Empowering the Next Generation of Nuclear Engineers: Large Language Model-Driven Educational Tools for the Nuclear Fuel Cycle
Disciplines
Nuclear Engineering
Abstract (300 words maximum)
Without the nuclear fuel cycle, nuclear power generation would not be possible. This complex sequence of industrial processes produces the uranium dioxide fuel pellets used in commercial nuclear reactors in the United States. The Nuclear Fuel Cycle course at Kennesaw State University introduces students to each stage of this process, including mining, milling, conversion, enrichment, fuel fabrication, power generation, and the storage and disposal of spent fuel. To help students better comprehend the extensive material, this project focuses on developing concise lectures and chapter summaries that reinforce key concepts and support cumulative learning. Creating comprehensive and accessible educational content that accurately represents the entire fuel cycle demands both time and specialized expertise. To address this challenge, the project explores the use of artificial intelligence, specifically Large Language Models, to generate high-quality, technically accurate lectures and summaries efficiently. All AI-generated content has undergone rigorous review and revision to ensure accuracy and educational value, contributing to a well-structured, multi-chapter curriculum on the nuclear fuel cycle. Chapters and chapter summaries were developed to serve as effective pre-reading materials, review aids, and accelerated learning resources. Students are encouraged to engage with these materials prior to lectures and assigned readings to reinforce foundational concepts and enhance comprehension. In addition to covering the core stages of the nuclear fuel cycle, the chapters and summaries also address key related topics such as low-level versus high-level waste, reprocessing, nuclear nonproliferation, and environmental impacts. This study also aims to improve both student performance and conceptual understanding within the course. As the nuclear industry is projected to expand significantly by 2050 due to global carbon reduction goals and increasing energy demand, these educational tools will help better prepare students for future careers in the field.
Use of AI Disclaimer
no
Academic department under which the project should be listed
SPCEET – Mechanical Engineering
Primary Investigator (PI) Name
Dr. Eduardo Farfan
Empowering the Next Generation of Nuclear Engineers: Large Language Model-Driven Educational Tools for the Nuclear Fuel Cycle
Without the nuclear fuel cycle, nuclear power generation would not be possible. This complex sequence of industrial processes produces the uranium dioxide fuel pellets used in commercial nuclear reactors in the United States. The Nuclear Fuel Cycle course at Kennesaw State University introduces students to each stage of this process, including mining, milling, conversion, enrichment, fuel fabrication, power generation, and the storage and disposal of spent fuel. To help students better comprehend the extensive material, this project focuses on developing concise lectures and chapter summaries that reinforce key concepts and support cumulative learning. Creating comprehensive and accessible educational content that accurately represents the entire fuel cycle demands both time and specialized expertise. To address this challenge, the project explores the use of artificial intelligence, specifically Large Language Models, to generate high-quality, technically accurate lectures and summaries efficiently. All AI-generated content has undergone rigorous review and revision to ensure accuracy and educational value, contributing to a well-structured, multi-chapter curriculum on the nuclear fuel cycle. Chapters and chapter summaries were developed to serve as effective pre-reading materials, review aids, and accelerated learning resources. Students are encouraged to engage with these materials prior to lectures and assigned readings to reinforce foundational concepts and enhance comprehension. In addition to covering the core stages of the nuclear fuel cycle, the chapters and summaries also address key related topics such as low-level versus high-level waste, reprocessing, nuclear nonproliferation, and environmental impacts. This study also aims to improve both student performance and conceptual understanding within the course. As the nuclear industry is projected to expand significantly by 2050 due to global carbon reduction goals and increasing energy demand, these educational tools will help better prepare students for future careers in the field.