Human-centered and explainable artificial intelligence in nuclear operations
Anna Hall 1 , Patrick Murray 2, Ronald Boring 1, & Vivek Agarwal 1
1 Idaho National Laboratory
2 EQRPI
The operating fleet of light water nuclear reactors in the United States is undergoing modernization from analog to partially digitalized environments, and the advent of new plant designs will feature fully digital control rooms. Retrofitting legacy instrumentation and controls (I&C) and new digital concepts of operations require significant increases in the level of automation, incorporating artificial intelligence (AI) and machine learning (ML). Human-centered AI (HCAI) is a combination of human-centered design (human factors, human-in-the-loop, etc.) combined with AI/ML to design an efficient, reliable system with full consideration for human engagement.
The transition from digital to AI-automation does not have an industry-ready template, and significant research is needed to bridge the gaps and maximize the application of AI. This paper provides a comprehensive and novel discussion of HCAI considerations in nuclear power, highlighting unique applications for the existing fleet and new advanced reactor designs. We end with a real-life use case of AI applications to work management in nuclear power plants (NPPs) and lessons learned.
