大学化学 >> 2026, Vol. 41 >> Issue (1): 289-297.doi: 10.12461/PKU.DXHX202509083

所属专题： 化学实验数字化设计竞赛获奖作品

专题 上一篇    下一篇

以研促学、以创促能、科教融合的高分子材料综合实验教学探索与实践——以机器学习辅助的智能书写识别系统为例

马松梅1, 张盈1, 刘刚2, 徐文龙1   

  1. 1 鲁东大学材料科学与工程学院, 山东 烟台 264025;
    2 鲁东大学化学化工学院, 山东 烟台 264025
  • 收稿日期:2025-09-17 录用日期:2025-11-24 发布日期:2025-12-30
  • 通讯作者: 徐文龙 E-mail:xuwenlong@ldu.edu.cn Wenlong Xu
  • 基金资助:
    国家自然科学基金(22472073)；山东省本科教学改革研究项目(Z2022157)

Comprehensive Experiment Teaching Exploration and Practice in Polymeric Materials Integrating Research-Driven Learning, Creativity-Enhanced Competency, and Science-Education Synergy: A Case Study of Machine Learning-Assisted Intelligent Handwriting Recognition System

Songmei Ma1, Ying Zhang1, Gang Liu2, Wenlong Xu1   

  1. 1 School of Materials Science and Engineering, Ludong University, Yantai 264025, Shandong Province, China;
    2 School of Chemistry and Chemical Engineering, Ludong University, Yantai 264025, Shandong Province, China
  • Received:2025-09-17 Accepted:2025-11-24 Published:2025-12-30
  • Contact: Wenlong Xu E-mail:xuwenlong@ldu.edu.cn

PDF

147

赞

摘要： 导电水凝胶传感器因其高灵敏度和柔性特点，在智能交互领域展现出巨大的应用潜力。本实验以甲基丙烯酸为单体、MXene为导电填料，通过自由基聚合制备复合水凝胶，构建机器学习辅助的书写识别系统。实验将科研前沿与教学融合，结合跨学科设计，提升学生创新能力，同时使其深刻体会到数字化设计与智能化技术对社会发展的重要意义。

关键词: 水凝胶, 传感器, 机器学习, 实验教学, 数字化

Abstract: Conductive hydrogel sensors demonstrate significant application potential in intelligent interaction systems due to their high sensitivity and flexible characteristics. This experimental study developed a composite hydrogel through free radical polymerization using methacrylic acid as the monomer and MXene as the conductive filler, subsequently constructing a machine learning-assisted handwriting recognition system. By integrating cutting-edge research with pedagogical practice and incorporating interdisciplinary design elements, this approach effectively enhances students’ innovative capacities while fostering their understanding of the crucial role digital design and intelligent technologies play in societal advancement.

Key words: Hydrogel, Sensor, Machine learning, Experimental teaching, Digitalization