新工科背景下AI赋能《金属材料及热处理》实验教学改革探索

doi:10.13251/j.issn.0254-6051.2026.02.051

金属热处理 ›› 2026, Vol. 51 ›› Issue (2): 340-346.DOI: 10.13251/j.issn.0254-6051.2026.02.051

• 教学与实践 • 上一篇

新工科背景下AI赋能《金属材料及热处理》实验教学改革探索

谢芋江, 周培山, 文雄, 冷曼希

西南石油大学新能源与材料学院, 四川成都 610500

收稿日期:2025-11-18 修回日期:2025-12-03 发布日期:2026-03-05
作者简介:谢芋江(1985—),男,副教授,硕士生导师,博士,主要研究方向为金属材料加工工程的教学和科学研究,E-mail:xyj_0212@163.com
基金资助:
国家自然科学基金(52376076);四川省高等学校创新性实验项目(川教函[2025]199号-66);西南石油大学2024-2026年校级本科教育教学改革研究项目(X2024JGYB35)

An exploration of AI-empowered experimental teaching reform in "Metallic Materials and Heat Treatment" under background of emerging engineering education

Xie Yujiang, Zhou Peishan, Wen Xiong, Leng Manxi

School of New Energy and Materials, Southwest Petroleum University, Chengdu Sichuan 610500, China

Received:2025-11-18 Revised:2025-12-03 Published:2026-03-05

摘要/Abstract

摘要： 新工科建设背景下,《金属材料及热处理》课程传统的实验教学面临安全隐患、时空限制、组织转变过程抽象、分析浅层化等瓶颈,难以适配复合型工程技术人才培养需求。立足“虚实结合、人机协同、数据驱动、深度探究”的核心理念,探索构建AI赋能的实验教学新体系。通过整合机器学习与数据预测、虚拟仿真与数字孪生、计算机视觉与图像识别等技术模块,重构“课前-课中-课后”三段式教学模式,同时以“碳钢热处理综合实验”“钢的淬透性及淬硬性实验”为案例,探索工艺参数智能推荐、过程虚拟可视化、数据自动分析等融合路径,并基于AI建立多元评价体系,解决传统实验教学的瓶颈问题。

关键词: 新工科, AI赋能, 《金属材料及热处理》, 实验教学改革

Abstract: Under the background of emerging engineering education, the traditional experimental teaching of the "Metallic Materials and Heat Treatment" faces bottlenecks such as potential safety hazards, time and space constraints, the abstract nature of microstructure evolution, and superficial analysis, making it difficult to meet the training needs of compound engineering and technical talents. Based on the core concepts of "combination of virtual and real, human-machine collaboration, data-driven approach, and in-depth inquiry", the construction of a new AI-empowered experimental teaching system is explored. By integrating technical modules including machine learning and data prediction, virtual simulation and digital twin, and computer vision and image recognition, the three-stage teaching model of "pre-class - in-class - post-class" is reconstructed. Meanwhile, using "comprehensive experiment of carbon steel heat treatment" and "experiment of hardenability and hardenability of steel" as examples, integration paths including intelligent process parameter recommendations, virtual process visualization, and automatic data analysis are explored, and a multi-dimensional evaluation system based on AI is established. These measures address the bottleneck problems of traditional experimental teaching.

Key words: emerging engineering education, AI-empowered, Metallic Materials and Heat Treatment, experimental teaching reform

中图分类号:

G642.0

谢芋江, 周培山, 文雄, 冷曼希. 新工科背景下AI赋能《金属材料及热处理》实验教学改革探索[J]. 金属热处理, 2026, 51(2): 340-346.

Xie Yujiang, Zhou Peishan, Wen Xiong, Leng Manxi. An exploration of AI-empowered experimental teaching reform in "Metallic Materials and Heat Treatment" under background of emerging engineering education[J]. Heat Treatment of Metals, 2026, 51(2): 340-346.

