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 ANS Annual Conference
May 31–June 3, 2026
Denver, CO|Sheraton Denver
Latest Magazine Issues
Feb 2026
Jul 2025
Latest Journal Issues
Nuclear Science and Engineering
March 2026
Nuclear Technology
February 2026
Fusion Science and Technology
January 2026
Latest News
Hanford begins removing waste from 24th single-shell tank
The Department of Energy’s Office of Environmental Management said crews at the Hanford Site near Richland, Wash., have started retrieving radioactive waste from Tank A-106, a 1-million-gallon underground storage tank built in the 1950s.
Tank A-106 will be the 24th single-shell tank that crews have cleaned out at Hanford, which is home to 177 underground waste storage tanks: 149 single-shell tanks and 28 double-shell tanks. Ranging from 55,000 gallons to more than 1 million gallons in capacity, the tanks hold around 56 million gallons of chemical and radioactive waste resulting from plutonium production at the site.
Aidan Rigby, Mike Wagner, Daniel Mikkelson, Ben Lindley
Nuclear Technology | Volume 212 | Number 2 | February 2026 | Pages 427-445
Regular Research Article | doi.org/10.1080/00295450.2025.2466137
Articles are hosted by Taylor and Francis Online.
The ability of nuclear reactors to operate their power conversion cycles more flexibly will enhance their value to energy grids with variable pricing. Current nuclear control systems are typically classical controllers that are often based on proportional-integral-derivative (PID) control. This paper presents a method of augmenting the existing PID control for difficult transient operations in nuclear power plants using a reinforcement learning–derived feedforward signal applied in real time. The agents, which are trained on a test thermal load-following problem, are designed to improve steam generator outlet temperature control for a range of fast load-following scenarios covering ramp rates from 9%/min to 15%/min.
Several reinforcement learning algorithms were initially investigated for the training of the feedforward agents with deep Q-learning (DQN) and proximal policy optimization (PPO) networks, which were found to be the most promising. The DQN controllers utilize discrete actions, giving them a better disturbance rejection at steady state but inconsistent response to initial temperature deviations. In contrast, PPO-trained agents, which take continuous actions except for a dead zone around zero, were shown to have the best combination of high disturbance rejection at steady state and good tracking of the desired temperature value. The ability of the PPO agent was also examined, with the average time of decision making found to be on the order of 1 ms.
The fault properties of the controller under the loss of the reinforcement learning agent feedforward signal were also examined. The controller showed strong performance in situations of “no-signal” faults. but was less good at handling “stuck-at” faults, where the feedforward signal remains at a set value. In both cases, however, the PID was able to successfully maintain stability, eventually returning the system to a steady state. It is hoped that this work will allow for the proposed control architecture to be examined for more difficult control problems such that it may eventually be used to adapt existing nuclear plants for more aggressive load-following on grids of the future.