基于鸿蒙的EAST中央控制系统设计与实现
Design and Implementation of the EAST Central Control System Based on HarmonyOS
DOI: 10.12677/csa.2026.164114, PDF,    科研立项经费支持
作者: 黄子涵, 徐国顺:合肥综合性国家科学中心能源研究院,安徽省能源实验室,安徽 合肥;安徽理工大学,计算机科学与工程学院,安徽 淮南;张祖超*:合肥综合性国家科学中心能源研究院,安徽省能源实验室,安徽 合肥;中国科学院合肥物质科学研究院,安徽 合肥;田腾飞:中国科学院合肥物质科学研究院,安徽 合肥;张 杰:安徽理工大学,计算机科学与工程学院,安徽 淮南;中国科学院合肥物质科学研究院,安徽 合肥
关键词: EAST HarmonyOS N-BEATSxEAST HarmonyOS N-BEATSx
摘要: 针对EAST中央控制系统存在的通信协议不统一、实时性不足以及对国外系统依赖度高等问题,本文设计并实现了一种基于鸿蒙操作系统(HarmonyOS)的EAST中央控制系统。系统通过对EPICS IOC进行容器化部署,并引入WebSocket双向通信机制,实现了系统架构与通信模式的升级与优化。为进一步提升系统智能化水平,本文提出一种改进的N-BEATSx预测算法,在模型结构中引入多尺度残差增强模块(MSRR)和通道–时间注意力模块(CBAM-1D),并通过ModernTCN优化基函数,以增强特征表达能力与时序建模能力。实验结果表明,改进模型在多项评价指标上均优于传统预测模型及基准模型。研究结果表明,该系统不仅实现了EAST中央控制系统的国产化替代与实时性能优化,也为聚变装置控制系统的自主可控与智能化发展提供了可行路径。
Abstract: To address the issues of non-unified communication protocols, insufficient real-time performance, and heavy reliance on foreign systems in the EAST central control system, this paper designs and implements a HarmonyOS-based EAST central control system. The system architecture and communication framework are upgraded and optimized through containerized deployment of EPICS IOCs and the introduction of a bidirectional WebSocket communication mechanism. To further enhance system intelligence, an improved N-BEATSx forecasting algorithm is proposed. The model incorporates a Multi-Scale Residual Reinforcement (MSRR) module and a Channel-Temporal Attention Module (CBAM-1D), while ModernTCN is employed to optimize the basis functions, thereby strengthening feature representation and temporal modeling capabilities. Experimental results demonstrate that the improved model outperforms conventional forecasting methods and baseline models across multiple evaluation metrics. The findings indicate that the proposed system not only achieves domestic substitution and real-time performance optimization of the EAST central control system but also provides a feasible pathway toward autonomous controllability and intelligent development of fusion device control systems.
文章引用:黄子涵, 张祖超, 田腾飞, 张杰, 徐国顺. 基于鸿蒙的EAST中央控制系统设计与实现[J]. 计算机科学与应用, 2026, 16(4): 114-125. https://doi.org/10.12677/csa.2026.164114

参考文献

[1] Wan, Y., Li, J., Weng, P., et al. (2006) First Engineering Commissioning of EAST Tokamak. Plasma Science and Technology, 8, 253-254. [Google Scholar] [CrossRef
[2] Wu, S. (2007) An Overview of the EAST Project. Fusion Engineering and Design, 82, 463-471. [Google Scholar] [CrossRef
[3] 柴竹新, 吴宜灿, 刘伯学. 核聚变装置EAST高可靠性辐射防护控制系统[J]. 核电子学与探测技术, 2005(1): 28-31, 43.
[4] 彭标, 陈根, 段文学, 等. 合肥国产超导质子回旋加速器主真空控制系统的设计与实现[J]. 原子核物理评论, 2025, 42(2): 273-278.
[5] Leone, D., Carrubba, V., Mazzaro, S., Nobili, M., Cucè, D. and Hamilton, D. (2021) EPICS Application for ITER RH Supervisory Control System. Fusion Engineering and Design, 169, Article ID: 112429. [Google Scholar] [CrossRef
[6] He, S., Huang, L., Chen, X., Zhang, X., Wang, Z., Zuo, Y., et al. (2025) Safety and Interlock System for Poloidal Field Power Supply Based on Epics. Fusion Engineering and Design, 212, Article ID: 114823. [Google Scholar] [CrossRef
[7] 贵重, 李艳, 李云翔, 等. 国产操作系统发展及分析[J]. 电信工程技术与标准化, 2023, 36(6): 76-80.
[8] 苏行, 杨韬, 孙保琪, 等. 基于N-BEATS的单站对流层天顶总延迟预报[J]. 中国空间科学技术, 2022, 42(2): 56-63.
[9] 程旭初, 刘景霞, 康荣凯. 基于改进STGCN与N-BEATS的风功率超短期预测[J]. 现代电子技术, 2025, 48(8): 115-121.
[10] Vijayalakshmi, B., Ramar, K., Jhanjhi, N., Verma, S., Kaliappan, M., Vijayalakshmi, K., et al. (2020) An Attention‐based Deep Learning Model for Traffic Flow Prediction Using Spatiotemporal Features Towards Sustainable Smart City. International Journal of Communication Systems, 34, e4609. [Google Scholar] [CrossRef
[11] Salinas, D., Flunkert, V., Gasthaus, J. and Januschowski, T. (2020) DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks. International Journal of Forecasting, 36, 1181-1191. [Google Scholar] [CrossRef
[12] Luo, D. and Wang, X. (2024) ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis. The Twelfth International Conference on Learning Representations 2024, Vienna, 7-11 May 2024, 1-43.
[13] Oreshkin, B.N., Carpov, D., Chapados, N., et al. (2019) N-BEATS: Neural Basis Expansion Analysis for Interpretable Time Series Forecasting. arXiv: 1905.10437.
[14] Olivares, K.G., Challu, C., Marcjasz, G., Weron, R. and Dubrawski, A. (2023) Neural Basis Expansion Analysis with Exogenous Variables: Forecasting Electricity Prices with NBEATSx. International Journal of Forecasting, 39, 884-900. [Google Scholar] [CrossRef
[15] Woo, S., Park, J., Lee, J. and Kweon, I.S. (2018) CBAM: Convolutional Block Attention Module. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer VisionECCV 2018, Springer, 3-19. [Google Scholar] [CrossRef