大学物理 ›› 2025, Vol. 44 ›› Issue (12): 89-.doi: 10.16854/j.cnki.1000-0712.250156

• 教学改革 • 上一篇    下一篇

人工智能在《高等电磁场》课程中的辅助教学研究

包扬,刘子嫣,周飞,陈欣茹,宛汀   

  1. 1.南京邮电大学 电子与光学工程学院,江苏南京210023;2. 南京邮电大学 通信与信息工程学院,江苏南京210023 
  • 收稿日期:2025-03-23 修回日期:2025-05-09 出版日期:2026-03-13 发布日期:2026-03-23
  • 作者简介:包扬(1989—),男,江苏南京人,博士,副教授,硕士研究生导师. 主要从事高等电磁场方面的教学和研究工作.
  • 基金资助:
    国家自然科学基金(62071245)资助

Research on teaching in the course of advanced electromagnetic #br# fields assisted by artificial intelligence

BAO Yang1, LIU Ziyan1, ZHOU Fei1, CHEN Xinru1, WAN Ting2   

  1. 1. School of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023; 
    2. School of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, 
    Nanjing 210023, China
  • Received:2025-03-23 Revised:2025-05-09 Online:2026-03-13 Published:2026-03-23

摘要: 《高等电磁场》课程是电磁场与无线技术专业开设的一门重要的专业基础课,是微波工程、天线理论等课程的学习基础.该课程立足于麦克斯韦方程的积分和微分形式的求解,各个知识点的学习均以大量的公式推导为基础,理论性强、概念抽象.将人工智能方法引入《高等电磁场》课程的学习,既可以保持该课程知识点的传授与可持续性发展,又融合了当下流行的人工智能算法,激发了学生的学习动力.本文将以《高等电磁场》课程中涡流检测问题和电磁散射问题的授课为例,对复杂繁琐的检测响应的全波仿真计算引入人工智能算法,将复杂的数值计算和当下主流的人工智能算法相结合,避免了突兀枯燥,引发学生的学习热情,通过结合实际涡流检测的工程案例,将理论融入实践,提升学生参与度并激发其创新潜力.



关键词: 人工智能, 教学改革, 教学研究, 电磁场理论, 涡流检测

Abstract:  “Advanced Electromagnetic Fields” is a core and foundational course for students majored in the electromagnetic field and wireless technology, serving as the prerequired course for other courses such as microwave engineering and antenna theory. This course focuses on solving the integral and differential forms of Maxwell’s equations. Learning of each knowledge point is based on numerous formula derivations, with strong theoretical and abstract concepts. The integration of artificial intelligence (AI) methods into the “Advanced Electromagnetic Fields” course not only preserves the teaching of core knowledge concepts and ensures sustainable development of the curriculum, but also incorporates cutting-edge AI algorithms, effectively stimulating students’ learning motivation. This article will take the teaching of eddy current testing problems in the “Advanced Electromagnetic Fields” course as an example. It introduces artificial intelligence algorithms into the full-wave simulation calculations of complex and cumbersome detection responses, combining complex numerical computations with mainstream AI algorithms. This approach avoids abrupt and dull teaching methods, sparking students’ enthusiasm for learning. By integrating practical engineering cases of eddy current testing, it incorporates theory into practice, enhancing student engagement and stimulating their potential.


Key words: artificial intelligence, teaching innovation, educational research, electromagnetic field theory, eddy current testing