ANS is committed to advancing, fostering, and promoting the development and application of nuclear sciences and technologies to benefit society.
Explore the many uses for nuclear science and its impact on energy, the environment, healthcare, food, and more.
Explore membership for yourself or for your organization.
Conference Spotlight
2026 Nuclear Energy Conference & Expo (NECX)
August 24–27, 2026
Dallas, TX|Hilton Anatole
Latest Magazine Issues
Jul 2026
Jan 2026
2026
Latest Journal Issues
Nuclear Science and Engineering
September 2026
Nuclear Technology
August 2026
Fusion Science and Technology
Latest News
Gov. Sherrill signs bill to begin nuclear procurement in N.J.
On July 13, New Jersey Gov. Mikie Sherrill signed the Power NJ Act, a bill that directs the state’s Board of Public Utilities (BPU), in collaboration with the state’s Economic Development Authority, to establish an “advanced nuclear energy procurement program.”
Yuanzhe Zhao, Zhicheng Chen, Yu Gu, Wei Liu, Shihua Song, Qinglong Cui
Fusion Science and Technology | Volume 82 | Number 6 | August 2026 | Pages 1237-1244
Regular Research Article | doi.org/10.1080/15361055.2025.2526283
Articles are hosted by Taylor and Francis Online.
In this work, we propose and implement a high‐speed, multi‐mode control scheme for a neutral beam injection (NBI) system at the Experimental Advanced Superconducting Tokamak (EAST), encompassing open‐loop, proportional-integral-derivative (PID) feedback, and deep neural network (DNN)–based follow‐up modes. The system supports continuous, pulsed, ramp, and user‐defined waveforms and has been fully tested on a National Instruments (NI) PXI-7842 R field-programmable gate array (FPGA) under LabVIEW Real-Time (RT). With a real‐time control latency below 1 ms, it responds to a 1% (0.2 A) disturbance on a nominal 20-A beam current within 100 ms and maintains beam stability within ±5% over pulses longer than 10s. The DNN follow‐up control achieves a correlation coefficient above 0.95 between the four power supply outputs and beam power variations across 0.8 to 1.8 MW. The entire control system has now been deployed and commissioned on the EAST positive ion beam line. Future work includes extending the DNN’s valid power range beyond 1.8 MW, integrating edge computing hardware to reduce latency below 0.5 ms, and employing higher precision current sensors to shrink steady‐state error to within ±2%.