CIESC Journal ›› 2025, Vol. 76 ›› Issue (3): 1093-1101.DOI: 10.11949/0438-1157.20241001

• Process system engineering • Previous Articles     Next Articles

Machine learning-assisted high-throughput screening approach for CO2 separation from CO2-rich natural gas using metal-organic frameworks

Yinjie ZHOU(), Sibei JI, Songyang HE, Xu JI, Ge HE()   

  1. School of Chemical Engineering, Sichuan University, Chengdu 610065, Sichuan, China
  • Received:2024-09-05 Revised:2024-09-20 Online:2025-03-28 Published:2025-03-25
  • Contact: Ge HE

机器学习辅助高通量筛选金属有机骨架用于富碳天然气中分离CO2

周印洁(), 吉思蓓, 何松阳, 吉旭, 贺革()   

  1. 四川大学化学工程学院,四川 成都 610065
  • 通讯作者: 贺革
  • 作者简介:周印洁(2001—),女,硕士研究生,zhouyinjie1@stu.scu.edu.cn
  • 基金资助:
    国家重点研发计划项目(2021YFB40005)

Abstract:

Driven by the goal of carbon dioxide peaking and carbon neutrality, it is of great social and economic significance to develop green chemical technologies, such as the substantial use of H2 generated by water electrolysis with offshore wind power and CO2 separated from CO2-rich natural gas to produce green methanol is gaining significant socioeconomic and environmental relevance. However, how to efficiently separate carbon dioxide from marine carbon-rich natural gas has become a key technical difficulty. Conventional high-throughput screening methods for metal organic frameworks (MOFs) to separate actual natural gas component CO2 face the problems of high model complexity and long solution time. Therefore, a machine learning-assisted high-throughput screening strategy is proposed. The R2 values on the training set and the test set are more than 0.98 and 0.92, respectively, which can be used to quickly and efficiently separate CO2 from the actual natural gas of six components (N2, CO2, CH4, C2H6, C3H8, H2S).

Key words: metal-organic frameworks, high-throughput screening, CO2 separation, machine learning, molecular simulation, CO2-rich natural gas

摘要:

在碳达峰和碳中和目标的推动下,开发绿色化学技术,如利用海上风电电解水生产的绿色氢气和从富碳天然气中分离出来的CO2合成绿甲醇具有重要的社会经济意义。但如何高效分离海洋富碳天然气中的二氧化碳成为其中的关键技术难点,常规的高通量筛选方法用于金属有机骨架(MOFs)分离实际天然气组分CO2面临着模型复杂性高、求解时间长的问题。提出了一种机器学习辅助的高通量筛选策略,其在训练集和测试集上的R2值分别超过了0.98和0.92,可用于快速从富碳天然气六元混合物(N2、CO2、CH4、C2H6、C3H8、H2S)中分离出CO2

关键词: 金属有机骨架, 高通量筛选, CO2分离, 机器学习, 分子模拟, 富碳天然气

CLC Number: