Research on Smart Teaching Methods for High-Frequency Electronic Circuits Course Empowered by Artificial Intelligence

Abstract

High-Frequency Electronic Circuits is a core course for electronic information majors. It has long faced three teaching challenges: difficulty in intuitively understanding nonlinear theories, the "black-box" nature of hardware experiments, and delayed learning assessment feedback. Based on the Outcome-Based Education (OBE) philosophy, this study explores AI-empowered smart teaching methods. First, a "micro-project"-driven parameter visualization teaching model is proposed. AI-assisted interactive models transform abstract nonlinear circuit analysis into dynamic visual curves, helping students develop physical intuition. Second, an "AI Teaching Assistant + Hardware Practice" experimental paradigm is designed. AI identifies circuit topology and analyzes component functions, guiding students from passive wiring to active principle exploration. Third, a data-driven diagnostic mechanism is established. AI performs semantic analysis on high-frequency errors and generates learning diagnostic reports, supporting dynamic adjustment of teaching strategies. Two rounds of teaching practice show promising results. The average accuracy on objective questions in difficult chapters exceeded 70%. Effective operating time in laboratory sessions increased significantly. Classroom interaction also improved notably. This study provides a scalable paradigm for digital teaching transformation in application-oriented universities.