参考文献

[1] 钟登华. 新工科建设的内涵与行动[J]. 高等工程教育研究, 2017(3): 1-6.
[2] 周端明, 沈燕培. 习近平科技创新重要论述指引新工科建设的方向[J]. 高等工程教育研究, 2021(4): 1-7.
[3] 吴璇, 陆雨薇, 毛成芳. 新工科背景下复合型人才培养模式探究——以机械工程专业本科生培养方案为例[J]. 大学教育, 2024(23): 140-144.
[4] 石永华, 凌亮建, 张嘉仪, 等. 机器人焊接智能视觉传感技术的研究及应用进展[J]. 机电工程技术, 2025, 54(12): 1-23.
Shi Yonghua, Ling Liangjian, Zhang Jiayi, et al. Research and application progress of intelligent vision sensing technology in robotic welding[J]. Mechanical Electrical Engineering Technology, 2025, 54(12): 1-23.
[5] 谈毅, 江丽珍, 廖志青, 等. 交叉融合的新工科机器人焊接实训课程体系规划与实践研究[J]. 电焊机, 2024, 54(5): 153-159.
Tan Yi, Jiang Lizhen, Liao Zhiqing, et al. Planning and praction research of practical training course system for new engineering robot welding[J]. Electric Welding Machine, 2024, 54(5): 153-159.
[6] 谢芋江, 周培山, 温飞娟, 等. 人工智能赋能“金属材料及热处理”课程教学改革初探[J]. 金属热处理, 2025, 50(3): 250-254.
Xie Yujiang, Zhou Peishan, Wen Feijuan, et al. A preliminary probe into teaching reform of the course "Metal Materials and Heat Treatment" enabled by artificial intelligence[J]. Heat Treatment of Metals, 2025, 50(3): 250-254.
[7] 蒋亮, 秦春, 李涌泉. 新工科背景下金属材料及热处理课程思政探索与实践[J]. 高教学刊, 2025, 11(27): 34-37.
[8] 马煜林, 葛彦伟, 张瑜. 新工科背景下以OBE为导向《金属学与热处理》的课程教学改革——以材料成型及控制工程(铸造方向)专业为例[J]. 铸造设备与工艺, 2019(5): 49-52.
Ma Yulin, Ge Yanwei, Zhang Yu. Curriculum reform of OBE-oriented Metals and Heat Treatment under the background of new engineering-take the material forming and control engineering (casting direction) as an example[J]. Foundry Equipment and Technology, 2019(5): 49-52.
[9] 伊俊振, 张占伟, 王超, 等. 金属材料与热处理课程教学改革与实践[J]. 中国现代教育装备, 2023(15): 148-149, 156.
[10] 王子奇, 李红, 李玲. 人工智能交互式数字教师的构建及其在材料科学实验教学中的应用探索[J]. 教育进展, 2025(6): 718-721.
[11] 郭丹, 金剑锋, 王明涛, 等. 新工科背景下计算材料学实验教学改革与实践[J]. 实验室研究与探索, 2022, 41(3): 181-186.
Guo Dan, Jin Jianfeng, Wang Mingtao, et al. Reform and practice of experimental teaching of computational materials science under the background of new engineering[J]. Research and Exploration in Laboratory, 2022, 41(3): 181-186.
[12] 马冬威, 张元好, 王天国, 等. 虚拟仿真技术在热处理实验中的应用探索[J]. 中国现代教育装备, 2020(13): 28-30.
[13] 黄鹏, 孙建林, 刘国权, 等. 综合热处理虚拟实验的设计与应用[J]. 实验技术与管理, 2015, 32(11): 132-135.
Huang Peng, Sun Jianlin, Liu Guoquan, et al. Design and application of virtual laboratory based on comprehensive heat treatment experiments[J]. Experimental Technology and Management, 2015, 32(11): 132-135.
[14] 杨春亮, 杨林, 刘飞. “现代材料分析方法”虚实结合实验教学模式改革的探索与实践——以X射线衍射仪实验为例[J]. 广东化工, 2023, 50(15): 223-226.
[15] 李春梅, 何洪, 李元, 等. “新工科”背景下材料类专业“虚实互补”实验教学体系深化研究[J]. 西南师范大学学报(自然科学版), 2020, 45(4): 143-148.
