FPGA-Accelerated Real-Time Beam Emission Spectroscopy Diagnostics at DIII-D Using the SLAC Neural Network Library for ML Inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908693064318976 |
|---|---|
| author | Dave, Abhilasha Russell, James Mishra, Mudit Ruckman, Larry Erickson, Keith Kim, SangKyeun Joung, Semin Butt, Jalal Herbst, Ryan Coffee, Ryan Smith, David Kolemen, Egemen |
| author_facet | Dave, Abhilasha Russell, James Mishra, Mudit Ruckman, Larry Erickson, Keith Kim, SangKyeun Joung, Semin Butt, Jalal Herbst, Ryan Coffee, Ryan Smith, David Kolemen, Egemen |
| contents | Achieving reliable real-time control of tokamak plasmas is essential for sustaining high-performance operation in next-generation fusion reactors. A major challenge is the accurate and timely prediction of edge-localized modes (ELMs), especially in high-confinement regimes such as wide-pedestal quiescent H-mode. We present a hardware-accelerated machine learning (ML) inference system integrated into the RTSTAB processing node of the DIII-D real-time diagnostic and control infrastructure. The system uses an AMD/Xilinx KCU1500 FPGA to enable ultra low latency plasma state classification and ELM forecasting. Input features come from real-time Beam Emission Spectroscopy (BES), and the ML model is implemented as a dense neural network using the SLAC Neural Network Library (SNL).
A key capability is SNL dynamic parameter loading, which allows on-the-fly updates of neural network weights and biases without hardware resynthesis. This enables multiple classification tasks on a single FPGA design and supports adaptive control strategies that respond to evolving plasma conditions. By decoupling inference from fixed-weight configurations, the system supports continuous model refinement and seamless task switching during live operation.
The SNL-based inference engine is fully integrated with the FPGA in the DIII-D RTSTAB Plasma Control System (PCS), improving ELM avoidance, confinement, and operational stability. These results show the feasibility of embedding dynamically reconfigurable FPGA-based ML inference into real-time fusion diagnostic pipelines, providing a scalable and resilient path toward intelligent and autonomous plasma control in future magnetic confinement fusion devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21924 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FPGA-Accelerated Real-Time Beam Emission Spectroscopy Diagnostics at DIII-D Using the SLAC Neural Network Library for ML Inference Dave, Abhilasha Russell, James Mishra, Mudit Ruckman, Larry Erickson, Keith Kim, SangKyeun Joung, Semin Butt, Jalal Herbst, Ryan Coffee, Ryan Smith, David Kolemen, Egemen Plasma Physics Achieving reliable real-time control of tokamak plasmas is essential for sustaining high-performance operation in next-generation fusion reactors. A major challenge is the accurate and timely prediction of edge-localized modes (ELMs), especially in high-confinement regimes such as wide-pedestal quiescent H-mode. We present a hardware-accelerated machine learning (ML) inference system integrated into the RTSTAB processing node of the DIII-D real-time diagnostic and control infrastructure. The system uses an AMD/Xilinx KCU1500 FPGA to enable ultra low latency plasma state classification and ELM forecasting. Input features come from real-time Beam Emission Spectroscopy (BES), and the ML model is implemented as a dense neural network using the SLAC Neural Network Library (SNL). A key capability is SNL dynamic parameter loading, which allows on-the-fly updates of neural network weights and biases without hardware resynthesis. This enables multiple classification tasks on a single FPGA design and supports adaptive control strategies that respond to evolving plasma conditions. By decoupling inference from fixed-weight configurations, the system supports continuous model refinement and seamless task switching during live operation. The SNL-based inference engine is fully integrated with the FPGA in the DIII-D RTSTAB Plasma Control System (PCS), improving ELM avoidance, confinement, and operational stability. These results show the feasibility of embedding dynamically reconfigurable FPGA-based ML inference into real-time fusion diagnostic pipelines, providing a scalable and resilient path toward intelligent and autonomous plasma control in future magnetic confinement fusion devices. |
| title | FPGA-Accelerated Real-Time Beam Emission Spectroscopy Diagnostics at DIII-D Using the SLAC Neural Network Library for ML Inference |
| topic | Plasma Physics |
| url | https://arxiv.org/abs/2511.21924 |