AI-Empowered Reform and Practice of the Graduate Course “Automotive Reliability Theory and Applications”

Abstract

Amid the rapid development of intelligent vehicles and digital engineering, the conventional graduate course Automotive Reliability Theory and Applications faces new challenges in connecting theoretical instruction with engineering applications, integrating modern computational tools, and diversifying instructional evaluation. To enhance graduate students’ ability to solve complex vehicle-engineering problems using reliability theory, data-analysis methods, and engineering-simulation techniques, this study takes AI-empowered curriculum reform as its central theme. It develops an integrated curriculum system comprising theoretical foundations, data intelligence, and engineering practice and uses outcome-based education (OBE) as its methodological foundation to systematically reconstruct course content, innovate teaching methods, embed engineering cases, and optimize evaluation mechanisms. Based on the practical needs of course development, the study proposes an overall roadmap for AI-empowered curriculum reform, designs a machine-learning case for predicting the service life of automotive components and a finite-element case for assessing the reliability of vehicle-body structures, and establishes a competency-attainment analysis framework and reform-outcome evaluation system that do not depend on fabricated score improvements. The proposed model can facilitate students’ transition from acquiring theoretical knowledge to developing the competence required to solve complex engineering problems and has strong potential for wider application in the cultivation of advanced vehicle-engineering talent under the emerging engineering education initiative.