Abstract
Machine protection is a core task of real-time image diagnostics aiming for steady-state operation in nuclear fusion devices. The paper evaluates the applicability of the newest low-power NVIDIA Jetson Xavier NX platform for image plasma diagnostics. This embedded NVIDIA Tegra System-on-a-Chip (SoC) integrates a Graphics Processing Unit (GPU) and Central Processing Unit (CPU) on a single chip. The hardware differences and features compared to the previous NVIDIA Jetson TX2 are signified. Implemented algorithms detect thermal events in real-time, utilising the high parallelism provided by the embedded General-Purpose computing on Graphics Processing Units (GPGPU). The performance and accuracy are evaluated on the experimental data from the Wendelstein 7-X (W7-X) stellarator. Strike-line and reflection events are primarily investigated, yet benchmarks for overload hotspots, surface layers and visualisation algorithms are also included. Their detection might allow for automating real-time risk evaluation incorporated in the divertor protection system in W7-X. For the first time, the paper demonstrates the feasibility of complex real-time image processing in nuclear fusion applications on low-power embedded devices. Moreover, GPU-accelerated reference processing pipelines yielding higher accuracy compared to the literature results are proposed, and remarkable performance improvement resulting from the upgrade to the Xavier NX platform is attained.
Highlights
Machine protection is one of the primary challenges in the current and future largepower fusion devices operating with plasma pulses longer than 30 min, such as Wendelstein 7-X (W7-X), ITER and DEMO
The paper demonstrates the feasibility of applying low-power SoC devices for relatively complex real-time image processing for image plasma diagnostics, including the first real-time capable implementation of strike-line segmentation for W7-X
It provides the reasons for selecting cost-efficient and power-efficient embedded Tegra devices for image plasma diagnostics, especially in MicroTCA.4 architectures
Summary
Machine protection is one of the primary challenges in the current and future largepower fusion devices operating with plasma pulses longer than 30 min, such as Wendelstein 7-X (W7-X), ITER and DEMO. Hard real-time image acquisition and processing systems are essential to provide effective machine operation. Both the suitable hardware platform and efficient software contribute towards complying with the time constraints. In W Environment in Steady-state Tokamak (WEST), vision systems detect hotspots and recognise thermal events based on their location and evolution, including electrical arcs, B4C flakes and fast ion losses [10]. Since fusion devices will reach long discharges in future, e.g., 30 min in W7-X, new challenges emerge that might affect the robustness of image-processing methods. Graphics Processing Units (GPUs) are utilised in fusion experiments to provide hardware acceleration for efficient computations [13,14]. New System-on-a-Chip (SoC) platforms provide accelerated edge computing on low-power embedded systems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
