基于知识图谱与AI赋能的《传热学》课程建设探索与实践

Exploration and Practice of Heat Transfer Course Construction Empowered by Knowledge Graphs and Artificial Intelligence

摘要: 针对《传热学》传统教学中知识模块孤立割裂、工程应用缺乏前沿衔接、学情反馈缺乏数据驱动等问题，本文提出了一种集“图谱骨架、AI强化、案例驱动”于一体的智慧课程重构方案。该方案以KAP (知识–应用–问题)模型为核心构建课程骨架知识图谱，AI助教强化全流程学习支持，工程案例驱动教学全过程。通过全面梳理导热、对流换热、辐射换热及传热过程分析等核心内容，构建了“知识点–模型方法–工程问题–学习资源”相互关联的智慧知识图谱，旨在帮助学生重塑系统化认知结构。同时，方案将数字化辅助教材、科研反哺案例与AI全过程学情诊断有机融合。本研究为工科核心基础课程的数字化转型与智慧化重构提供了系统性的方案设计与建设路径。

Abstract: To address the major problems in traditional Heat Transfer teaching, including fragmented knowledge modules, insufficient integration of cutting-edge engineering applications, and the lack of data-driven feedback on student learning, this study proposes a smart course reconstruction framework integrating a “knowledge-graph backbone, AI enhancement, and case-driven teaching.” Centered on the KAP (Knowledge-Application-Problem) model, the framework develops a knowledge graph as the structural foundation of the course, employs an AI teaching assistant to support the entire learning process, and uses engineering cases to organize teaching activities. By systematically reviewing the core content of heat conduction, convective heat transfer, radiative heat transfer, and heat transfer process analysis, an interconnected knowledge graph linking “knowledge points, models and methods, engineering problems and learning resources” is established to help students build a more systematic cognitive structure. The framework also integrates digital supplementary materials, research-based teaching cases, and AI-assisted learning diagnosis throughout the teaching process. This study provides a systematic design framework and practical pathway for the digital transformation and intelligent reconstruction of core engineering courses.