Implementation of AI/DEEP learning disruption predictor into a plasma control system

Journal Article · 28 June 2023 · Contributions to Plasma Physics

DOI: https://doi.org/10.1002/ctpp.202200095 · OSTI ID:1987587

Tang, William ^[1]; Dong, Ge ^[1]; Barr, Jayson  ^[2]; Erickson, Keith ^[1]; Conlin, Rory ^[1]; Boyer, Dan ^[1]; Kates‐Harbeck, Julian ^[1]; Felker, Kyle ^[1]; Rea, Cristina  ^[3]; Logan, Nikolas ^[4]; Svyatkovskiy, Alexey ^[1]; Feibush, Eliot ^[1]; Abbatte, Joseph ^[1]; Clement, Mitchell ^[1]; Grierson, Brian ^[1]; Nazikian, Raffi ^[1]; Lin, Zhihong ^[5]; Eldon, David ^[2]; Moser, Auna ^[2]; Maslov, Mikhail ^[6]

---

1. Princeton Plasma Physics Laboratory Princeton New Jersey USA
2. General Atomics San Diego California USA
3. Massachusetts Institute of Technology, PSFC Cambridge Massachusetts USA
4. Lawrence Livermore National Lab Livermore California USA
5. University of California Irvine Irvine California USA
6. EUROfusion Consortium JET, Culham Science Centre Abingdon UK

Abstract This paper reports on advances in the state‐of‐the‐art deep learning disruption prediction models based on the Fusion Recurrent Neural Network (FRNN) originally introduced in a 2019 NATURE publication [ https://doi.org/10.1038/s41586‐019‐1116‐4 ]. In particular, the predictor now features not only the “disruption score,” as an indicator of the probability of an imminent disruption, but also a “sensitivity score” in real time to indicate the underlying reasons for the imminent disruption. This adds valuable physics interpretability for the deep learning model and can provide helpful guidance for control actuators now implemented into a modern plasma control system (PCS). The advance is a significant step forward in moving from modern deep learning disruption prediction to real‐time control and brings novel AI‐enabled capabilities relevant for application to the future burning plasma ITER system. Our analyses use large amounts of data from JET and DIII‐D vetted in the earlier NATURE publication. In addition to “when” a shot is predicted to disrupt, this paper addresses reasons “why” by carrying out sensitivity studies. FRNN is accordingly extended to use more channels of information, including measured DIII‐D signals such as (i) the “n1rms” signal that is correlated with the n  = 1 modes with finite frequency, including neoclassical tearing mode and sawtooth dynamics; (ii) the bolometer data indicative of plasma impurity control; and (iii) “q‐min”—the minimum value of the safety factor relevant to the key physics of kink modes. The additional channels and interpretability features expand the ability of the deep learning FRNN software to provide information about disruption subcategories as well as more precise and direct guidance for the actuators in a PCS.

• Sponsoring Organization: USDOE
• OSTI ID: 1987587
• Journal Information: Contributions to Plasma Physics, Journal Name: Contributions to Plasma Physics Journal Issue: 5-6 Vol. 63; ISSN 0863-1042
• Publisher: Wiley Blackwell (John Wiley & Sons)Copyright Statement
• Country of Publication: Germany
• Language: English