用多尺度贝叶斯优化提升托卡马克等离子体稳定性控制效果
Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks
- 结合高频数据模型与低频高斯过程，分层更新预测
- 实测成功率达50%，较历史结果提升117%
- 适合等离子体控制、核聚变研究者参考
机器学习在复杂现实系统控制中常遇瓶颈，尤其在核聚变领域，系统动态高度复杂、数据稀缺、硬件易故障，且实验影响可能持续超过实验周期。现有强化学习、监督学习与贝叶斯优化虽部分缓解问题，但缺乏整体解决方案。本文提出一种多时间尺度贝叶斯优化方法，融合高频数据驱动动力学模型与低频高斯过程，在实验间更新高斯过程，快速适应新数据，从而修正动态模型的不准确性。通过在DIII-D核聚变装置上控制撕裂不稳定性进行验证：离线历史数据测试显示性能显著优于多个基线；现场实验在高约束等离子体场景下实现50%的成功率，相较历史水平提升117%。
原文摘要 · Abstract (English)
Machine learning algorithms often struggle to control complex real-world systems. In the case of nuclear fusion, these challenges are exacerbated, as the dynamics are notoriously complex, data is poor, hardware is subject to failures, and experiments often affect dynamics beyond the experiment's duration. Existing tools like reinforcement learning, supervised learning, and Bayesian optimization address some of these challenges but fail to provide a comprehensive solution. To overcome these limitations, we present a multi-scale Bayesian optimization approach that integrates a high-frequency data-driven dynamics model with a low-frequency Gaussian process. By updating the Gaussian process between experiments, the method rapidly adapts to new data, refining the predictions of the less reliable dynamical model. We validate our approach by controlling tearing instabilities in the DIII-D nuclear fusion plant. Offline testing on historical data shows that our method significantly outperforms several baselines. Results on live experiments on the DIII-D tokamak, conducted under high-performance plasma scenarios prone to instabilities, shows a 50% success rate, marking a 117% improvement over historical outcomes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。