Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

The knowledge-based framework for a nuclear power plant operator advisor

Conference · · Transactions of the American Nuclear Society; (USA)
OSTI ID:5322235
An important facet in the design, development, and evaluation of aids for complex systems is the identification of the tasks performed by the operator. Operator aids utilizing artificial intelligence, or more specifically knowledge-based systems, require identification of these tasks in the context of a knowledge-based framework. In this context, the operator responses to the plant behavior are to monitor and comprehend the state of the plant, identify normal and abnormal plant conditions, diagnose abnormal plant conditions, predict plant response to specific control actions, and select the best available control action, implement a feasible control action, monitor system response to the control action, and correct for any inappropriate responses. These tasks have been identified to formulate a knowledge-based framework for an operator advisor under development at Ohio State University that utilizes the generic task methodology proposed by Chandrasekaran. The paper lays the foundation to identify the responses as a knowledge-based set of tasks in accordance with the expected human operator responses during an event. Initial evaluation of the expert system indicates the potential for an operator aid that will improve the operator's ability to respond to both anticipated and unanticipated events.
OSTI ID:
5322235
Report Number(s):
CONF-890604--
Conference Information:
Journal Name: Transactions of the American Nuclear Society; (USA) Journal Volume: 59
Country of Publication:
United States
Language:
English