Continuous monitoring and diagnosis are important for safe operation of nuclear facilities. In an emergency shutdown, the diagnostic tasks can be challenging for human operators who may be under intense stress and/or ...
详细信息
Continuous monitoring and diagnosis are important for safe operation of nuclear facilities. In an emergency shutdown, the diagnostic tasks can be challenging for human operators who may be under intense stress and/or lack training. In recent years, studies using artificial-intelligence technologies have been actively conducted to help in diagnostic tasks. The current study proposes a data-driven approach that leverages deep reinforcement-learning techniques to intelligently learn effective strategies for state diagnosis of safetyfunctions. First, a learning framework and key elements of reinforcement learning are designed as basic components. Then, a deep neural-network structure and a deep reinforcement algorithm are presented for diagnosis learning. The experimental results demonstrate the feasibility of deep reinforcement learning on diagnosing the safetyfunctions of a nuclear facility.
The advanced human-machine interface (HMI) in nuclear power plants provides an information environment that supports the operators' burdensome cognitive tasks. safety function status check (SFSC), one of such task...
详细信息
The advanced human-machine interface (HMI) in nuclear power plants provides an information environment that supports the operators' burdensome cognitive tasks. safety function status check (SFSC), one of such tasks, can benefit from well-designed information aid. This paper describes an interface design for supporting the operator's SFSC task as an element of HMI for Advanced Power Reactor 1400 (APR1400) of Korea. A prototype interface scheme for the SFSC task was developed based on the task analysis on APR1400 HMI and an evaluation of existing plants. The interface consists of three hierarchical levels of information: the goal tree including safetyfunctions and their success paths, the flow structure of the success paths, and the system's topological structures related to the success paths. The interface is expected to have advantages in terms of cognitive information processing, which are currently being verified through systematic evaluations under diverse contexts and will be accordingly improved.
暂无评论