{"title":"神经网络用于托卡马克等离子体简化模型中的湍流传输预测","authors":"L M Pomârjanschi","doi":"10.1088/1361-6587/ad3eb0","DOIUrl":null,"url":null,"abstract":"The method of using neural networks (NNs) for turbulent transport prediction in a simplified model of tokamak plasmas is explored. The NNs are trained on a database obtained via test-particle simulations of a transport model in the slab-geometrical approximation. It consists of a five-dimensional input of transport model parameters, and the radial diffusion coefficient as output. The NNs display fast and efficient convergence, a validation error below 2 , and predictions in excellent agreement with the real data, obtained orders of magnitude faster than test-particle simulations. In comparison to a spline interpolation, the NN outperforms, exhibiting better predicting and extrapolating capabilities. We demonstrate the preciseness and efficiency of this method as a proof-of-concept, establishing a promising approach for future, more comprehensive research on the use of NNs for transport predictions in tokamak plasmas.","PeriodicalId":20239,"journal":{"name":"Plasma Physics and Controlled Fusion","volume":"16 1","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Neural networks for turbulent transport prediction in a simplified model of tokamak plasmas\",\"authors\":\"L M Pomârjanschi\",\"doi\":\"10.1088/1361-6587/ad3eb0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The method of using neural networks (NNs) for turbulent transport prediction in a simplified model of tokamak plasmas is explored. The NNs are trained on a database obtained via test-particle simulations of a transport model in the slab-geometrical approximation. It consists of a five-dimensional input of transport model parameters, and the radial diffusion coefficient as output. The NNs display fast and efficient convergence, a validation error below 2 , and predictions in excellent agreement with the real data, obtained orders of magnitude faster than test-particle simulations. In comparison to a spline interpolation, the NN outperforms, exhibiting better predicting and extrapolating capabilities. We demonstrate the preciseness and efficiency of this method as a proof-of-concept, establishing a promising approach for future, more comprehensive research on the use of NNs for transport predictions in tokamak plasmas.\",\"PeriodicalId\":20239,\"journal\":{\"name\":\"Plasma Physics and Controlled Fusion\",\"volume\":\"16 1\",\"pages\":\"\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2024-04-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Plasma Physics and Controlled Fusion\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1088/1361-6587/ad3eb0\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PHYSICS, FLUIDS & PLASMAS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Plasma Physics and Controlled Fusion","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1088/1361-6587/ad3eb0","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, FLUIDS & PLASMAS","Score":null,"Total":0}
引用次数: 0
摘要
本文探讨了在托卡马克等离子体简化模型中使用神经网络(NN)进行湍流输运预测的方法。神经网络是在一个数据库上进行训练的,该数据库是通过对板状几何近似的输运模型进行测试粒子模拟而获得的。它由五维输运模型参数输入和径向扩散系数输出组成。网络显示出快速高效的收敛性,验证误差低于 2,预测结果与实际数据非常吻合,比测试粒子模拟快了几个数量级。与样条插值相比,NN 的性能更优越,具有更好的预测和外推能力。作为概念验证,我们证明了这种方法的精确性和高效性,为今后更全面地研究如何使用 NN 进行托卡马克等离子体中的输运预测提供了一种可行的方法。
Neural networks for turbulent transport prediction in a simplified model of tokamak plasmas
The method of using neural networks (NNs) for turbulent transport prediction in a simplified model of tokamak plasmas is explored. The NNs are trained on a database obtained via test-particle simulations of a transport model in the slab-geometrical approximation. It consists of a five-dimensional input of transport model parameters, and the radial diffusion coefficient as output. The NNs display fast and efficient convergence, a validation error below 2 , and predictions in excellent agreement with the real data, obtained orders of magnitude faster than test-particle simulations. In comparison to a spline interpolation, the NN outperforms, exhibiting better predicting and extrapolating capabilities. We demonstrate the preciseness and efficiency of this method as a proof-of-concept, establishing a promising approach for future, more comprehensive research on the use of NNs for transport predictions in tokamak plasmas.
期刊介绍:
Plasma Physics and Controlled Fusion covers all aspects of the physics of hot, highly ionised plasmas. This includes results of current experimental and theoretical research on all aspects of the physics of high-temperature plasmas and of controlled nuclear fusion, including the basic phenomena in highly-ionised gases in the laboratory, in the ionosphere and in space, in magnetic-confinement and inertial-confinement fusion as well as related diagnostic methods.
Papers with a technological emphasis, for example in such topics as plasma control, fusion technology and diagnostics, are welcomed when the plasma physics is an integral part of the paper or when the technology is unique to plasma applications or new to the field of plasma physics. Papers on dusty plasma physics are welcome when there is a clear relevance to fusion.