Enhancing STEAM education in engineering through the integration of AI and smartphone technology in teaching practices

Abstract

This paper introduces an innovative educational approach to enhancing Structural Health Monitoring (SHM) within engineering curricula, utilizing smartphones and generative AI. The project bridges the gap between theory and practice by enabling students to conduct eigenfrequency analysis, damping ratio measurements, and mode shape analysis using smartphone sensors. AI tools like ChatGPT support students in developing and verifying data analysis scripts, while Perplexity AI assists in validating academic references. Access to commercial sensor data allows students to compare their results with real-world industry standards, ensuring the accuracy of their analyses. The project fosters both individual and collaborative learning experiences: students independently conduct eigenfrequency and damping ratio measurements, while group work focuses on mode shape analysis. By engaging with real-world data and AI-assisted coding, students gain practical, hands-on experience that prepares them for professional challenges in SHM. Preliminary feedback has been highly positive, with students reporting increased engagement and understanding of SHM concepts. This paper also highlights the potential for scaling this educational model, particularly its integration into the Erasmus Mundus "NoRisk" Master’s program. Furthermore, the project aligns with the United Nations' Sustainable Development Goals (SDGs), specifically promoting quality education (SDG 4) and innovation in infrastructure (SDG 9).

Postprint (published version)