文献类型：期刊文献

英文题名：Integrating Wireless Passive Sensor Technology Into Smart Manufacturing Education: A Teaching Framework From Theory to Practice

作者：Tao, Shunzhen[1,2];Tu, Huating[1,3];Liang, Kaihao[1,2];Gao, Yang[1,2];Zhang, Jianrui[1,2];Zhang, Yang[4];Xuan, Fuzhen[1,2]

机构：[1]East China Univ Sci & Technol, Sch Mech & Power Engn, Shanghai Key Lab Intelligent Sensing & Detect, Shanghai, Peoples R China;[2]East China Univ Sci & Technol, Key Lab Pressure Syst & Safety, Minist Educ, Shanghai, Peoples R China;[3]Shanghai Univ Med & Hlth Sci, Coll Med Instruments, Shanghai, Peoples R China;[4]CNC Huayi Engn & Technol Grp, Shanghai, Peoples R China

年份：2026

卷号：34

期号：3

外文期刊名：COMPUTER APPLICATIONS IN ENGINEERING EDUCATION

收录：;EI(收录号：20261920652101);WOS:【SCI-EXPANDED(收录号:WOS:001754565700001)】；

基金：This project was supported by the National Natural Science Foundation of China (Grant Nos. 52275146, 61804054, 12411530109, 62301314, 52321002 and 12174102), Shanghai Municipal Education Commission AI-Driven Reform of Research Paradigms to Empower Advancement of Disciplines (G100-2-24107), and China Higher Education Institution Industry-University-Research Innovation Project (2024MZ020).

语种：英文

外文关键词：AI-driven design; DLP-3Dprinting; RF simulation; wireless passive sensors

摘要：With the rapid development of intelligent manufacturing, it is imperative that the engineering education system urgently needs to evolve in sync with cutting-edge industrial technologies. The industrial sector has widely adopted advanced technologies such as wireless passive sensors (WPS), but the content of relevant courses in universities still lags behind technological development, especially in the integration of new sensing mechanisms such as WPS into mechatronics and sensor courses, which have obvious shortcomings. To fill this gap, a comprehensive teaching framework that integrates "Theory, Design, Preparation, Testing" was proposed in this article. This framework integrates the basic theory of microwave sensing, electromagnetic simulation practice, intelligent optimization design based on transformer neural network, convenient digital manufacturing methods, and actual sensing testing, aiming to help students systematically master the full process capability of WPS from theory to practice through a layered and progressive teaching path. The introduction of encoding structures and neural network prediction methods significantly improves the efficiency and effectiveness of sensor performance optimization, enabling students to experience a paradigm shift from traditional empirical design to data-driven intelligent design. At the same time, by replacing traditional MEMS processes with 3D printing technology, the complexity, costness, and difficulties to implement micro-nano processing equipment have been effectively solved, achieving rapid closed-loop verification from concept to physical object. The effectiveness of this framework has been verified through multi-dimensional student feedback. The framework not only cultivates students' interdisciplinary integration abilities in the fields of digital manufacturing and industrial IoT, but also provides an extensible teaching practice path for engineering education to adapt to technological development.