| 李治国,高洪霞,周在峰,王建,刘建容,刘春.人工智能赋能轻化工程专业实验教学的探索与实践——以《制浆造纸分析与检测》课程为例[J].中国造纸,2026,45(7):228-236 |
二维码（扫一下试试看！） |
| 人工智能赋能轻化工程专业实验教学的探索与实践——以《制浆造纸分析与检测》课程为例 |
| Innovative Research on AI-empowered Experimental Teaching in Light Chemical Engineering: A Case Study of the Course Pulp and Paper Testing |
| 收稿日期：2026-01-24 修订日期：2026-02-27 |
| DOI：10.11980/j.issn.0254-508X.2026.07.027 |
| 关键词: 人工智能 轻化工程 实验教学 制浆造纸分析与检测 个性化学习 |
| Key Words:artificial intelligence (AI) light chemical engineering experimental teaching Pulp and Paper Testing personalized learning |
| 基金项目:国家级大学生创新创业训练计划项目（X2025031）；四川轻化工大学教学改革研究项目（AL202402）。 |
| 作者 | 单位 | 邮编 | | 李治国* | 1内江师范学院人工智能学院,四川内江,641100 | 641100 | | 高洪霞* | 2四川轻化工大学食品与 酿酒工程学院,四川宜宾,644000 | 644000 | | 周在峰* | 3中国制浆造纸研究院有限公司,北京,100102 | 100102 | | 王建 | 1内江师范学院人工智能学院,四川内江,641100 | 641100 | | 刘建容 | 2四川轻化工大学食品与 酿酒工程学院,四川宜宾,644000 | 644000 | | 刘春 | 2四川轻化工大学食品与 酿酒工程学院,四川宜宾,644000 | 644000 |
|
| 摘要点击次数: 324 |
| 全文下载次数: 71 |
| 摘要:在教育数字化与产业智能化转型背景下，为破解轻化工程（制浆造纸工程）实验教学内容固化、反馈低效、评价片面、数字化融合不足等问题，本研究以《制浆造纸分析与检测》为载体，探索AI与实验教学深度融合路径，构建了基于多模态感知与知识图谱的个性化学习路径，搭建了 “端-边-云”智能诊断反馈平台，建立了三维九指标评价体系。对比结果显示，实验组学生学业成绩提升9.0%，教学效率提升57.8%，学习满意度提升34.3%，两极分化有效减小。该模式可为工科实验教学数字化改革提供借鉴参考，助力高素质工程技术人才培养。 |
| Abstract:Against the backdrop of digital transformation in education and intelligent industrial upgrading, this paper addresses persistent challenges in experimental teaching for light chemical engineering (pulp and paper engineering), including rigid content, inefficient feedback, one-sided assessment, and insufficient digital integration. Using the course Pulp and Paper Testing as a vehicle, this paper explored pathways for deep AI-pedagogy integration. The research constructed personalized learning paths based on multimodal perception and domain knowledge graphs, built an “edge-cloud-terminal” collaborative intelligent diagnostic feedback platform, and established a three-dimensional, nine-indicator evaluation system. Comparative experiment results demonstrated that the experimental group achieved a 9.0% increase in academic performance of the students, a 57.8% improvement in teaching efficiency, a 34.3% rise in learning satisfaction, while effectively reducing polarization. This model could provide a valuable reference for the digital reform of engineering experimental teaching, contributing to the cultivation of high-caliber engineering and technical talent. |
| 查看全文
HTML
查看/发表评论 下载PDF阅读器 |
|
|
|