大学化学 >> 2025, Vol. 40 >> Issue (9): 148-155.doi: 10.12461/PKU.DXHX202412099

所属专题: AI赋能化学教育

专题 上一篇    下一篇

人工智能在科学研究中的融合创新应用——以双碳目标背景下的二氧化碳电催化还原为例

张浩然, 金亚鑫, 康鹏, 张生   

  1. 天津大学化工学院, 绿色合成与转化教育部重点实验室, 天津化学化工协同创新中心, 天津 300072
  • 收稿日期:2024-12-20 录用日期:2025-04-15 发布日期:2025-09-16
  • 通讯作者: 张生, 康鹏 E-mail:sheng.zhang@tju.edu.cn;kang.peng@tju.edu.cn
  • 基金资助:
    国家重点研发项目(2023YFA1507901);国家自然科学基金项目(22478289);国家自然科学基金项目(22078232)

The Convergence and Innovative Application of Artificial Intelligence in Scientific Research: A Case Study of Electrocatalytic Carbon Dioxide Reduction in the Context of the Dual-Carbon Strategy

Haoran Zhang, Yaxin Jin, Peng Kang, Sheng Zhang   

  1. Key Laboratory for Green Chemical Technology of Ministry of Education, Collaborative Innovation Centre of Chemical Science and Engineering, School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
  • Received:2024-12-20 Accepted:2025-04-15 Published:2025-09-16
  • Contact: Sheng Zhang, Peng Kang E-mail:sheng.zhang@tju.edu.cn;kang.peng@tju.edu.cn

摘要: 在全球人工智能技术飞速发展的大背景下,高校应如何应对时代命题,将传统科学研究与人工智能结合起来,快速拓展工科研究生的视野,激发其创新思维,提高创新产出效率,为国家和社会培育出复合型人才,是目前高校教育所面临的重大挑战。鉴于此,本文以双碳目标背景下的二氧化碳电催化还原为例,阐述科学研究融合人工智能提高科研产出和准确性的重要性,总结了人工智能(AI)计算帮助筛选和预测高性能催化剂,帮助研究者深入理解复杂反应机理,优化电解液和设计实验方案等应用,促进了多学科交叉融合,为高校工科研究生实验入门提供参考。

关键词: 人工智能, 二氧化碳电催化还原, 碳中和, 催化剂筛选, 电解液优化, 反应机理研究, 实验方案设计

Abstract: Against the backdrop of rapid advancements in artificial intelligence (AI) technology worldwide, universities face significant challenges in addressing contemporary issues by integrating traditional scientific research with AI. This integration aims to broaden the perspectives of engineering graduate students, stimulate innovative thinking, enhance the efficiency of innovative outputs, and cultivate versatile talents for national and societal needs. This paper, using electrocatalytic carbon dioxide reduction (CO2RR) within the framework of carbon neutrality as a case study, underscores the importance of merging scientific research with AI to augment research output and accuracy. It highlights how AI computing facilitates the screening and prediction of high-performance catalysts, deepens the understanding of complex reaction mechanisms, optimizes electrolytes, and aids in experimental design. Furthermore, it promotes interdisciplinary collaboration and serves as a reference for engineering graduate students embarking on experimental research in universities.

Key words: Artificial intelligence, Carbon dioxide electrocatalytic reduction, Carbon neutrality, Catalyst screening, Electrolyte optimization, Reaction mechanism research, Experimental plan design