Research on Intelligent Diagnosis of Circuit Faults and Personalized Learning System Based on Artificial Intelligence

Circuit analysis is a fundamental course for disciplines such as electronic information, electrical engineering and automation, and artificial intelligence. Due to its abstract concepts and strong practical orientation, ensuring high-quality teaching can be challenging. Students often develop resistance to circuit experiments and encounter difficulties in promptly diagnosing and troubleshooting various circuit faults, which hinders the achievement of optimal learning outcomes. To address these challenges, this study proposes an intelligent system for circuit fault diagnosis and personalized learning, leveraging artificial intelligence as an innovative teaching tool. The system comprises two main modules: a machine learning-based fault diagnosis engine and a knowledge graph-based personalized learning path recommender. The fault diagnosis engine rapidly and accurately identifies common circuit fault patterns, such as short circuits and open circuits, by analyzing key electrical parameters across different circuit nodes, and presents the results through graphical simulations akin to teacher guidance. The personalized learning recommender constructs a knowledge graph for the circuit analysis course and delivers targeted learning resources to students based on their historical diagnostic records and learning behavior, thereby realizing truly customized instruction. For a representative circuit case, the operational amplifier circuit, Python scripts are employed to automate data collection, train the diagnostic model, and provide students with closed-loop intelligent assistance. This approach offers an innovative and feasible technical solution for practical teaching in circuit analysis courses and establishes a foundation for further exploring the integration of AI technologies in engineering education.