Autonomous Control of Nuclear Power Plants

Basher, H.A.

doi:10.2172/885601

Cited by 18 publications

(13 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, more-advanced artificial intelligence (AI) techniques may be an alternative for the development of an algorithm for power-increase operations in NPPs. In addition, more extensive use of AI techniques must be considered for the realization of autonomous control of higher-level NPP operations [45].…”

Section: Some Gaps Of Related Studiesmentioning

confidence: 99%

Algorithm for Autonomous Power-Increase Operation Using Deep Reinforcement Learning and a Rule-Based System

2020

View full text Add to dashboard Cite

The power start-up operation of a nuclear power plant (NPP) increases the reactor power to the full-power condition for electricity generation. Compared to full-power operation, the power-increase operation requires significantly more decision-making and therefore increases the potential for human errors. While previous studies have investigated the use of artificial intelligence (AI) techniques for NPP control, none of them have addressed making the relatively complicated power-increase operation fully autonomous. This study focused on developing an algorithm for converting all the currently manual activities in the NPP power-increase process to autonomous operations. An asynchronous advantage actorcritic, which is a type of deep reinforcement learning method, and a long short-term memory network were applied to the operator tasks for which establishing clear rules or logic was challenging, while a rule-based system was developed for those actions, which could be described by simple logic (such as if-then logic). The proposed autonomous power-increase control algorithm was trained and validated using a compact nuclear simulator (CNS). The simulation results were used to evaluate the algorithm's ability to control the parameters within allowable limits, and the proposed power-increase control algorithm was proven capable of identifying an acceptable operation path for increasing the reactor power from 2% to 100% at a specified rate of power increase. In addition, the pattern of operation that resulted from the autonomous control simulation was found to be identical to that of the established operation strategy. These results demonstrate the potential feasibility of fully autonomous control of the NPP power-increase operation.

show abstract

Section: Some Gaps Of Related Studiesmentioning

confidence: 99%

Algorithm for Autonomous Power-Increase Operation Using Deep Reinforcement Learning and a Rule-Based System

2020

View full text Add to dashboard Cite

show abstract

“…1,3 While many plant operations must be overseen by human operators, there will likely need to be an increased level of automation in SMR operations. 4,5 This will be particularly so for control functions, which must maintain suitable margins from safety limits during plant transients, versus safety functions, which must maintain a certain level of operator interaction in order to meet regulatory safety requirements.…”

Section: Research Descriptionmentioning

confidence: 99%

Advanced I&C for Fault-Tolerant Supervisory Control of Small Modular Reactors

Cole¹

2018

View full text Add to dashboard Cite

In this research, we have developed a supervisory control approach to enable automated control of SMRs. By design the supervisory control system has an hierarchical, interconnected, adaptive control architecture. A considerable advantage to this architecture is that it allows subsystems to communicate at different/finer granularity, facilitates monitoring of process at the modular and plant levels, and enables supervisory control. We have investigated the deployment of automation, monitoring, and data collection technologies to enable operation of multiple SMRs. Each unit's controller collects and transfers information from local loops and optimize that unit's parameters. Information is passed from the each SMR unit controller to the supervisory controller, which supervises the actions of SMR units and manage plant processes. The information processed at the supervisory level will provide operators the necessary information needed for reactor, unit, and plant operation. In conjunction with the supervisory effort, we have investigated techniques for fault-tolerant networks, over which information is transmitted between local loops and the supervisory controller to maintain a safe level of operational normalcy in the presence of anomalies. The fault-tolerance of the supervisory control architecture, the network that supports it, and the impact of faulttolerance on multi-unit SMR plant control has been a second focus of this research. To this end, we have investigated the deployment of advanced automation, monitoring, and data collection and communications technologies to enable operation of multiple SMRs. We have created a faulttolerant multi-unit SMR supervisory controller that collects and transfers information from local loops, supervise their actions, and adaptively optimize the controller parameters. The goal of this research has been to develop the methodologies and procedures for faulttolerant supervisory control of small modular reactors. To achieve this goal, we have identified the following objectives. These objective are an ordered approach to the research: I) Development of a supervisory digital I&C system II) Fault-tolerance of the supervisory control architecture III) Automated decision making and online monitoring.

show abstract

“…Depletion problems can be solved and fuel management for multi-cycle analysis. The code has also been used along with WIMSD code for reactor physics calculations for different thermal research and power reactors (Aziz and Andrzejewski, 2000;Bhuiyan et al, 2000;Basher and Neal, 2003;Dalle et al, 2002;Khan et al, 2004;Zaker, 2003). …”

Section: The Reactor Simulation Code Citationmentioning

confidence: 99%