22]  S. Munaretto, et al. "Effect of resonant magnetic perturbations on three dimensional equilibria in the Madison Symmetric Torus reversed-field pinch." Physics of Plasmas, 23 (2016) 056104.
[23]  E. M. Hollmann, et al. "Experiments in DIII-D toward achieving rapid shutdown with runaway electron suppression." Physics of Plasmas, 17 (2010) 056117.
[24]  O. Ficker, et al. "Runaway electron beam stability and decay in COMPASS." Nuclear Fusion, 59 (2019) 096036.
[25]  D. Shiraki, et al. "Dissipation of post-disruption runaway electron plateaus by shattered pellet injection in DIII-D." Nuclear Fusion, 58 (2018) 056006.
[26]  M. R. Ghanbari, et al. "Runaway electron generation decrease during a major disruption by limiter biasing in tokamaks." Radiation Effects and Defects in Solids, 168 (2013) 664.
[27]  A. Alavi, et al. "Prediction of hard x-ray behavior by using the NARX neural network to reduce the destructive effects of runaway electrons in tokamak." Physica Scripta, 96 (2021) 125625.
[28]  Y. Liu, et al. "Toroidal modeling of runaway electron loss due to 3-D fields in DIII-D and COMPASS." Physics of Plasmas, 27 (2020) 102507.
[29]  M. Landreman, et al. "Numerical calculation of the runaway electron distribution function and associated synchrotron emission." Computer Physics Communications, 185 (2014) 847.
[30]  K. Björk, et al. "Kinetic modelling of runaway electron generation in argon-induced disruptions in ASDEX Upgrade." Journal of Plasma Physics, 86 (2020) 855860401.
[31]  S. H. Saadat, et al. "Stochastic modeling of plasma mode forecasting in tokamak." Journal of Plasma Physics, 78 (2012) 99.
[32]  F. Matos, et al. "Classification of tokamak plasma confinement states with convolutional recurrent neural networks." Nuclear Fusion, 60 (2020) 036022.
[33]  R. M. Churchill, et al. "Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic data." Physics of Plasmas, 27 (2020) 062510.
[34]  W. Zheng, et al. "Disruption predictor based on neural network and anomaly detection on J-TEXT." Plasma Physics and Controlled Fusion, 62 (2020) 045012.
[35]  K.L. van de Plassche, et al. "Fast modeling of turbulent transport in fusion plasmas using neural networks." Physics of Plasmas, 27 (2020): 022310.
[36]  B. Yang, et al. "Modeling of the HL-2A plasma vertical displacement control system based on deep learning and its controller design." Plasma Physics and Controlled Fusion, 62 (2020) 075004.
[37]  N. Karayiannis, N.V. Anastasios. Artificial neural networks: learning algorithms, performance evaluation, and applications. Springer Science & Business Media, 209 (1992).
[38]  A. N. James, et al. "Measurements of hard x-ray emission from runaway electrons in DIII-D." Nuclear Fusion, 52 (2011) 013007.
[39]  M.T. Hagan, et al. "An introduction to the use of neural networks in control systems." International Journal of Robust and Nonlinear Control: IFAC‐Affiliated Journal, 12 (2002) 959.
[40]  K. Guo, "Research on location selection model of distribution network with constrained line constraints based on genetic algorithm." Neural Computing and Applications, 32 (2020) 1679.
[41]  Wei, Han, Hua Bao, and Xiulin Ruan. "Genetic algorithm-driven discovery of unexpected thermal conductivity enhancement by disorder." Nano Energy, 71 (2020) 104619.
[42]  M. Jawad, et al. "Genetic algorithm‐based non‐linear auto‐regressive with exogenous inputs neural network short‐term and medium‐term uncertainty modelling and prediction for electrical load and wind speed." The Journal of Engineering, 2018 (2018) 721.
[43]  L. Liu, et al. "Optimizing an ANN model with genetic algorithm (GA) predicting load-settlement behaviours of eco-friendly raft-pile foundation (ERP) system." Engineering with Computers, 36 (2020) 421.
[44]  Y. Zhou, et al. "Hybrid genetic algorithm method for efficient and robust evaluation of remaining useful life of supercapacitors." Applied Energy, 260 (2020) 114169.
[45]  H. Liang, et al. "An improved genetic algorithm optimization fuzzy controller applied to the wellhead back pressure control system." Mechanical Systems and Signal Processing, 142 (2020) 106708.
[46]  A. Al Mamun, et al. "A comprehensive review of the load forecasting techniques using single and hybrid predictive models." IEEE Access, 8 (2020) 134911.
[47]  M. Albadr, Musatafa, et al. "Genetic algorithm based on natural selection theory for optimization problems." Symmetry, 12 (2020) 1758.
[48]  Y. Sun, et al. "Automatically designing CNN architectures using the genetic algorithm for image classification." IEEE transactions on cybernetics, 50 (2020) 3840.
[49]  H. Dreicer, "Electron and ion runaway in a fully ionized gas. I." Physical Review, 115 (1959) 238.
[50]  H. Dreicer, "Electron and ion runaway in a fully ionized gas. II." Physical review, 117 (1960) 329.
[51]  Y. Sokolov, ''Multiplication''of accelerated electrons in a tokamak." JETP Lett., 29 (1979).
[52]  R. Jayakumar, et al, "Collisional avalanche exponentiation of runaway electrons in electrified plasmas." Physics Letters A, 172 (1993) 447.
[53]  M. N. Rosenbluth, and S. V. Putvinski. "Theory for avalanche of runaway electrons in tokamaks." Nuclear fusion, 37 (1997) 1355.
[54]  M. Gobbin, et al. "Runaway electron mitigation by 3D fields in the ASDEX-Upgrade experiment." Plasma Physics and Controlled Fusion, 60 (2017) 014036.
[55]  A. Lvovskiy, et al. "The role of kinetic instabilities in formation of the runaway electron current after argon injection in DIII-D." Plasma Physics and Controlled Fusion, 60 (2018) 124003.
[56]  V. V. Plyusnin, et al. "Hard X-ray Bremsstrahlung of relativistic Runaway Electrons in JET." Journal of Instrumentation, 14 (2019) C09042.
[57]  D. Graupe, Principles of artificial neural networks. World Scientific, 7 (2013).
[58]  Z. Y. Chen, et al. "Investigation of the effect of electron cyclotron heating on runaway generation in the KSTAR tokamak." Physics Letters A, 375 (2011) 2569.
Journal of Interfaces, Thin Films, and Low dimensional systems
Volume 5, Issue 2
February 2022
Pages 537-545