Cultivating Adaptive Engineering Expertise through Metaphor-Based Socratic Artificial Intelligence and Interactive Simulation

This project aims to serve the national interest by strengthening undergraduate engineering education through Socratic artificial intelligence tutoring, interactive visual simulation, and metaphor-based learning. Many engineering concepts require students to connect physical intuition, mathematical models, and symbolic reasoning, yet these connections are often difficult to develop through lecture, textbook examples, or calculation-based practice alone. This project intends to increase students’ ability to reason across these representations by creating a learning environment in which abstract engineering ideas become visible, interactive, and explainable. The significance of the project lies in its effort to help students move beyond rote memorization toward conceptual understanding, misconception repair, and adaptive problem solving. This Level 1 Engaged Student Learning project plans to develop and study a metaphor-based Socratic artificial intelligence tutoring framework that connects real-time simulation states with guided dialogue and instructor-supported learning activities. The project intends to support students in foundational electrical and computer engineering courses, including semiconductor physics and signals and systems, while producing reusable instructional tools that can be adapted across engineering and STEM education contexts. The goals of the project are to design, implement, and evaluate a simulation-grounded artificial intelligence tutoring system that helps students transfer from intuitive visual exploration to formal mathematical reasoning. The scope of the project includes refinement of the project learning platform, integration of metaphor-based simulations into selected electrical and computer engineering courses, development of Socratic tutoring prompts and instructor-facing learning analytics, and evaluation of student learning outcomes. The methodology plans to combine interactive physics-based simulations, artificial intelligence-guided questioning, concept inventories, student surveys, classroom implementation data, and formative and summative evaluation. The project plans to study how simulation-anchored feedback affects conceptual depth, student trust in artificial intelligence, perceived usefulness, ease of use, and students’ ability to repair misconceptions. The project is expected to advance understanding of how artificial intelligence tutors can be grounded in real-time simulation environments while maintaining mathematical rigor, supporting instructor oversight, and promoting transferable engineering reasoning. Results, metaphor templates, instructional modules, and implementation guidance are planned for dissemination to support broader adoption in engineering education. The NSF IUSE: EDU Program supports research and development projects to improve the effectiveness of STEM education for all students. Through the Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.