Purdue University Graduate School
Browse

DEVELOPMENT OF A MACHINE LEARNING-ASSISTED CORE SIMULATION FOR BOILING WATER REACTOR OPERATIONS

Download (23.32 MB)
thesis
posted on 2023-10-13, 13:39 authored by Muhammad Rizki OktavianMuhammad Rizki Oktavian

The research focuses on improving core simulation procedures in Boiling Water Reactors (BWRs) by leveraging machine learning techniques. Aimed at better fuel planning and enhanced safety, a machine learning model has been developed to predict errors in existing low-fidelity, diffusion-based core simulators. The machine learning models have demonstrated the capability to accurately and efficiently predict errors in core eigenvalue and power distribution in BWR Operations. This results in a significant improvement over conventional simulation methods in nuclear reactors without increasing computational complexity.

Funding

Blue Wave AI Labs, with funding under contract number COEUS 23024433

History

Degree Type

  • Doctor of Philosophy

Department

  • Nuclear Engineering

Campus location

  • West Lafayette

Advisor/Supervisor/Committee Chair

Dr. Yunlin Xu

Additional Committee Member 2

Dr. Lefteri H. Tsoukalas

Additional Committee Member 3

Dr. Hany Abdel-Khalik

Additional Committee Member 4

Dr. Jonathan Nistor