Exploring Artificial Intelligence Tools for Materials Science in Engineering: A Work-in-Progress in Undergraduate Classroom Integration

Rackan Sami Mansour; Osama Desouky; Marwa AbdelGawad

Download Paper | Permalink

Conference: 2024 ASEE Annual Conference & Exposition
Location: Portland, Oregon
Publication Date: June 23, 2024
Start Date: June 23, 2024
End Date: July 12, 2024
Conference Session: Multidisciplinary Engineering Division (MULTI) Technical Session 9
Tagged Division: Multidisciplinary Engineering Division (MULTI)
Permanent URL: https://peer.asee.org/47398

Request a correction

Paper Authors

biography

Rackan Sami Mansour Texas A&M University at Qatar

visit author page

Rackan Mansour is a graduating student at Texas A&M University in Qatar, where he has pursued his interests in material science, machine learning, and design independently. His work in material science has equipped him with a deep understanding of the properties and applications of various engineering materials. Rackan has also explored machine learning, focusing on its potential to influence and transform data analysis and decision-making processes. In the realm of design, he has actively engaged in product design and computer-aided design projects, including participation in the Shell Eco-Marathon. Each of these areas reflects Rackan's versatility and dedication to mastering diverse aspects of modern engineering.

visit author page

biography

Osama Desouky Texas A&M University at Qatar

visit author page

Osama Desouky is a Technical Laboratory coordinator at Texas A&M University in Qatar. Osama is currently pursuing his Ph.D. in interdisciplinary engineering from Texas A&M University at College Station. He is responsible for assisting with experimental method courses, 3D printing, mechanics of materials, material science, senior design projects, and advanced materials classes. Osama’s professional interests include manufacturing technology, materials science, 3D printing, experiments, and product design, and systems engineering for development of additive manufacturing systems.

visit author page

biography

Marwa AbdelGawad Texas A&M University at Qatar orcid.org/0000-0003-0561-0994

visit author page

Dr. Marwa AbdelGawad is an Instructional Assistant Professor at Texas A&M University at Qatar. She earned her Ph.D. in Mechanical Engineering from Texas A&M University (USA), where her research focused on examining the impact of microstructure on the corrosion response and mechanical integrity of magnesium alloys used in biomedical applications, specifically orthopedic implants, which resulted in the publication of several papers in prestigious journals and presentations at conferences.

Dr. AbdelGawad's interests are centered around materials and manufacturing, with a strong focus on corrosion of advanced materials, and the study of statics and mechanics. With an extensive teaching background, she has developed a keen interest in advancing innovation in engineering education. At present, she actively explores various methods to enhance student engagement and optimize their learning experiences through curriculum and course design.

visit author page

Download Paper | Permalink

Abstract

The onset of user-friendly Artificial Intelligence (AI) tools has significantly disrupted traditional educational methodologies within higher education. This paper explores the application of advanced AI technologies, specifically GPT-4, to enhance student assessments in material science education. It details the strategic integration of AI to develop dynamic and personalized assessments, such as multiple-choice quizzes and open-ended case studies, aiming to redefine classroom engagement by adapting to diverse student needs and learning environments. AI is a promising transformative tool in educational assessment processes within material science. Utilizing GPT-4, the study investigates the creation of diverse assessment forms, showing AI's capability to tailor assessments to individual learning requirements and curriculum standards. This approach deepens student engagement and advances educational strategies by equipping educators with dynamic tools that respond to the evolving educational landscape. The current study particularly emphasizes prompt engineering with AI, a critical element in optimizing AI’s utility for generating advanced, curriculum-aligned assessments. It assesses how effectively crafted prompts can guide AI to produce more relevant educational content, thereby enhancing learning experiences. As effective prompts are developed, GPT-4’s potential to customize assessments to meet specific student needs and address the complexities of material science theories is highlighted, presenting a valuable approach to boost student engagement, and understanding. These AI-driven methodologies aim to enhance the creative process in educational material development, offering educators an expanded array of tools for designing customized instructional materials. The role of AI in enriching educational content is expected to significantly elevate student engagement and deepen their comprehension of complex material science concepts. The study documents iterative testing and refinement of AI tools in producing and improving educational materials, providing tangible examples of AI’s contributions to educational innovation. The results add important insights to the discourse on integrating AI into engineering education, underscoring its potential as a collaborative tool in a rapidly evolving academic environment.

Citation
Format

Mansour, R. S., & Desouky, O., & AbdelGawad, M. (2024, June), Exploring Artificial Intelligence Tools for Materials Science in Engineering: A Work-in-Progress in Undergraduate Classroom Integration Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. https://peer.asee.org/47398

TY  - CPAPER
AB  - The onset of user-friendly Artificial Intelligence (AI) tools has significantly disrupted traditional educational methodologies within higher education. This paper explores the application of advanced AI technologies, specifically GPT-4, to enhance student assessments in material science education. It details the strategic integration of AI to develop dynamic and personalized assessments, such as multiple-choice quizzes and open-ended case studies, aiming to redefine classroom engagement by adapting to diverse student needs and learning environments.
AI is a promising transformative tool in educational assessment processes within material science. Utilizing GPT-4, the study investigates the creation of diverse assessment forms, showing AI&#39;s capability to tailor assessments to individual learning requirements and curriculum standards. This approach deepens student engagement and advances educational strategies by equipping educators with dynamic tools that respond to the evolving educational landscape. The current study particularly emphasizes prompt engineering with AI, a critical element in optimizing AI’s utility for generating advanced, curriculum-aligned assessments. It assesses how effectively crafted prompts can guide AI to produce more relevant educational content, thereby enhancing learning experiences. As effective prompts are developed, GPT-4’s potential to customize assessments to meet specific student needs and address the complexities of material science theories is highlighted, presenting a valuable approach to boost student engagement, and understanding.
These AI-driven methodologies aim to enhance the creative process in educational material development, offering educators an expanded array of tools for designing customized instructional materials. The role of AI in enriching educational content is expected to significantly elevate student engagement and deepen their comprehension of complex material science concepts. The study documents iterative testing and refinement of AI tools in producing and improving educational materials, providing tangible examples of AI’s contributions to educational innovation. The results add important insights to the discourse on integrating AI into engineering education, underscoring its potential as a collaborative tool in a rapidly evolving academic environment.


AU  - Rackan Sami Mansour
AU  - Osama Desouky
AU  - Marwa AbdelGawad
CY  - Portland, Oregon
DA  - 2024/06/23
PB  - ASEE Conferences
TI  - Exploring Artificial Intelligence Tools for Materials Science in Engineering: A Work-in-Progress in Undergraduate Classroom Integration
UR  - https://peer.asee.org/47398
ER  -