Technical Basis for Advanced Artificial Intelligence and Machine Learning Adoption in Nuclear Power Plants

Abstract

The research and development reported here is part of the Technology Enabled Risk-Informed Maintenance Strategy project sponsored by the U.S. Department of Energy's Light Water Reactor Sustainability program. The primary objective of the research presented in this report is to produce a technical basis for developing explainable and trustable artificial intelligence (AI) and machine learning (ML) technologies. The technical basis will lay the foundation for addressing the technical and regulatory adoption challenges of AI/ML technologies across plant assets and the nuclear industry at scale and to achieve seamless cost-effective automation without compromising plant safety and reliability.The technical basis ensuring wider adoption of AI/ML technologies presented in this report was developed by Idaho National Laboratory (INL), in collaboration with Public Service Enterprise Group (PSEG) Nuclear, LLC. To develop the initial technical basis, the circulating water system (CWS) at the PSEG-owned plant sites was selected as the identified plant asset. Specifically, the issue of waterbox fouling diagnosis in the CWS using different types of CWS data is presented to address the said challenge. The approach presented in this report is based on the closed-loop forward-backward process that tries to capture the advancements in data science addressing the explainability of AI/ML outcomes, user-centric interpretability of those outcomes, and how user interpretation can be used as feedback to further simplify the process. A prototype interface is developed to present a focused component-level display of the ML model outputs in a usable and digestible form.

Digitalization Guiding Principles and Method for Nuclear Industry Work Processes

“…The LWRS Plant Modernization Pathway recognizes this need-I&C architecture and digital infrastructure is one of its core research areas. Last, proper data governance paves the way for advanced AI/ML technologies, such as risk-informed predictive maintenance (Agarwal et al, 2022;Walker et al, 2023), to generate intelligent insights, predictions, and action recommendations.…”

“…Further, for the end users, it may not be a foregone conclusion that the new digitalized technologies will make life easier. Healthy skepticism is pervasive in nuclear power operations due to its rigorous safety culture (Agarwal et al, 2022), especially if there has been an instance in which the introduction of new technology in the past has failed or increased workload. Managing first impressions, and subsequently giving end users time (over weeks and months), and importantly, listening to feedback will pay dividends in overcoming any user-barriers to adoption in the long run.…”

“…Risk can be estimated when the data are normalized and proper statistical models are applied to equipment based on maintenance, probability of failure, environment, age, plant conditions, and safety limits. The LWRS Program at INL has condition-based maintenance initiatives, such as Technology-Enabled Risk-informed Maintenance Strategy, which uses data reconciliation and normalization efforts (Agarwal et al, 2022). The work is being developed to integrate the results of predictive analytics with enterprise resource planning (e.g., work orders and work packages).…”

Human and Technology Integration Evaluation of Advanced Automation and Data Visualization

“…Data architecture and analytics develops and demonstrates advanced monitoring and data processing capabilities to replace labor-intensive plant support tasks. These capabilities leverage machine learning (ML) and artificial intelligence (AI) techniques to automate burdensome tasks to significantly increase efficiencies and reduce both system and human errors (Agarwal et al, 2022). There have been diverse use cases demonstrated in this area, including condition-based monitoring (Agarwal et al, 2022), automated outage risk and technical specification compliance (St Germain, Masterlark, Priddy, and Beck, 2019), automated work packages (Al Rashdan, Oxstrand, and Agarwal, 2016), computer-based procedures for field workers (Oxstrand, Le Blanc, and Bly, 2016), and automated fire watch (Al Rashdan, Griffel, and Powell, 2019).…”

“…These capabilities leverage machine learning (ML) and artificial intelligence (AI) techniques to automate burdensome tasks to significantly increase efficiencies and reduce both system and human errors (Agarwal et al, 2022). There have been diverse use cases demonstrated in this area, including condition-based monitoring (Agarwal et al, 2022), automated outage risk and technical specification compliance (St Germain, Masterlark, Priddy, and Beck, 2019), automated work packages (Al Rashdan, Oxstrand, and Agarwal, 2016), computer-based procedures for field workers (Oxstrand, Le Blanc, and Bly, 2016), and automated fire watch (Al Rashdan, Griffel, and Powell, 2019). The application of these advanced capabilities provides a significant opportunity to reduce costs across plant support functions by transforming the way work is done at the plant, transitioning from labor-centric to technology-centric models.…”