In alignment with the Department of Energy (DOE)'s mission to bolster America's security by addressing its energy, environmental, and nuclear challenges, this panel will delve into the potential of leveraging a Digital Twin (DT) approach powered by Artificial Intelligence (AI) and Machine Learning (ML), in Nuclear Plant Asset Management & Modernization. Specifically, this panel will shed light on both the technological promise and economic implications of prognostic and health management from Digital Twin approaches, with an emphasis on: (1) Predictive Maintenance & Degradation Monitoring: Harnessing Digital Twins to foresee maintenance needs and track asset degradation in real-time. (2) Data Integration & Interpretability: Consolidating heterogeneous data sources into coherent Digital Twin models while ensuring model transparency. (3) Economic Optimization: Evaluating the return on investment and risk reduction potential of Digital Twin adoption. (4) Compliance Considerations: Ensuring regulatory alignment as Digital Twin capabilities progress. (5) Strategic Collaboration: Working closely with the DOE to maximize Digital Twins' impact through co-creation and knowledge sharing. Overall, this panel aims to bridge innovation and implementation, offering a comprehensive perspective on how Digital Twins, integrated with plant data infrastructure, can transform nuclear plant asset management with prognostic and health management. By convening experts across industry, government, and academia, we hope to chart a path toward increased efficiency, safety, and cost-effectiveness in maintaining these vital clean energy assets over their lifetime.


Panelists

  • Syed Bahauddin Alam (Univ. Illinois, Urbana-Champaign)
  • Sajedul Talukder (University of Texas at El Paso)
  • Lefteri H. Tsoukalas (Purdue Univ.)
  • Vaibhav Yadav (INL)

Discussion

To join the conversation, you must be logged in and registered for the meeting.

Register NowLog In