Automatic identification of tokamak plasma confinement states (L-mode, ELM-free H-mode, and ELMy H-mode) with multi-task learning neural network.
Saved in:
| Title: | Automatic identification of tokamak plasma confinement states (L-mode, ELM-free H-mode, and ELMy H-mode) with multi-task learning neural network. |
|---|---|
| Authors: | Deng, Guo-Hong1,2 (AUTHOR), Xie, Peng-Cheng1,2 (AUTHOR), Sun, You-Wen1 (AUTHOR) ywsun@ipp.ac.cn, Wang, Hui-Hui1 (AUTHOR) hhwang@ipp.ac.cn, Xu, Jian3 (AUTHOR), Ma, Qun1 (AUTHOR), Gu, Shuai1 (AUTHOR), Sheng, Hui1 (AUTHOR), Yang, Hua1,2 (AUTHOR), Chen, Gao-Ting4 (AUTHOR) |
| Source: | Nuclear Fusion. Jul2025, Vol. 65 Issue 7, p1-13. 13p. |
| Subjects: | Plasma confinement, H-mode plasma confinement, Machine learning, Artificial neural networks, Tokamaks |
| Abstract: | The identification of plasma confinement states (L-mode, ELM-free H-mode, and ELMy H-mode) is carried out using a multi-task learning neural network (MTL-NN) in EAST. The identification process can be divided into two tasks: identifying the operational modes and detecting the edge localized modes (ELMs). D α and Mirnov coil measurements are selected as features for detecting the ELM. Parameters from scaling laws, which are related to thermal energy confinement time and heating threshold of L–H transition, are selected as features for identifying the operational modes. The data set used for supervised learning is collected from ELM control experiments in EAST. The MTL-NN comprises two task-specific layers and a shared layer. The multi-task learning framework allows for mutual error correction between tasks, resulting in higher accuracy and robustness compared to single-task models. Evaluation results demonstrate that the MTL-NN achieves an accuracy of 96.7% on the test set, representing a 3.6% improvement compared to single-task models. [ABSTRACT FROM AUTHOR] |
| Copyright of Nuclear Fusion is the property of IOP Publishing and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 187906112 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Automatic identification of tokamak plasma confinement states (L-mode, ELM-free H-mode, and ELMy H-mode) with multi-task learning neural network. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Deng%2C+Guo-Hong%22">Deng, Guo-Hong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xie%2C+Peng-Cheng%22">Xie, Peng-Cheng</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+You-Wen%22">Sun, You-Wen</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> ywsun@ipp.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Hui-Hui%22">Wang, Hui-Hui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hhwang@ipp.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Xu%2C+Jian%22">Xu, Jian</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ma%2C+Qun%22">Ma, Qun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gu%2C+Shuai%22">Gu, Shuai</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sheng%2C+Hui%22">Sheng, Hui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yang%2C+Hua%22">Yang, Hua</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Gao-Ting%22">Chen, Gao-Ting</searchLink><relatesTo>4</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Nuclear+Fusion%22">Nuclear Fusion</searchLink>. Jul2025, Vol. 65 Issue 7, p1-13. 13p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Plasma+confinement%22">Plasma confinement</searchLink><br /><searchLink fieldCode="DE" term="%22H-mode+plasma+confinement%22">H-mode plasma confinement</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Tokamaks%22">Tokamaks</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The identification of plasma confinement states (L-mode, ELM-free H-mode, and ELMy H-mode) is carried out using a multi-task learning neural network (MTL-NN) in EAST. The identification process can be divided into two tasks: identifying the operational modes and detecting the edge localized modes (ELMs). D α and Mirnov coil measurements are selected as features for detecting the ELM. Parameters from scaling laws, which are related to thermal energy confinement time and heating threshold of L–H transition, are selected as features for identifying the operational modes. The data set used for supervised learning is collected from ELM control experiments in EAST. The MTL-NN comprises two task-specific layers and a shared layer. The multi-task learning framework allows for mutual error correction between tasks, resulting in higher accuracy and robustness compared to single-task models. Evaluation results demonstrate that the MTL-NN achieves an accuracy of 96.7% on the test set, representing a 3.6% improvement compared to single-task models. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Nuclear Fusion is the property of IOP Publishing and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=187906112 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1088/1741-4326/ade3ed Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 13 StartPage: 1 Subjects: – SubjectFull: Plasma confinement Type: general – SubjectFull: H-mode plasma confinement Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Tokamaks Type: general Titles: – TitleFull: Automatic identification of tokamak plasma confinement states (L-mode, ELM-free H-mode, and ELMy H-mode) with multi-task learning neural network. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Deng, Guo-Hong – PersonEntity: Name: NameFull: Xie, Peng-Cheng – PersonEntity: Name: NameFull: Sun, You-Wen – PersonEntity: Name: NameFull: Wang, Hui-Hui – PersonEntity: Name: NameFull: Xu, Jian – PersonEntity: Name: NameFull: Ma, Qun – PersonEntity: Name: NameFull: Gu, Shuai – PersonEntity: Name: NameFull: Sheng, Hui – PersonEntity: Name: NameFull: Yang, Hua – PersonEntity: Name: NameFull: Chen, Gao-Ting IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 07 Text: Jul2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 00295515 Numbering: – Type: volume Value: 65 – Type: issue Value: 7 Titles: – TitleFull: Nuclear Fusion Type: main |
| ResultId | 1 |
