Dr. Botros H​anna
Postdoctoral Research Scholar
Computer Science Department
New Mexico State University

Abstract

In the Nuclear Power Plant (NPP) control room, various challenges may impact the operators’ performance in emergencies. Among these challenges is the need to monitor many indicators on the control room boards, the limited time to interact with dynamic events, and the incompleteness in the operator’s knowledge. Recent research has been directed toward increasing the level of automation in the NPP control room by employing modern AI methods that support the operator’s decisions. Some of these proposed AI methods rely on statistical learning/machine learning and the availability of big data from the NPP history or the simulations of the NPP transients. Another type of AI methods is the reasoning-based qualitative methods that  represent our fundamental understanding of the NPP system, the flow and heat paths, the operating and emergency procedures and mimic human reasoning.

In this presentation, I will give an overview of AI methods that support the operator decisions with an emphasis on my work in developing a novel real-time automated reasoning system that assists the operator in real-time diagnosis, decision making, expecting consequences of different scenarios, and verifying whether the system is operating as expected. The novel operator support system not only provides diagnoses and recommendations but also computes explanations for these diagnoses/recommendations, enabling the operator to decide whether to trust the reasoning system answers.

Biography

Botros Hanna is currently a postdoctoral research scholar in the Computer Science Department at New Mexico State University. He is developing a system for artificial intelligence-guided decision support and automated reasoning for nuclear power plant management and control. Hanna did his Ph.D. and M.Sc. in Nuclear Engineering at North Carolina State University, where he studied from Fall 2012 to Spring 2018. His research areas include physics-informed machine learning, computational fluid dynamics, AI-Guided Reasoning.