Cross-tokamak deployment study of plasma disruption predictors based on convolutional autoencoder
文献类型：期刊论文
| 作者 | Ai, X. K.1; Zheng, W.1; Zhang, M.1 ; Ding, Y. H.1; Chen, D. L.2; Chen, Z. Y.1; Shen, C. S.1; Guo, B. H.2; Wang, N. C.1; Yang, Z. J.1
|
| 刊名 | PLASMA PHYSICS AND CONTROLLED FUSION
 |
| 出版日期 | 2024-08-01 |
| 卷号 | 66 |
| 关键词 | disruption prediction deep learning anomaly detection cross-tokamak transfer learning |
| ISSN号 | 0741-3335 |
| DOI | 10.1088/1361-6587/ad5934 |
| 通讯作者 | Zheng, W.(zhengwei@hust.edu.cn) |
| 英文摘要 | In the initial stages of operation for future tokamak, facing limited data availability, deploying data-driven disruption predictors requires optimal performance with minimal use of new device data. This paper studies the issue of data utilization in data-driven disruption predictor during cross tokamak deployment. Current predictors primarily employ supervised learning methods and require a large number of disruption and non-disruption shots for training. However, the scarcity and high cost of obtaining disruption shots for future tokamaks result in imbalanced training datasets, reducing the performance of supervised learning predictors. To solve this problem, we propose the Enhanced Convolutional Autoencoder Anomaly Detection (E-CAAD) predictor. E-CAAD can be trained only by non-disruption samples and can also be trained by disruption precursor samples when disruption shots occur. This model not only overcomes the sample imbalance in supervised learning predictors, but also overcomes the inefficient dataset utilization faced by traditional anomaly detection predictors that cannot use disruption precursor samples for training, making it more suitable for the unpredictable datasets of future tokamaks. Compared to traditional anomaly detection predictors, the E-CAAD predictor performs better in disruption prediction and is deployed faster on new devices. Additionally, we explore strategies to accelerate the deployment of the E-CAAD predictor on the new device by using data from existing devices. Two deployment strategies are presented: mixing data from existing devices and fine-tuning the predictor trained on existing devices. Our comparisons indicate that the data from existing device can accelerate the deployment of predictor on new device. Notably, the fine-tuning strategy yields the fastest deployment on new device among the designed strategies. |
| WOS关键词 | JET |
| 资助项目 | National MCF Energy R&D Program of China[2022YFE03040004] ; National Natural Science Foundation of China[51821005] |
| WOS研究方向 | Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:001264292600001 |
| 出版者 | IOP Publishing Ltd |
| 资助机构 | National MCF Energy R&D Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/136953]  |
| 专题 | 中国科学院合肥物质科学研究院 |
| 通讯作者 | Zheng, W. |
| 作者单位 | 1.Huazhong Univ Sci & Technol, Sch Elect & Elect Engn, State Key Lab Adv Electromagnet Technol, Int Joint Res Lab Magnet Confinement Fus & Plasma, Wuhan 430074, Peoples R China 2.Chinese Acad Sci, Inst Plasma Phys, Hefei 230031, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ai, X. K.,Zheng, W.,Zhang, M.,et al. Cross-tokamak deployment study of plasma disruption predictors based on convolutional autoencoder[J]. PLASMA PHYSICS AND CONTROLLED FUSION,2024,66. |
| APA | Ai, X. K..,Zheng, W..,Zhang, M..,Ding, Y. H..,Chen, D. L..,...&Xiao, B. J..(2024).Cross-tokamak deployment study of plasma disruption predictors based on convolutional autoencoder.PLASMA PHYSICS AND CONTROLLED FUSION,66. |
| MLA | Ai, X. K.,et al."Cross-tokamak deployment study of plasma disruption predictors based on convolutional autoencoder".PLASMA PHYSICS AND CONTROLLED FUSION 66(2024). |
入库方式： OAI收割
来源：合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。