Li Chunmei, He Hong, Li Yuan, et al. In-depth study on experimental teaching mode with virtual simulation and actual experiments complementing each other in materials specialty[J]. Journal of Southwest China Normal University (Natural Science Edition), 2020, 45(4): 143-148.
[16] 柳红东, 韩涛, 胡荣, 等. 基于人工智能和大数据技术的材料科学与工程专业课程体系的改革研究[J]. 广东化工, 2021, 48(16): 263-265.
[17] Cheloee Darabi A, Rastgordani S, Khoshbin M, et al. Hybrid data-driven deep learning framework for material mechanical properties prediction with the focus on dual-phase steel microstructures[J]. Materials, 2023, 16(1): 447.
[18] 朱贺, 徐涵, 赵庆. 基于改进神经网络算法的中碳钢热处理工艺参数预测方法研究[J]. 山西冶金, 2024, 47(3): 10-13.
Zhu He, Xu Han, Zhao Qing. Research on process parameter prediction method of medium carbon steel heat treatment based on improved neural network algorithm[J]. Shanxi Metallurgy, 2024, 47(3): 10-13.
[19] 王雪. 基于卷积神经网络的金相分析与品质评价技术研究[D]. 兰州: 兰州理工大学, 2019.
Wang Xue.Research on metallographic analysis and quality evaluation technology based on convolutional neural network[D]. Lanzhou: Lanzhou University of Technology, 2019.
[20] 张永志, 辛全忠, 王永亮, 等. 基于迁移学习的钢金相组织分类与识别方法的研究[J]. 材料导报, 2021, 35(24): 24152-24157.
Zhang Yongzhi, Xin Quanzhong, Wang Yongliang, et al. Research on classification and recognition method of steel metallographic structure based on transfer learning[J]. Materials Reports, 2021, 35(24): 24152-24157.
[21] 崔忠圻, 刘北兴. 金属学与热处理原理[M]. 哈尔滨: 哈尔滨工业大学出版社, 2016: 230-242.
[22] 宋孟, 白凤梅, 周红伟, 等. 虚拟仿真实验教学平台在材料成型及控制工程专业实验教学中的应用[J]. 安徽工业大学学报(社会科学版), 2021, 38(1): 80-81.
Song Meng, Bai Fengmei, Zhou Hongwei, et al. Application of virtual reality experimental teaching platform in experimental teaching of material forming and control engineering[J]. Journal of Anhui University of Technology (Social Sciences), 2021, 38(1): 80-81.
[23] 赵隆, 韩小稚, 王景人, 等. 基于卷积神经网络的12Cr1MoV钢金相组织球化级别智能化分析[J]. 中国特种设备安全, 2024, 40(3): 80-83.
[24] 张永志, 李旭英, 辛全忠, 等. 自组织CNN建模识别耐热钢金相组织研究[J]. 材料导报, 2022, 36(12): 160-165.
Zhang Yongzhi, Li Xuying, Xin Quanzhong, et al. Research on self-organized CNN modeling to identify metallographic structure of heat-resistant steel[J]. Materials Reports, 2022, 36(12): 160-165.
[25] 马佳琪, 滕国文. 基于Matplotlib的大数据可视化应用研究[J]. 电脑知识与技术, 2019, 15(17): 18-19.

新工科背景下AI赋能《金属材料及热处理》实验教学改革探索

An exploration of AI-empowered experimental teaching reform in "Metallic Materials and Heat Treatment" under background of emerging engineering education

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价