Research on the Concrete Teaching of Abstract Theories in the “Fundamentals of Mechanical Engineering Control” Course Empowered by Generative Artificial Intelligence

作者：Teng Hu, Yue Wang, Jiaxin Wang · 发表于：Computer Applications in Engineering Education · 年份：2026 · DOI：10.1002/cae.70184 · 被引用次数：1 · 研究领域：Model Reduction and Neural Networks、Artificial Intelligence in Healthcare and Education、Clinical Reasoning and Diagnostic Skills

ABSTRACT The modules on “System Stability Criteria” and “Frequency Domain Characteristics” within the “Fundamentals of Mechanical Engineering Control” course constitute essential theoretical components. However, their highly abstract mathematical nature and disconnect from physical intuition present considerable teaching challenges. This study examines the potential of Generative Artificial Intelligence (GAI) to facilitate concrete representation of abstract theories in engineering education. Grounded in cognitive load theory and the SAMR model, this research systematically analyzes key pedagogical obstacles—including the separation between mathematical derivations and physical significance, the abstraction of graphical logic, and insufficient engineering case studies—and harnesses GAI's capabilities in text analysis, dynamic visualization, and case generation to develop an innovative pedagogical framework. Using “System Stability Criteria” and “Frequency Domain Characteristics” as primary examples, this paper demonstrates the integration of text generation models (such as ChatGPT), image and dynamic visualization tools (including Midjourney and Stable Diffusion), and code generation models (like GitHub Copilot) to transform abstract theories into intuitive, interactive learning experiences. Through the design and classroom implementation of this GAI‐enhanced pedagogical framework, its feasibility and perceived utility are evaluated. Qualitative feedback from students and ins...